HOME
QUICK SEARCH
AUTHORS
KEYWORDS
HELP
BUGSSAS Explore 2023 Papers - Index
101 papers. Source: SAS Explore conference proceedings.
| # | Title× | Authors× | Abstract× | Keywords× | Extras | Pages |
|---|---|---|---|---|---|---|
| 1 | 7 Key Points about the Digital Ecosystem and Fraud Trends in Banking | Gökhan Dumrul | Presentation: In the financial sector, corporations must attract customers' attention by announcing new and innovative banking products or improving the user experience. While allowing customers instant access to products and services, this digital transformation has increased their vulnerability to fraud. This session proposed an effective approach for addressing and managing counter-fraud risks within the financial sector. Discussion points: Presentation slides are attached to this post. | source | ||
| 2 | A College Professor's Journey to SAS Viya From SAS Enterprise Miner and Beyond | Cali M. Davis | Presentation: From the impressiveness of pattern discovery and the interactive decision tree growth to running multiple predictive models at one time fairly quickly, data mining would never be the same as those very early days of SAS Enterprise Miner in 2002. Fast-forward to over 20 years later when SAS Enterprise Miner is still around, but a new tool has been added to the toolbelt. SAS Viya offers some of the same functionality that made SAS Enterprise Miner so desirable for data miners, but it now includes a whole new world of reimagined tools for data analytics professionals. Undergraduate students in two data mining classes were the test groups for determining the best tools to use as part of a university's new Academic Program partnership with SAS. One class used SAS Enterprise Miner, and the other used SAS Viya for an entire semester. Students were given similar projects and asked to evaluate their experiences at the end of the course. The results of this analysis will be shared during this presentation. As a preview of the results, SAS makes data mining easy, no matter the tools! Hear from a longtime academic user of SAS about my journey through learning SAS, teaching SAS, getting certified in SAS and growing along with the company. | source | ||
| 3 | A Digital Twin Solution | Vyacheslav Zakharov, Erdni Okunov, Murzabayev Mestay, Madi Albek, Nerses Avetissov, Tatyana Savitskaya |
Presentation: We developed a solution to optimize mining production equipment operation using machine learning and optimization algorithms. Using SAS Viya, we created predictive models for key operational parameters. The models are integrated into an optimization task that seeks the best operation parameters based on set constraints and goals. Implementing these recommendations could increase processing volume by 1-2%, improve quality by 3-4%, and reduce energy consumption by 1.5%. This solution can easily be applied to other types of equipment and process steps. Presentation slides are attached to this post. | source | ||
| 4 | A Hybrid Setup as an Intermediate When Migrating to SAS Viya on Kubernetes | Stephan Minnaert | Presentation: At a customer site, we were asked to update their SAS environment. The version was a SAS 9.4 M3 BI Server installation. The customer was already using the opportunities of SAS Visual Analytics. They were also still using Web Report Studio for many reports. Several thousands of jobs had been built using Data Integration Studio, using various standard and non-standard transformations. This presentation addressed the challenges we faced when researching how to approach the migration to SAS Viya. We wanted to use Viya primarily for reporting and advanced analytics. Since many of the data preparation steps available in SAS Data Integration Studio are not yet available in SAS Viya, we opted for a hybrid installation with SAS 9.4 M7/8. That would give us time to evaluate the performance of SAS Viya and start preparation for the migration of data preparation jobs as soon as more functionalities become available. We have migrated all reports to SAS Viya successfully. Our focus is redirected to upgrading our SAS9 environment, which will integrate far better with SAS Viya. The goal for the coming years is to start migrating from SAS9 to SAS Viya for all data preparation jobs as soon as new functionality is added. The customer can create better insights with the new options that SAS Viya offers. Presentation slides are attached to this post. | source | ||
| 5 | Activating Cloud-Based Customer Data That Enables Responsible Marketing | Mark A. Chaves | Presentation: For all industries, effectively managing and activating your customer data has long been a critical ingredient for establishing a competitive advantage. By meeting your customers where they are in their buying cycle and journey, you can connect on a deeper level to better anticipate and respond to their needs. In this session, we will discuss data management and control supporting marketing communications across all customer touchpoints. Customer Data Platforms (CDPs) allow you to manage access to customer data while meeting compliance requirements and driving growth for your business. We will share best practices and demonstrate the power of: • Collecting and managing customer data across public/private clouds and on-premises environments. • Designing advanced segments and target audiences based on a variety of sources. • Orchestrating personalized consumer experiences and journeys that use customer data in a responsible manner. We look forward to sharing best practices around data and audience management while providing "how to" instruction with SAS Customer Intelligence software. | source | ||
| 6 | Actual Operationalization of Health Care Data with the Help of SAS Viya | Dennis Menkveld | Presentation: To operationalize the usage of health care data and AI models in the clinic, PW Consulting collaborated with SAS and Erasmus MC, one of the top Academic Medical Centers in the Netherlands, to start an IT and health project in an ICU department. Hospitals often lack the ability to use the data that is present or deploy AI models and make them applicable. They struggle to operationalize their health data, make their processes more efficient, reduce costs and increase health workers' time spent on patients. This presentation will describe the outcome of that project, demonstrate the solution built in SAS Visual Analytics with data-driven content and share insights into future improvements. The solution combines dashboards supported by ETL, analytics and AI models that are developed in a governed and validated environment and aligned with the ICUs and MCs' primary health processes. The first phase of the solution is fundamental to the data platform, and it is designed for scalability, where it can be easily enriched with more information from SAMDs, other data points and patient parameters or new departments. This initiative is an important step to operationalize health data and to support operational efficiency, better clinical decision making and improve the quality and patient safety. | source | ||
| 7 | Advanced Spatial Data Visualization and Analysis With SAS Visual Analytics | Falko Schulz | Presentation: Governments and businesses all over the world make geographic data available for analysis. The amount of data available is growing year by year. In this presentation, you will learn how to master different types of spatial data with SAS Visual Analytics. Discover how to use special polygon and polyline data and how to apply advanced mapping techniques for better spatial data visualization and analytics. Explore how SAS Visual Analytics can be used to interact with geographical maps, how to apply advanced analytics to your spatial data, and how to customize map features for navigational routing and distance calculations. The presentation will cover advanced spatial use cases, from building and floor plan mapping and traffic monitoring to visualizing flood-level predictions. You will learn how each example converts basic location data into enriched, decision-supporting visuals backed by state-of-the-art AI and machine learning routines. Let's make spatial data accessible! | source | ||
| 8 | AlgoWatt: Leveraging Analytics for Energy Community (EC) Planning and Operation | Vijayan Sugumaran | Presentation: Learn how we leveraged data-intensive analytics for optimal integration of renewable Distributed Generation (DG) and storage in distribution networks for optimized Energy Community (EC) planning, sizing and operation. Energy Communities aim to foster Distributed Generation by supporting generation and simultaneous consumption at the local level to avoid impacts on the distribution (and even transmission) network. Current regulation requires EC to be bounded to the grid portion fed by a single primary substation, which can be a pretty large portion of the network with several different constraints (cable sizing, load distribution, etc.) in different areas. We wanted to identify analytic methods to specify the maximum DG hosting capacity of the different portions of the network, considering hardware constraints, load models and DG installation forecast at a fine grain level in the network. We also wanted to characterize distribution network voltages without electrical models. The growing uptake of PV forces distribution companies to estimate network voltage rise issues for operation and planning. Voltage calculations are based on power flow analyses and require detailed, complex three-phase electrical models, which are not readily available for most distribution companies. We focus on capturing the nonlinear relationships among the historical data (demand and voltages) and the corresponding feeders. | source | ||
| 9 | An End-to-End Case Study on Flooding Based on ML, Forecasting, Optimization and Spatial Data | Carlos Pinheiro | Presentation: Flooding is a common threat worldwide. Knowing what happens in case of such events can increase the chances of human survival and property protection. The team performed data connectivity, metadata discovery, data quality inference and data exploration on the data sources to better understand the main features associated with flooding events over time. We created several machine learning models to predict flooding events, compared them and published champion and challenger models. Flooding is all about mitigating and anticipating events to help people. In addition to the ML models to predict flooding events, we developed additional models to mitigate damage and help people. We developed an optimization model to identify the optimal flows to evacuate displaced people to public shelters based on their capacity and distance. We also developed an optimization model to find the optimal routes and trips to evacuate displaced people to the identified shelters based on the number of vehicles available and their capacity. The team created a forecasting model with autocorrelation analysis to identify a set of parameter estimates associated with variables that impact the likelihood of flooding events. A what-if analysis was created to simulate the impact of flooding events while changing the values of the significant variables. Finally, a regression model on referenced spatial data was developed to estimate possible locations within hurricane paths to prepare a set of mitigation actions to help people in danger. | source | ||
| 10 | Analyzing Social Media Signs of Self-Loathing to Support Better Mental Health | Elwira Gliwska, Klaudia Barańska, Michał M. Klos |
Presentation: The internet is flooding our minds with content. Consuming content with "body hate" themes may result in disorders including depression, anorexia and even suicide. Flagging body hate may contribute to a healthier online presence, prevent such disorders, reduce the demand for costly treatments or even increase revenue from content platforms. In this session, we'll walk through our hackathon project addressing "body hate" flagging with a custom machine learning model powered by a SAS suite. Presentation slides are attached to this post. See the full video of the SAS Hackathon entry in the Hacker's Hub . | source | ||
| 11 | Arrow/Parquet in SAS Compute | Jerry Adair | Presentation: If you want to use SAS to perform data analysis but want your data stored in the Parquet on-disk format rather than the traditional sas7bdat format, this presentation is for you. Parquet is an open source on-disk format that has been traditionally utilized in a Hadoop context but can exist outside a Hadoop cluster. Arrow is the in-memory variant of the associated technology. Both are columnar data stores and yield more efficient data query performance. For these reasons, Arrow/Parquet has gained popularity throughout the data analytics community. Learn about the Arrow/Parquet feature that you can use while continuing to conduct analysis with SAS. Presentation slides are attached. See also Parquet Support in SAS Compute Server . | source | ||
| 12 | Best Practices When Planning for Your Migration From SAS9 to SAS Viya | Steven Sober | Presentation: Create a data-driven SAS9 to SAS Viya migration plan with SAS9 content assessment and SAS Enterprise Session Monitor results. Using SAS9 content assessment, a collection of applications designed to examine the characteristics of your SAS9 system, and SAS Enterprise Session Monitor, an offering designed to collect real-time workload data, you'll know the facts to make sizing decisions for SAS Viya, including what you use and who is using it. Presentation slides are attached. | source | ||
| 13 | Constituent Journey Management and Digital Personalization With The Nature Conservancy | John Blackwell | Presentation: The Nature Conservancy (TNC) is a global environmental nonprofit working to create a world where people and nature can thrive. TNC is one of the most effective and wide-reaching environmental organizations in the world. TNC uses SAS Customer Intelligence 360 and SAS Viya to maximize donations from more than a million members worldwide through email, phone, mail, digital ads and other channels. SAS' customer data platform capabilities, which aggregate and contextualize first-party and third-party assets, have been key to this initiative. This enables TNC to combine offline data with digital campaign data and web analytics into a single member profile, creating insights to learn from and act on. The content shared in this session: • Introduced TNC and its approach to data management, customer analytics and integrated marketing. • Strategically described how SAS is used for audience segmentation and paid media targeting. • Demonstrated how both marketers and analysts can use SAS to capture first-party data from owned digital properties, derive both rules-based and algorithmic segments, integrate with Google and Facebook Ads and orchestrate contextual personalization beyond ad impressions/clicks for the acquisition of new constituents while engaging current members. Presentation slides are attached to this post. When the ultimate goal is protecting the natural world, working more efficiently to increase fundraising revenue translates into a brighter future for the planet. John Blackwell, The Nature Conservancy | source | ||
| 14 | Cracking the (Supply) Chains: Data-Driven Strategies for Combating Modern-Day Slavery | Becky Lorig, Zoraya Cruz-Bonilla, Arpita Deb |
Presentation: There are more than 27 million people in situations of forced labor worldwide on any given day. The international charity Hope for Justice and social enterprise Slave-Free Alliance strive for data-driven approaches to help organizations move toward slave-free operations and supply chains. By leveraging a suite of business intelligence, open source and advanced analytics, disparate data sources, such as PDF documents, can be mined for patterns to detect possible exploitation in difficult-to-track supply chains. Our team integrated Power Query and Python to extract and transform unstructured data and SAS Visual Text Analytics on the SAS Viya platform to develop a deeper understanding of the data through natural language processing techniques. We discovered emerging textual themes and patterns through our text analytics life cycle approach. Our team used the prevalence of specific concepts and existing text-based knowledge to suggest commodities and industries with an increased risk of forced labor due to supply chain complexity and lack of oversight when products frequently changed hands. To convey our findings and maximize the range of capabilities the SAS ecosystem offers, we deployed an interactive dashboard to further explore forced labor based on country and commodity. We applied these insights to a risk assessment tool for organizations to mitigate or build resilience against modern-day slavery. | source | ||
| 15 | Customize Your Way to Success: Using Custom Steps From the SAS GitHub Repository in SAS Studio | Mary Kathryn Queen | Presentation: SAS Studio Custom Steps enable you to create a user interface for users at your site to complete a specific custom task. There is a public GitHub repository of these custom steps designed by both SAS employees and other customers that you can import and use at your site. You can use them as designed or tweak them to fit your specific use case. In this presentation, you will learn how to access this public GitHub repository of custom steps and import them into your environment. This demonstration will use two custom steps from the public GitHub repository in a SAS Studio Flow that anonymizes a column in the input data, creates a new output table, and then sends an email that the output is ready for viewing. | source | ||
| 16 | Data for Good: Galapagos Sea Turtles | Jonny McElhinney | Presentation: As part of the Data for Good initiative, a team of SAS volunteers has collaborated with the Center for Galapagos Studies at UNC-Chapel Hill to help researchers identify and protect the native sea turtle population. During the last 10 years, researchers have captured photographs of hundreds of turtles, generating over 33,000 images. Each turtle has its own unique set of facial scales that can be used to identify it. Researchers want to utilize computer vision to identify individual turtles to help create an animal health index to track growth rates, health threats and presence data to understand temporal and spatial movement patterns. | source | ||
| 17 | Deploying and Managing SAS Viya 4 Using DevOps Pipelines | Tom Dogger | Presentation: Notilyze hosts and manages SAS Viya 4 environments in their own data center, in the public cloud (fully managed in our tenant or in the customer's tenant), and in customers' on-premise infrastructure. To deploy and manage these environments, Notilyze has developed DevOps pipelines to automate as many tasks as possible. This presentation outlines these pipelines and lessons learned from deploying and managing SAS Viya through these pipelines. Presentation slides are attached to this post. | source | ||
| 18 | Developer.sas.com 2.0: The Relaunch of the SAS Developer Portal | Joe Furbee | Presentation: We're almost there..... This session provided an overview of the new SAS developer portal, developer.sas.com. SAS recognizes the importance of integration with open source technologies and is investing in a world-class developer portal that will help developers work with SAS in new and exciting ways. The updated portal focuses on SAS APIs and use cases. It also provides resources for open source integration with SAS, SAS Viya programming, SDKs and other SAS solutions - all focused on the developer's perspective. The session began with an overview of what a developer portal is and what components make up a good portal. We discussed the intended personas for the site and affirm the various audiences who will use the resource. We walked through the site and demonstrate many of the components and functionality discussed earlier. We wrapped up the session with a talk about the site's future as we continue to develop and expand. The new developer portal is a highly anticipated resource, and we can't wait to show it off. Here's a recording of a tour of the new developer.sas.com. (function() { var wrapper = document.getElementById('lia-vid-6337805340112w1326h720r525'); var videoEl = wrapper ? wrapper.querySelector('video-js') : null; if (videoEl) { if (window.videojs) { window.videojs(videoEl).ready(function() { this.on('loadedmetadata', function() { this.el().querySelectorAll('.vjs-load-progress div[data-start]').forEach(function(bar) { bar.setAttribute('role', 'presentation'); bar.setAttribute('aria-hidden', 'true'); }); }); }); } }})(); (view in My Videos) And here's the new developer portal in action with an API use case. (function() { var wrapper = document.getElementById('lia-vid-6337806205112w994h540r634'); var videoEl = wrapper ? wrapper.querySelector('video-js') : null; if (videoEl) { if (window.videojs) { window.videojs(videoEl).ready(function() { this.on('loadedmetadata', function() { this.el().querySelectorAll('.vjs-load-progress div[data-start]').forEach(function(bar) { bar.setAttribute('role', 'presentation'); bar.setAttribute('aria-hidden', 'true'); }); }); }); } }})(); (view in My Videos) | source | ||
| 19 | Developing AI for Food Production Yield and Quality Optimization With SAS Viya | Colin Nugteren, Quinten van Dissel |
Presentation: Notilyze built an AI platform for a large cheese factory using SAS Viya. We collect, visualize and analyze all sensor and operator data in real time. We built the user interface using Microsoft technology and used SAS Studio flows, SAS Visual Analytics and SAS Visual Statistics, Model Studio, and SAS Intelligent Decisioning to optimize the manufacturing process. The operators and process technologists use the final solution to save time while significantly improving yields. We faced challenges with the large scale of the data, including 6,500 sensors and integrating SAS in the final product on a scalable infrastructure. This presentation shows the power of the full SAS Viya platform in developing AI for a specialized industry. | source | ||
| 20 | Developing Lightweight, Cloud-Native Applications Powered by SAS AI | Saurabh Mishra | Presentation: Are you looking to empower your business users with AI and analytics-powered applications that don't require data science teams to get involved or IT teams to manage? This session introduced the concept of developing lightweight, cloud-native apps underpinned by SAS' industry-leading AI, using SAS Viya App Factory. Viya App Factory is an app development platform that streamlines the development, deployment and operations of cloud-native apps built using existing or new analytic IP developed with SAS. With its IDE-like interface, developers can quickly assemble essential components such as the user interface, authentication provider, SAS AI-powered compute, database and file server. In this session, we will explore the example of one of SAS' existing industry solutions, SAS Energy Forecasting, and walk through transforming it into a SaaS app powered by the same market-leading Forecasting capabilities using Viya App Factory. Presentation slides are attached to this post. | source | ||
| 21 | Developing Purpose-Built Applications With SAS | Pavan Kapur, Malorie Robinson |
Presentation: Caesars Entertainment is using SAS Viya for charter flight scheduling analytics to more strategically schedule flights to maximize profitability. SAS worked alongside the business to fully understand its process. Change management, trust in analytics and business context were all very important. Throughout the process, these factors were addressed head-on and a joint solution was created. Now the scheduling solution is deployed in production, saving the charter team substantial time in scheduling and driving additional profitability of the charter program. | source | ||
| 22 | Embracing and Enhancing Open Source Algorithms in SAS Viya 4 | SAS Institute | Presentation: Data scientists and organizations have increasingly been interested in taking advantage of open source technologies and algorithms. While SAS Viya offers many ways for integrating with open source, SAS also internally incorporates and enhances various methods with open source roots to ensure that best-in-class technology is readily available in the SAS Viya platform. In this session, the presenters discussed some high-performance methods that Viya 4 has incorporated and will showcase the improvements in these methods from their open source beginnings. Examples include light gradient boosting machine (lightGBM), tabular data generation using generative adversarial networks, fast multi-core TSNE for data clustering and exploration and CSPADE for efficient frequent sequential pattern mining. Presentation slides are attached to this post. | source | ||
| 23 | Embracing the Power of Now: Real-Time Predictive Analytics With SAS Viya | Chalamayya Batchu, Sam Coyne, Ron Oudenaarden |
Presentation: In today's fast-paced manufacturing landscape, Georgia-Pacific recognizes the critical need for real-time decision making to drive operational excellence and maintain a competitive edge. This presentation focused on how to use the power of SAS Viya, an advanced analytics platform, to address the problem of outdated insights and unlock the potential of real-time predictive analytics in our manufacturing operations. Through real-world use cases and practical implementation considerations, the presenters illustrated how to optimize production processes, detect anomalies, predict maintenance needs and enhance quality control and supply chain management using real-time data. Attendees gained valuable insights and actionable strategies to apply within their organizations, empowering them to overcome the challenges of lagging insights and embrace the power of real-time predictive analytics. The presenters shared their experience so that the audience learned they could revolutionize their manufacturing operations with real-time decision making. Presentation slides are attached to this post. | source | ||
| 24 | Enabling Hybrid Cloud With SAS Cloud Data Exchange | Robin Thomson | Presentation: In this presentation, you will learn how to easily access data that remains on-site or on other public clouds using SAS Viya deployed in the cloud and Cloud Data Exchange. Following the presentation, you will better understand how Cloud Data Exchange can be deployed and the scenarios it covers, and start planning how you can use it. | source | ||
| 25 | Enhance Forecasting Accuracy With Time-Series Segmentation and Machine Learning | Spiros Potamitis | Presentation: It is important to segment time series into groups and model each group separately to enhance forecasting accuracy overall. But what does this look like in practice? Why not use an automated machine learning (AutoML) package or an auto-forecasting tool and let it do the hard work for you? We know that the best modeling technique is always based on the data we are dealing with. Machine learning methods have been proven useful for forecasting purposes, but they are computationally intensive and many times fail to outperform in accuracy simple statistical methods. This session explored how demand classification in SAS Visual Forecasting can group time series based on their historical demand patterns, allowing users to apply the most appropriate modeling technique to each segment. This optimizes the forecasting process, increases accuracy and speed, and leads to better decisions in a cost-effective way in the cloud. Presentation slides are attached to this post. | source | ||
| 26 | Ensuring Fairness in Fraud Detection Process Using Network Analytics | Luiz Kauffmann, Aline Riquetti |
Presentation: In the dynamic field of fraud detection, utilizing network analytics empowers our customers to delve into the intricate relationships and patterns within networks, including financial transactions, customer interactions and digital connections. By harnessing the power of network analytics, organizations gain the ability to identify suspicious behaviors and anomalies that may signify fraudulent activities. Additionally, the network enables the discovery of concealed relationships, exposing fraud rings and facilitating the proactive detection of emerging fraud trends. In this presentation, we will showcase how network analytics can play a vital role in detecting and addressing bias and ensuring fairness throughout data-driven strategies, particularly in the digital loan origination process. We will demonstrate how customers can leverage the visual network capabilities of SAS Visual Investigator to conduct counterfactual analysis, employing this tool to mitigate bias and evaluate fairness. | source | ||
| 27 | Event-Based Intelligent Decisioning | Diana Maris, Steven Allan |
Presentation: Companies need to respond to events in the digital world quickly to draw value out of their investments. The sources these events are coming from are also on the rise, with more and more solutions and processes becoming digitalized. Examples include clicks and user journeys through a web app or website, like loan and credit applications, interactions in CRM tools and IoT sensors in manufacturing or environmental tracking. Many situations require an immediate response, including providing a contextual and customized offer, detecting fraud, responding to defective machinery in the production line, a customer complaint or a natural disaster. With a combination of SAS Event Stream Processing and SAS Intelligent Decisioning, avoid delays in decision making and take action in the moment. This approach takes advantage of the high-throughput, low-latency capabilities of SAS Event Stream Processing to read streaming data, filter events of interest or identify anomalies and then pass that information to SAS Intelligent Decisioning for real-time decisions based on business rules and sophisticated analytics at scale, which can be consumed from a multitude of applications. The two products can directly integrate through a native REST API-based adapter and, coming soon, through Kafka topics. This presentation discusses the power of SAS Event Stream Processing and SAS Intelligent Decisioning using scenarios from banking and marketing. Presentation slides are attached to this post. | source | ||
| 28 | Five Reasons to Swipe Right on PROC FCMP | Troy Martin Hughes | Presentation: PROC FCMP (aka, the SAS function compiler) empowers SAS practitioners to build their own user-defined functions and subroutines, which are reusable software modules that containerize discrete functionality and extend the Base SAS programming language. This session, taught by the author of the 2023 SAS Press PROC FCMP book, explored five problem sets that user-defined functions can solve. Learn how to hide a hash object (and its complexity) inside a function, how to design a format (or informat) that calls a function and how to run a DATA STEP (or SAS procedure) inside a DATA STEP using RUN_MACRO! Software quality characteristics will also be showcased, including modularity, flexibility, configurability, reusability and maintainability, which are improved through the design and implementation of PROC FCMP user-defined functions. Presentation slides are attached to this post. |
source | ||
| 29 | Generating Better Synthetic Data | Robert Blanchard | Presentation: This presentation combined three techniques to generate better synthetic data. Active sampling, tabular GAN and SAS autotuning can generate data that improves a model's prediction task. A variation of query by committee written in SAS will be used to subsample a relevant data representation. A sample of cases near the decision boundary for the problem at hand will be drawn. Sampling the data in this manner will reduce the number of observations to only those most relevant to the problem, improving the signal and reducing the computational burden on the GAN. Tabular GAN will learn representations from only the subsampled data. Participants will see how we can leverage autotuning to tune the tabular GAN model to produce better synthetic representations where autotuning will maximize the error of a pseudo discriminator that attempts to distinguish between real and artificial data. Participants can apply what they learn to most supervised learning problems. This presentation combined key SAS technologies in a way that can benefit most data scientists working on supervised learning problems. Presentation slides are attached to this post. | source | ||
| 30 | Getting Full Value Out of the Analytics Life Cycle with SAS Intelligent Decisioning | Diana Maris | Presentation: Enterprises are embarking on analytics journeys across regions and domains as part of their digital transformation and evolution. They are faced with scalability, automation and governance challenges; a variety of execution targets; complex interfaces; and the lack of a unified platform. This impacts productivity and creates a gap between data engineers, data scientists, IT and business. As a result, companies are not getting full value from their investments in analytics. In the analytics life cycle, value means making confident, informed decisions in the moments that matter using AI-driven insights. With 42% of data scientists reporting their models don't get used by decision makers, it seems organizations can envision their victory, which translates to increased operations efficiency, customer loyalty, higher market standings, achieving compliance, reduced risk and fraud, and quicker responses in high agility environments, but they can't yet attain it. SAS Intelligent Decisioning (SID) is a leader in AI decisioning platforms and helps enterprises achieve value through operationalizing models seamlessly and at scale, offering a low-code, intuitive interface that boosts productivity and bridges the gap between all analytics and decision makers. This session will give an overview of SID and how to get started, and show examples of capabilities that counteract challenges across the analytics life cycle. | source | ||
| 31 | Guarding Secrets in SAS Programs With Azure Key Vault | Bogdan Teleuca | Presentation: In the ever-evolving landscape of application security, inadvertently exposing sensitive information like API keys, database credentials or private keys remains a critical mistake. With code repositories like Git being widely used, secrets can easily infiltrate your code base, whether it's SAS, Python or any other files, leaving your application vulnerable. Azure Key Vault is a powerful solution to prevent this security pitfall. By integrating a key vault into your development process, you can eliminate the need to store secrets in your code files. This straightforward yet highly effective approach draws inspiration from real-life scenarios: Keep your valuable assets secure and retrieve them only when necessary. Azure Key Vault provides robust protection against accidental leaks, significantly reducing the risks of compromising sensitive information. This SAS Explore presentation delved into the methods of safeguarding your code base by seamlessly retrieving secrets from an Azure Key Vault within SAS programs. Explore utilizing the Key Vault Python library, REST APIs or the Azure CLI when submitting SAS programs in batch. Bid adieu to the perils of secret exposure and elevate your code base to a secret-proof state with Azure Key Vault. | source | ||
| 32 | Health Monitoring to Prevent Solitary Death | Keisuke Fukunaga, Michito Taga, Ken Yonezawa |
Presentation: In Japan, a significant number of people die alone, exceeding 25,000 annually. There is a tendency for a considerable delay before these deaths are discovered, with an average duration of two weeks. While this issue is often perceived as mainly affecting the elderly, 40% of those dying alone are under 59, indicating that it's not just an issue for the older population. A proposed solution involves using smartphones to take self-portraits, from which the user's posture and vitals can be estimated. The system will notify the user's friends or family if it detects a potentially dangerous situation. Traditional monitoring services often involve difficult equipment installation and can result in being watched by strangers, which many people find uncomfortable. This suggested solution resolves these issues typically associated with conventional monitoring services. In this presentation, a SAS Hackathon entry, the presenters developed a use case for preventing solitary deaths. However, there are many other potential applications, such as health checks for construction site workers. In the future, we aim to achieve this by creating a structure that combines streaming processing features like ESP. Presentation slides are attached to this post. | source | ||
| 33 | How Compliance Teams Can Use Analytics to Navigate ESG Risks in Supply Chains | Rupesh Shah, Balaji Soundararajan |
Presentation: This SAS Explore session provided insights for companies looking to utilize compliance data to understand and mitigate environmental, social and governance (ESG) risks in their supply chains. Topics covered include concepts from data management on audit data gathering and sharing, basic types of data required, types of ESG risks that can be measured, and SAS tools and methodologies. Presentation slides are attached to this post. | source | ||
| 34 | How to Build a Smart Search System Using SAS Viya With Microsoft Azure and SingleStore DB | Paul Koot, Michel Philippens |
Presentation: SAS and Notilyze collaborated on a pilot project for a Belgian governmental department. A team of legal experts within this department is responsible for responding to policy questions from the Parliament and companies. To guarantee the historical consistency of responses, the legal team members sifted through a database of 30,000 historical questions and answers. Notilyze, SAS and the customer collaborated on the "Smart Search" pilot project to improve the existing Q&A database and search experience. During the pilot project, machine learning and AI techniques were used to automatically extract relevant legal metadata information from documents and to automatically classify legal documents into a granular taxonomy of policy-related topics. In addition, we introduced modern search techniques (TF-IDF, semantic and fuzzy search, and multilingual search) to boost the relevancy of search results. The presenters illustrated how SAS Viya's machine learning and visualization capabilities, Microsoft Azure's cloud computing and AI services, and SingleStore's powerful machine learning database can be combined to provide a next-generation search and information retrieval experience. Presentation slides are attached to this post. | source | ||
| 35 | How to Debug SAS DATA Step | Chris Hemedinger | Presentation: Learn how to use the SAS DATA STEP debugger to save time and become a more productive programmer. You will learn: Presented at SAS Explore 2023 - slide presentation is attached to this article. Learn more at: For completeness, I've also included the animated images used during demonstration. Debug IF vs WHERE (WHERE example) Debug IF vs WHERE (IF example) Setting a conditional breakpoint FIRSt-dot and LAST-dot processing in the PDV Closer look at INFILE and INPUT processing DATA STEP arrays in the Watch window (SAS Studio view) |
source | ||
| 36 | HPE GreenLake Solutions for SAS Analytics | Anshul Nagori | Presentation: HPE GreenLake is the cloud that comes to you and offers modern, reliable and efficient hybrid cloud solutions for SAS to run AI, machine learning and analytics workloads. With data-first modernization and cloud operating experience, HPE GreenLake combines security, flexibility, scalability, ease of management and pay-per-use predictability. Join this breakout session to know more about the leading storage and compute offerings from HPE to run your SAS environments faster and better. | source | ||
| 37 | I Got 99 Problems and Biased AI is #1 | Allie DeLonay | Presentation: AI is helping us to work and live more efficiently, but while AI comes with benefits, it also comes with risks. When data is biased, AI systems created from that data are also biased, which can cause unintended harm to vulnerable populations. Understanding how to prevent and/or mitigate these biases using technical and non-technical solutions will help organizations develop more trustworthy AI applications and reduce the possibility of harm. We will discuss how different types of bias can be unintentionally laced into an AI system and how the SAS analytics platform, SAS Viya 4, allows users to assess the fairness and bias in a model. | source | ||
| 38 | Innovative Approaches to Vehicle Routing Problems | Yan Xu, Rob Pratt |
Presentation: For modern logistics and supply chain management, efficiently solving Vehicle Routing Problems (VRPs) has become an essential task for organizations to ensure timely deliveries, minimize cost, reduce environmental impact and enhance customer satisfaction. In a typical VRP, a set of customers must be assigned to a fleet of vehicles. The vehicles start and end at a common depot and visit all customers once. There are different variants of VRPs, such as Capacitated Vehicle Routing Problem (CVRP) and Vehicle Routing Problem with Profits (VRPP). This presentation first introduces the fundamental aspects of VRPs and their applications. Next, it presents several novel approaches that efficiently solve VRPs with time windows and other constraints. Those new approaches were motivated by real-world use cases and are available in SAS Optimization. | source | ||
| 39 | Installing, Upgrading and Migrating to the Latest Release of SAS 9.4 | SAS Institute | Presentation: This session covered the latest version of SAS 9.4 or the eighth maintenance release of SAS 9.4 (9.4M8 for short), which was released early this year. Presenters discussed its benefits, including significant security upgrades and modernized implementation. Also covered: what is needed for SAS 9.4 customers to create SAS 9.4M8 environments. If you're a SAS user, administrator or an IT professional using SAS 9.4M7 or earlier, or a new SAS9 customer, this post is for you. In addition to highlighting new features and enhancements delivered with SAS 9.4M8, this session shared the best practices for installing, upgrading and migrating to this latest SAS 9.4 release. Presentation slides are attached to this post. | source | ||
| 40 | Interactive Events Management in SAS Visual Forecasting | Joseph H. Katz | Presentation: What are events in time-series data and how do we distinguish them from outliers? We can define an event as any incident that disrupts the normal process that generates a time series. This disruption creates volatility in the data beyond the "normal" pattern or variation. An event can have many different forms including holidays, sales and promotions, natural disasters, public health emergencies, sudden economic and geopolitical changes, etc. The difference between events and outliers in historical data is that events are comprehensible and explainable phenomena that we believe have an impact on the variation of our time series. | source | ||
| 41 | JAWARA: Jakarta Water Resource Analytics | Amir Toha | Presentation: Learn how a SAS Hackathon team created a decision support system for managing floods in Jakarta based on near real-time IoT data capture and advanced predictive analysis. | source | ||
| 42 | Keeping the Lights On With 'Insight-O-Meter', NEC's AI-enabled Prediction Solution for Utilities | Himanshu Shekhar | Presentation: Varying temperatures, a growing population and a changing energy landscape are driving electricity demand higher and higher. This puts more pressure on aging electric grids, causing brownouts, blackouts and forced electricity shortages at peak times and an increase in consumption costs. New technologies are critical to helping power producers and end users better manage, demand and facilitate a reliable electrical grid. This helps ensure consistent availability of electricity and mitigates negative effects of energy generation that can contribute to climate change. NEC's "Insight-O-Meter" is a groundbreaking prediction tool that enables end users to take control of their energy use by providing data that can help reduce their energy footprint and save money. With electricity grids stressed to the max amid record summer heat levels or winter heating needs, NEC's Insight-O-Meter addresses utility challenges holistically, developing technologies to overcome the challenges of a changing climate and grid. For utility providers, the benefit is multifold. The Insight-O-Meter's energy dashboard can compare energy consumption to generation, increasing the ability to adjust generation accordingly and help roll out a time-of-use plan. Insight-O-Meter similarly opens a new world for consumers. By providing key operational insights on their energy consumption through a digital channel, users can cut electricity costs and help ensure energy is reliable and dependable. | source | ||
| 43 | Learn SAS Event Stream Processing Open Source Integration With Git and Grafana on Azure Marketplace | Daniele Cazzari, Steven Allan |
Presentation: SAS Event Stream Processing (ESP), the market-leading platform for developing and operationalizing streaming analytics, is evolving to enhance productivity and facilitate scalable, resilient architecture patterns. This SAS Explore session was on how to package and store streaming projects in Git to facilitate distribution and enhance version control. The presenters introduced a new Grafana plugin that simplifies the visualization of your streaming data, enhancing your streaming application. They also explored the SAS Event Stream Processing Lightweight Kubernetes Architecture, which focuses on delivering essential functionality with fewer resources and reduced complexity. This architecture enables SAS Event Stream Processing on Azure Marketplace, a new delivery method available today that allows you to deploy your streaming environment in minutes and preview all the new ESP features in a ready-to-use environment. Presentation slides are attached to this post. | source | ||
| 44 | Leverage the Power of SAS With SingleStore | Bill Danker | Presentation: Learn how to leverage the power of SAS Viya working directly with data stored in SingleStore's relational database. Viya data science users are familiar with exporting data into a SAS data set and then curating that data with SAS formats, new calculated columns and new data views. Those SAS data sets are a duplication of data from some previous database. But what if everything you do today with a copy of the data could be accomplished without having to extract the data into a SAS data set? What if you could build your visual analytics and models directly on top of data sitting in a database? SAS Viya with SingleStore gives you that exact capability. By using SAS with SingleStore, you can minimize data movement and data duplication and enable multiple data scientists to develop models against one single data source. Learn how this approach can speed up the development of new analytics and simultaneously democratize your data, enabling additional open access to other downstream uses and applications. | source | ||
| 45 | Leveraging SAS Information Catalog REST APIs: Programmatically Discovering Data | Bogdan Teleuca | Presentation: This SAS Explore presentation delved into SAS Information Catalog REST APIs. It showcased how utilizing these REST APIs, accessible from SAS, Python or shell scripts, can unlock the potential of programmatically discovering data. Participants discovered how SAS Information Catalog REST APIs enable searching and identification of files, tables and other assets based on specific criteria. The session provided hands-on demonstrations illustrating how programmers and data engineers can leverage these APIs to incorporate files and tables into data management tasks, as well as trigger actions or automate workflows. These REST APIs can gather insightful metadata and provide a comprehensive view of your data landscape. Users can navigate and explore their data ecosystem effectively, providing a high-level overview of assets and enabling informed decision making. Attendees gained insight into the SAS Information Catalog REST APIs and witnessed several demonstrations. Attendees learned about this powerful method to unlock the true potential of the SAS Information Catalog. Presentation slides are attached to this post. See the attachment at the very top, under the title. Watch the recorded presentation, including four short demonstrations: (function() { var wrapper = document.getElementById('lia-vid-6338349566112w600h600r83'); var videoEl = wrapper ? wrapper.querySelector('video-js') : null; if (videoEl) { if (window.videojs) { window.videojs(videoEl).ready(function() { this.on('loadedmetadata', function() { this.el().querySelectorAll('.vjs-load-progress div[data-start]').forEach(function(bar) { bar.setAttribute('role', 'presentation'); bar.setAttribute('aria-hidden', 'true'); }); }); }); } }})(); (view in My Videos) No matter how comprehensive the interfaces in an information catalog might be, there will always be a need for custom reporting or custom workflows based on extremely specific asset characteristics. A SAS Information Catalog allows you to discover, to search and to manage your SAS Viya assets. Let's look at a few use cases and at the corresponding catalog API endpoints: Imagine you have the following requirements: How would you go about and fulfill those requirements? Well, you can write a program invoking the catalog search REST API. Play the video above , around 05'50'', to see an example where we call the Catalog Search REST API from SAS Studio, using SAS code. Imagine now that you have a different set of requirements you have to use for your reporting. In your marketing reporting, you are using a certain set of tables. But there are some conditions: You can fulfill those requirements by writing a program which is invoking the Catalog Instances REST API. Play the video above , around 10'22'', to see an example where we call the Catalog Instances API from Visual Studio Code. The example uses Python code. Let's say that we have a caslib or a SAS library that we would like to discover. You can use the /catalog/bots endpoint to: Play the video above , around 13'11'', where we call the Catalog Bots API from Postman. The Catalog REST APIs will be public during the fall of 2023, and I can only hope that this session will encourage you to try the Catalog REST API, to explore your assets using SAS Information Catalog and to talk about the product in your organization. | source | ||
| 46 | Machine Learning Meets Retention: A Higher Education End-to-End Guide | Lisa Moore, Amanda Zhao |
Presentation: The student retention rate is a highly focused and actively tracked metric for all institutions to evaluate progress toward growth goals and objectives. Innovations to use SAS Visual Data Mining and Machine Learning to facilitate higher education retention success are in high demand. However, institutions must move beyond descriptive and prescriptive analytics and use more advanced AI and machine learning models to predict the retention result early enough to implement measures to alter student outcomes. The audience got an overview of the work done in this area. We shared the success stories, the lessons learned in building a predictive model for higher education and the important things to consider in the context of higher education. The audience gained practical end-to-end techniques and skills to get started, develop and implement a model that uses SAS Visual Data Mining and Machine Learning. We shared challenges faced in each step of the project and the modeling and technical resolutions we implemented to overcome the challenges. The presentation included hands-on demonstrations of how to prepare the data, choose the variables and build complex analytics pipelines with a range of models to demonstrate the power of machine learning. Learn how to tune and optimize the model and produce model interpretability plots to help stakeholders gain actionable insights. Presentation slides are attached to this post. | source | ||
| 47 | Making the Analytics Life Cycle Accessible to People With Disabilities | Greg Kraus | Presentation: SAS believes that disabilities are not a limitation of the individual. Rather, disabilities arise when people are confronted with barriers in their environment. We also believe that the arc of human progress improves as we remove those barriers, closing the gap between progress and equal access to technology. SAS has been at the forefront of breaking down those barriers in the analytics space for people with disabilities. We have developed data visualizations accessible to people with visual impairments by utilizing sonification, we have enabled customers to create accessible reports, and we have created pathways for data scientists to participate in the analytics life cycle. In this presentation, we will show how individual users and organizations can utilize these features within SAS software to create more equitable work environments and to communicate insights in accessible ways to even wider audiences. It takes a village to implement accessible analytics at scale. Every organization in the ecosystem has a role - from customers to suppliers, partners, developers and managers, assistive technology vendors and standards organizations. We must work together to remove barriers to data. The inequity of progress ensures there will be much work to do. However, SAS is up to the challenge. We also invite you to join us in this work to understand your challenges and help break down barriers together. | source | ||
| 48 | Migration Journey Steps From SAS Grid to OpenShift Kubernetes Containerized SAS | Paresh Patel | Presentation: At Discover Financial Services, we have a very stable SAS Grid environment. In response to mandatory reporting requirements for financial institutions, we migrated our environments to the cloud. To be successful, we needed to process terabytes of data in a few hours instead of days. I have seen other tools fail at 100 GB, but SAS processed 5 TB. This presentation will detail the steps we followed. We'll discuss the early migration journey from on-prem SAS Grid to SAS on container and tuning tips for SAS programs when accessing cloud databases. We have a single application/workbench for users to select the containerized tool of their choice. We'll also touch on using detokenization UDF of cloud database through a hybrid SAS implementation. With SAS Viya 4, the entire SAS environment is containerized and provides integration with other open source tools like Python and R. We will discuss the benefits of using SAS on containers even before we had SAS Viya 4. Containers on the cloud provide an elastic, scalable environment, and the combination with orchestration tools like plain Kubernetes or Openshift makes it a very stable, elastic and scalable environment. | source | ||
| 49 | Missing You Less and Less: Learning to Love Admissions Again With Predictive Model Imputations | Michael Stankey, Mark Hamner, Greg Gengo |
Presentation: The COVID-19 pandemic brought chaos and disruption to university operations, including college admissions. Testing centers closed, and 61% of applicants' SAT scores vanished. This meant that a key dimension was missing from our newly developed performance-based scholarship grid, which had led to near-record enrollment. In response, we developed an improved scholarship grid using class rank as a secondary dimension. But this approach created a new problem: 22% of applicants came from high schools that didn't rank their students. We considered using a common mean imputation process for handling missing data, but this approach disadvantaged potentially high-performing students, especially Hispanic students. Forcing non-ranked applicants to be "average" was not an appealing option when we're looking to reward overlooked and undervalued students with higher scholarship awards than what they can get at other schools. The better solution was to use a more sophisticated SAS-powered predictive model imputation process that utilizes other known information about unranked applicants to place them on the grid more precisely. This approach dramatically increased the support for our Hispanic applicants, with 88% receiving higher rank placements and 64% receiving higher scholarship awards than would have occurred with the more common mean imputation method. This session detailed the problem, explained key model relationships and revealed SAS coding secrets. Presentation slides are attached to this post. | source | ||
| 50 | MLOps for Pirates: R-sasctl | Sophia Rowland | Presentation: This session introduced R-sasctl and demonstrated how to leverage the package to bridge the gap between data scientists and MLOps engineers for R models. R-sasctl was released in January of this year and in our SAS Model Manager community. R-sasctl helps generate the score code and metadata for R models as well as allows R developers to import their model into SAS Model Manager directly from their R development environment. This makes the hand-off between our data scientist developing in R and our MLOps engineer managing and operationalizing the model much easier. R-sasctl has several other neat functions as well, but we are going to focus on the registration today. To learn more about R-sasctl, check out the following resources: MLOps for Pirates: R-sasctl Presentation slides are attached to this post. | source github |
||
| 51 | MLOps Uncoiled: Python's Path on SAS Viya With SAS Model Manager | Sophia Rowland, Anthony Kan |
Presentation: Analyst firm IDC recently placed SAS Viya as a leader in its MLOps Platforms evaluation , praising SAS for our support of a wide variety of languages and platforms. Using our open source package, python-sasctl, SAS Model Manager, containers and more, we will demonstrate how to create an end-to-end MLOps process for Python models on SAS Viya. Using python-sasctl, we will automatically generate scoring code and important metadata files for models developed using the most popular Python frameworks, including sklearn, xgboost, MLflow and more. These models are sent to SAS Model Manager directly from the Python development environment. From SAS Model Manager, these models are compared, tested, deployed into containers, and monitored. Review this presentation and come away with a better understanding of how to leverage SAS Viya to develop a MLOps process inclusive of Python models. To learn more about python-sasctl, check out the following resources: MLOps Uncoiled: Python's Path on SAS Viya with SAS Model Manager Presentation slides are attached to this post. | source github |
||
| 52 | Modernized Customer Journeys for the Modern Marketer | Mark Korey | Presentation: The rate of change and boundless expectations of the digital experience shows no signs of slowing down. To meet these needs, SAS is modernizing how customer journeys are built with SAS Customer Intelligence 360, a SaaS marketing technology and customer data platform. Orchestrating seamless journeys to deliver an omnichannel experience to your customers when and where they want is essential to modern marketing teams. Join this session to see a preview of how our vision will leverage your data (on-prem or in the cloud) with your customers' behavior to deliver your message to your customers via an array of channels. Our reimagined orchestration canvas enables both the technical and non-technical marketer to map out journey touchpoints and then glean performance insights and analytics in a highly visual manner. Whether the journey is an automated always-on multi-step campaign or a one-time event-centric promotion, we have you covered. | source | ||
| 53 | More Goodies in the SAS Extension for Visual Studio Code | Casey Smith | Presentation: The official SAS Extension for Visual Studio Code continues to grow, making it more enjoyable, convenient and productive to access the power of the SAS platform through programming in Visual Studio Code. This presentation will highlight features and enhancements recently added to the extension. These include greatly simplified authentication, support for SAS 9.4 servers, working with SAS content, navigating SAS libraries, viewing data sets, a notebook experience and more. Presented by Casey Smith of SAS. See also this article: SAS Extension for Visual Studio Code . | source link |
||
| 54 | Move to SAS Viya and Snowflake in the Cloud With SAS, Azure DevOps and Git | Lars Arne Skår | Presentation: This session demonstrated using Azure DevOps and Git to automate the move from SAS 9.4 DI Studio to SAS Viya Studio Flow while moving data to Snowflake using SAS code and the migrated SAS Viya Studio flows. Presentation slides are attached to this post. | source | ||
| 55 | NOAA (NOtebook AI Agent) | Daniel Petyus | Presentation: In this session, we'll discuss chat-based data science modeling and results interpretation. Data science modelling and experimentation often happen in an interactive notebook-based (REPL) environment. All of these steps involve writing small chunks of application code in the interactive environment. This work could be augmented by introducing a chat-based, interactive agent, which could interpret instructions, help with the hypothesis and answer related questions in plain English with a chat functionality. This agent embedded in the interactive environment can help with selecting features, interpreting results, providing consolidated answers related to technologies and technical questions and, most importantly, could generate code snippets to aid and speed up the data scientist's work. Once the modelling is done and the results are shown to business analysts and stakeholders, it is either up to the data scientist to try to convey the results in simple terms or feed them into a data warehouse for further interpretation. This process can be elevated by providing business users access to this interactive environment where they can interact with the results by asking questions. These cases are great examples of extending the capabilities of an analytics platform by allowing users to speed up modelling work and share the results directly with end users. | source | ||
| 56 | Performance Do's and Don'ts for SAS Visual Analytics | Gregor Herrmann | Presentation: When you ask BI application users what factors are important to them, many say acceptance of the solution, usability and performance. While usability is predefined by the application's design, performance is determined by many aspects. These range from tuning the compute server, optimizing data structures and data storage for reporting and report design, to choosing the browser that runs SAS Visual Analytics. This presentation covered the most important adjusting screws report authors and administrators should turn if they want to improve the overall performance of SAS Visual Analytics. Presentation slides are attached to this post. | source | ||
| 57 | Policy Evaluation of the US Opioid Pandemic Using SAS Viya | Amirreza Sahebi, Amir Sadeghi |
Presentation: The opioid crisis in the United States has had devastating effects on communities across the country, leading many states to pass legislation that limits the prescription of opioid medications to reduce the number of overdose deaths. This study investigates the impact of opioid prescription limit laws, which aim to reduce opioid overdose deaths, on opioid prescription rates. An Interrupted Time Series (ITS) model was utilized to assess the policy impact using SAS Viya. The Automatic Time Series Modeling (ATSM) package of SAS Visual Forecasting software (Viya 4 - Cadence version 2022.12) was used to find the best ARIMA models for each series. The intervention effect on the response variable was analyzed by adding event inputs in the shape of level-shift, ramp and inverse trend to the final ARIMA model for each series through the interactive modeling node of SAS Visual Forecasting. While the policy effectively reduced opioid prescription volumes overall, we observed an unintended consequence. Prescription volume increased in areas where prescribers were located far from patients, highlighting the limitations of state-level policies on doctors. | source | ||
| 58 | Public Transit Optimization for Istanbul Metropolitan Municipality | Rob Pratt, Pelin Cay, Sertalp B. Cay |
Presentation: Istanbul has one of the world's largest and oldest public transportation systems. The priority of the IETT, a subsidiary of the Istanbul Metropolitan Municipality, is to keep the existing bus operations running with fewer vehicles despite the increasing demand. This project aims to find the most efficient driver/bus/service assignments to minimize running costs. The project created savings of 2.9 million Turkish liras for Istanbul Metropolitan Municipality in two pilot bus garages. | source | ||
| 59 | Reading and Writing ZIP Files With SAS | Chris Hemedinger | Presentation: Data files are often compressed to save on storage space. For years, SAS users had to use external tools to work with these formats. But with SAS 9.4 and SAS Viya, you can use built-in methods to read and write these files directly in your SAS programs. Learn how to use the FILENAME ZIP method to read and write file content in the standard ZIP and gzip archive formats. Presentation slides are attached to this article. Learn more from this series of blog posts about FILENAME ZIP . |
source | ||
| 60 | Real-Time Insights and Real-World Impact: SAS Event Stream Processing at Rijkswaterstaat | Jorge Nogueira | Presentation: In this presentation, we will delve into compelling use cases from the Rijkswaterstaat, the Ministry of Infrastructure and Water Management of the Netherlands, where SAS has been instrumental in transforming data from an array of sensors into actionable insights. Rijkswaterstaat has multiple sensors installed across the country's vast network of highways, bridges, tunnels, locks and pumping stations, not to mention those deployed in the maritime environment. These sensors continuously transmit streams of data and have revolutionized how we monitor, manage and optimize infrastructure use in real time. We will explore how SAS Event Stream Processing, SAS Studio and SAS Visual Analytics are deployed to process this incoming data, from its import to its eventual analysis and visualization. Attendees will be exposed to the data engineering challenges and the creative solutions developed to meet them. We will showcase instances where custom-made codes, models and plugins had to be developed in different frameworks and integrated with SAS tools to transform complex data structures into comprehensible visualizations. This exploration of real-time sensor data, its processing, and its role in decision making will provide compelling insights and stimulate productive discussions. The presentation intends to demonstrate what real-time data analysis can achieve nowadays and encourage imaginative thinking to push its limits even further. | source | ||
| 61 | REDCap: Your SAS Friend for Data Collection | Brooke Ellen Delgoffe | Presentation: This presentation will demonstrate the utility of REDCap in the context of abstracting electronic health records (EHR) data in a way that integrates well with SAS. REDCap allows SAS to query against it using an API for easy data exchange. Discover an advanced export macro that automatically downloads the data dictionary and creates a labeled SAS data set, complete with labels and a format library based on the REDCap data dictionary. We will also cover special data concerns when using REDCap for housing PHI and methods for interfacing with an EHR. Visit here for complete code and resources: https://redcap.link/REDCapIsMySASFriend | source | ||
| 62 | Running SAS Viya 4 in a Security-Minded Environment | Eric Bourn | Presentation: With such heightened scrutiny around cybersecurity threats in today's world, ensuring all applications are as secure as possible is absolutely necessary. Utilizing the proper authentication and authorization frameworks to grant access to the proper set of users is undoubtedly a vital part of that. But is that enough? Whether you are operating within the cloud or on-premises deployment, what else can be done to protect your assets from a rogue user or application such that you can operate with a zero-trust model in mind? Join us to discuss various techniques, from limiting network communication to restricting allowed application-level permissions, for keeping your SAS Viya environment secure. | source | ||
| 63 | Santander US Customer Tool for ESG Transactions | Abby De Molina, Anne Jori Novo |
Presentation: Our team developed a carbon footprint tracker that links with bank accounts. Using SAS Viya and machine learning, we connected transaction categories with S&P Global's ESG scores. This tracker provides real-time insights on purchase impact, empowering users to make informed decisions and reduce their carbon footprint. | source | ||
| 64 | SAS Add In for Microsoft Office and the Theory of Evolution | Tim Beese | Presentation: Microsoft Office has been around a long time, and it has changed significantly over time. The same is true for SAS and the add-ins we've provided for Microsoft Office. As the world changes around us, so must our add-in. It is time to introduce you to the latest version of Office integration, SAS for Microsoft 365, and show how it has evolved from the SAS9 fan-favorite: SAS Add-In for Microsoft Office. This session will show what the new SAS add-in, which runs on the SAS Viya 4 platform, can do in Microsoft EXCEL, Microsoft Outlook, Microsoft PowerPoint and Microsoft Word. The add-in helps you access your SAS reports, data and programs within Microsoft Office, and seamlessly integrates these reports, data and programs into Office documents. However, the technology has changed from a desktop add-in to the cloud using the SAS Viya 4 platform. This session will explore where we came from, where we are now, and where we're heading with our integration for Microsoft Office. |
source | ||
| 65 | SAS In-Database Technologies in the Cloud | David Ghazaleh | Presentation: The main idea of in-database processing is to move the process to the data, regardless of where the data lives. With the rapid growth of cloud computing, companies are moving their data and computation to the cloud. SAS In-Database Technologies continues to evolve and has moved into the cloud. This presentation describes key SAS In-Database technologies that run on cloud platforms, such as SingleStore databases and Spark on Azure Synapse and Databricks. It explains the role of one of the main in-database technologies components: the SAS Embedded Process. Learn how to run a SAS Scoring Accelerator model on SingleStore using PROC SCOREACCEL and on Azure Synapse and Databricks using the SAS Scoring Accelerator Python and Scala API. |
source | ||
| 66 | SAS Infrastructure Maintenance - Items We Often Miss | Praveen Jampana | Presentation: The team at Highmark Health recently experienced pronounced slowness in their SAS 9 Grid Production environment. They worked with SAS tech support and R&D to diagnose the causes and created a remediation action plan. The environment is now holding up well after implementing various tuning options. This session was a case study of the tuning options they used. Learn about some of the options that were conceptually new for the team, like CFS Striping and using NMON to identify resource bottlenecks. The team has since installed ESM in the environment and is working on setting it up for real-time monitoring. Presentations slides are attached to this post. | source | ||
| 67 | SAS PROC GEOCODE by Example: A Case Study | Louise S. Hadden | Presentation: Numerous international and domestic governments provide free public access to downloadable health data databases. One example is the Centers for Medicare & Medicaid Services' Care Compare data, which contains provider address information. This paper and presentation will describe the process of downloading data and creating an analytic database, running SAS' PROC GEOCODE (part of Base SAS), using Tiger street address level data to obtain latitude and longitude at a finer level than a zip code, modeling the data points using SAS/STAT and finally using PROC SGMAP (part of Base SAS) with annotation to create a visualization of a proximity analysis. |
source | ||
| 68 | SAS Studio and Apache Airflow Integration | Alexey Vodilin | Presentation: Modern data stack encourages modular and flexible data architecture. It's crucial to be able to integrate with the best-of-breed technologies on the market to provide the best experience to the users. SAS Studio is a modern and powerful IDE for building robust and reliable data pipelines - Studio Flows. But once data pipelines are ready, how do you bind them together, define dependencies and execute them regularly? Apache Airflow (with 30,000+ stars on GitHub) is a dominating open source solution for orchestration, scheduling and monitoring of data pipelines and other assets. Airflow supports seamless integration with various third-party systems with its mechanism of external providers. SAS Provider for Airflow is one such provider. It allows SAS users to easily create Airflow tasks to execute SAS Studio Flows and other SAS assets. The provider is a project maintained by SAS and available on GitHub at https://github.com/sassoftware/sas-airflow-provider under Apache 2.0 license. This demonstration shows you how to create Airflow DAGs with Studio Flows in SAS Studio and then monitor the execution of DAGs in Airflow UI. You'll also learn how to contribute to the project with your ideas and features. | source github |
||
| 69 | SAS Visual Forecasting Open Source Modeling Node | Mahesh Joshi | Presentation: Data scientists, forecasters and researchers in academia and various industries are increasingly developing and open sourcing new time series forecasting algorithms by using popular programming languages, such as Python and R. SAS Visual Forecasting software, which offers an open environment for large-scale automatic modeling and forecasting, now supports running programs written in Python or R in its new open source modeling node. This new modeling node makes it easy for users to integrate their open source programs into the SAS Visual Forecasting pipelines with minimal modifications. Once integrated, the user's program is automatically distributed and efficiently executed by using the multithreading and massively parallel processing capabilities of the SAS Viya platform. The new node seamlessly fits into the SAS Model Studio pipelines and inherits all common features available to modeling nodes. This talk demonstrates using the new open source modeling node with examples. | source | ||
| 70 | SAS Viya AI for Cybersecurity: Malware Control | Al Cordoba, Patrick Alcorn, Michael Lewis, John Brocklebank, Manuel Figallo, John Shipway |
Presentation: This presentation illustrated malware detection enhancement using unsupervised and semi-supervised machine learning techniques to detect early zero-day attacks. Malware authors generate domains for command-and-control communication using domain generation algorithms (DGA). Different types of malware employ different algorithms. Our challenge is to classify a given domain as a DGA domain or non-DGA (benign) domain. A device that accesses a DGA domain is potentially infected with malware. Learn how we used SAS Viya to apply multiple advanced analytics techniques. Presentation slides are attached to this post. | source | ||
| 71 | SAS Viya Unleashed: Scalable and Performant Algorithms Across Coding Languages and Environments | Brett Wujek, Udo Sglavo |
Presentation: Discover how SAS is revolutionizing the analytics landscape by enabling consistent and accurate results across multiple programming languages. This SAS Explore session explored the cutting-edge capabilities of SAS Viya Workbench, a lightweight and fast-deployment environment that empowers users of SAS, Python and R to harness the full potential of SAS algorithms. Learn how to leverage a unified workbench to achieve unparalleled scalability, performance and accuracy, and broaden your user base by running SAS algorithms anywhere and everywhere. Presentation slides are attached to this post. | source | ||
| 72 | SAS Viya Workload Management: The Next Generation of Elasticity | Alex Daehnrich, Doug Haigh |
Presentation: As organizations create analytic and data management workloads in SAS Viya, they face challenges in balancing cost and agility. The SAS solution to balance good Viya performance with reasonable infrastructure costs is the SAS Workload Management feature (formerly a separately sold add-on) in the Viya portfolio. SAS Workload Management extends the capabilities of Kubernetes by adding priority-based queues that can control where and when jobs are processed based on prioritization and resource allocation. We're excited to introduce the next generation of Workload Management Autoscaling Workload Management. Nodes are identified as "scalable" to leverage the Kubernetes Cluster Auto-Scaler. This enhancement further extends the workload management capabilities for Viya Compute Server-based processing. | source | ||
| 73 | Shakespeare Versus AI: Spot the Differences Using SAS Visual Text Analytics | Mary Osborne | Presentation: Are you ready to delve into the realm of Shakespearean tragedies and embark on a journey to explore the boundaries between human creativity and artificial intelligence? ChatGPT has been shown to perform well in a variety of creative endeavors, but how well does it do at generating Shakespearean tragedies? In this presentation, I will compare AI-generated tragedies in iambic pentameter, in the style of Shakespeare, with authentic Shakespearean tragedies using techniques available in SAS Visual Text Analytics. I will explore the differences in language usage, sentence structure and other elements as a part of the ongoing conversation about the intersection of AI and art. | source | ||
| 74 | Speed to Results: How SAS Viya is a Productivity Multiplier for Life Sciences R&D | Nat Moorman, Rachel Hardin, Hamza Ghadyali |
Presentation: The pandemic taught the biopharma industry many lessons, including just how vital R&D productivity is to ensure the health and well-being of our local and global communities. This session showcased how the SAS Viya platform is a productivity multiplier for both data scientists and clinical scientists, how SAS advanced analytics enables deeper insights and accelerates discovery, and how the open design of the SAS platform allows integration with your current workflow and the technologies you depend on. The session featured various innovative projects led by the SAS analytics Center of Excellence using SAS Viya to accelerate drug discovery, enable computational drug repurposing at the Food and Drug Administration, and support the development of personalized therapeutics in collaboration with the University of North Carolina and the Rapidly Emerging Antiviral Drug Development Initiative (READDI). The hosts held a fireside chat with a leading virologist who is applying SAS in the race to discover novel antivirals in preparation for the next pandemic. This industry session will also highlighted how the SAS Viya platform operationalizes AI-driven analytics with maximal transparency and reproducibility, ensuring results are trusted by scientists, regulators and, most importantly, patients. Presentation slides are attached to this post. Rachel Hardin, SAS Hamza Ghadyali, SAS Nat Moorman, READDI | source | ||
| 75 | StaSASticians: ESG-Aware Wealth Management and Investing | Narges Hosseinzadeh, Vasileios Farmakiotis |
Presentation: Using ESG factors to evaluate companies before investing can help investors make more informed decisions by considering a company's environmental, social and governance practices, as well as its financial performance. This can lead to more sustainable and responsible investing, potentially fostering better long-term performance. | source | ||
| 76 | Storage Considerations and Best Practices for SAS Viya on AWS | Darryl Osborne, Dilip Rajan |
Presentation: SAS Viya as a Kubernetes-based architecture requires a thorough evaluation of the compute and storage components. For some customers, existing SAS 9.4 infrastructure might suffice, but for others, it might require adding more capacity and replacing existing infrastructure components. Over the years, AWS has significantly improved storage options from EBS - IO2 block express to FSx ZFS, each with its unique profile and workload applications. In this presentation, we reviewed these storage options along with best practices and recommendations for SAS Viya on AWS. This includes a combination of file systems and block devices for providing the optimum balance of price and performance. Presentation slides are attached. | source | ||
| 77 | Streamlining Customer Engagement: Integrating Generative AI with SAS Customer Intelligence 360 | Mac Carlton | Presentation: This session covered Customer Intelligence 360's ability to flexibly integrate with generative AI tools. With our approach, marketers can leverage generative AI assistants and agents across the customer engagement lifecycle. Some of our core capabilities include leveraging Large Language Models (LLMs) to brainstorming novel campaign strategies, using natural language to build segments for targeting, and accelerating content generation using custom models and knowledge bases. We reviewed one example where we have partnered with the SAS marketing department to develop custom models and knowledge bases to help build email campaigns. We continue to work with customers on these use cases to ensure we are developing intuitive and valuable capabilities for end users. We will also discuss how marketers can leverage generative AI technology in their marketing environments. This includes prioritizing data privacy, avoiding sharing sensitive company and customer data with these models, keeping a human in the loop, implementing a review and approval process, and creating interpretable and transparent output. This presentation equips marketers with the knowledge and tools necessary to harness the power of generative AI while upholding ethical practices and maintaining trust with consumers. Presentation slides are attached to this post. | source | ||
| 78 | Streamlining SAS Model Deployment to Azure: Leveraging SCR, Azure DevOps and App Service | Bogdan Teleuca | Presentation: This session introduced an innovative solution for automating the publishing and deployment of SAS models to Azure. The proposed approach streamlines the path-to-production for SAS models by leveraging SAS Container Runtime (SCR) and Azure DevOps release pipelines. The solution ensures a smooth and efficient deployment process by using Azure Service Plans and Web Apps as versatile back-end applications for model scoring. The process begins with creating an Azure App Service Plan and a Web App, establishing the target environment. An Azure publishing destination is set up, followed by configuring a release pipeline in Azure DevOps. The SAS model is published from SAS Model Manager to the Azure publishing destination, packaged as an SCR container image. Subsequently, the release pipeline retrieves the container image and seamlessly deploys it to a designated slot within the Azure Web App. The SCR enables model scoring through a simple REST API call. By employing tags during publishing, the pipeline can deploy the model to the desired slot, allowing individual testing in different slots and enabling seamless production deployment through slot swapping, eliminating downtime. Azure Web Apps support auto-scaling and scaling based on predefined rules, accommodating spikes in scoring requests. Network traffic isolation can also be enforced, ensuring requests are limited to the virtual network's resources. Presentation slides are attached to this post. | source | ||
| 79 | Successful Automation of Credit Risk Models Using SAS Platform Solutions | Víctor Hernández Ruíz | Presentation: This presentation showcased an extraordinary success story that revolves around implementing SAS platform solutions, focusing on creating a cutting-edge credit risk model factory. Our winning strategy hinged on seamlessly integrating data, state-of-the-art modeling tools and advanced estimation algorithms. We unleashed unparalleled efficiency by automating critical stages of the model life cycle, including deployment, backtesting and validation report generation. But we didn't stop there. Our relentless pursuit of excellence led us to introduce champion and challenger models bolstered by robust model governance. These groundbreaking enhancements supercharged our development and deployment times and empowered our teams to maximize productivity, enabling us to effectively manage our clients' credit risk like never before. The impact of our implemented models reverberated across the entire credit cycle, revolutionizing credit approval (+10%), expected credit losses estimation (-3.4%) and collection processes. Productivity soared (-80% time reduction in the modeling process), allowing us to navigate the complexities of risk management with confidence. Presentation slides are attached to this post. Victor Hernandez Ruiz Banco Popular - Colombia | source | ||
| 80 | Text Analytics and AI to Assess Police Narrative Events for Indications of Human Trafficking | Tom Sabo, Kirk Swilley |
Presentation: Narrative data from police agencies on arrest or offense incidents and tips to police departments are rich in information and largely unavailable to the public for analysis. Dallas has published over 45,000 de-identified incidents containing narrative data from 2013 and 2014. Assessing large quantities of narrative data for patterns using manual analysis alone can be time consuming and produces limited qualitative results. How can modern methods in text analytics assist? This presentation used the data set available from https://www.dallasopendata.com as a model for how text analytics can assist with assessing police narrative data for patterns, enhancing both time-to-value and quality of analysis. While this presentation assessed the data for crime-related patterns, it specifically covered methods to identify risk indicators for human trafficking. AI capabilities were showcased for developing relevant concepts for extraction from the narratives and demonstrate how to visualize these AI-supported extraction results in a user-friendly environment. These methods can be replicated across any police agency to comb narrative event data for human trafficking indicators or to surface other crime-related patterns of interest. Presentation slides are attached to this post. | source | ||
| 81 | The Art of SAS Modernization: A Five-Year Journey of Lessons Learned and Myths Busted | Eric Lacombe, National Bank of Canada |
Presentation: In this presentation, Éric Lacombe offered valuable insights into the challenges and successes encountered during a five-year journey to modernize SAS at the National Bank of Canada. The process was loaded with challenges, myths and significant operational risks inherent to the legacy environment. The talk focuses on dispelling prevalent misconceptions surrounding SAS and the modernization process. It also highlights the architecture and best practices applied to mitigate operational risks, clean the legacy environment, understand and present the business cases and align with stakeholders. By sharing his experiences, Lacombe aims to equip attendees with valuable lessons learned to foster a smooth and successful transition toward a modernized SAS landscape. Presentation slides are attached to this post. | source | ||
| 82 | The Future of Viewing and Editing SAS Datasets | Scott P Leslie | Presentation: Viewing and editing datasets on SAS Viya has reached a new level of functionality and ease with the use of our new DataViewer component across SAS solutions. Whether you are in SAS Studio or SAS Visual Analytics, viewing and editing your SAS data has never been easier or more functional on the web. This presentation walked you through the capabilities of the DataViewer and previewed the future of viewing and editing your data. Presentation slides are attached to this post. | source | ||
| 83 | The Intelligent Edge and Event Science: Putting Your Intelligence Where Your Data Is | Kirk Borne | Presentation: Generative AI is not just for static data collections. It can be trained to extract informative insights from the flood of streaming data from ubiquitous IoT sensors. Starting with the detection of domain-specific interesting patterns in IoT data, generative AI can create stories, reports, visualizations, and historical comparisons in context at the speed of data. Kirk Borne, Ph.D., presented his views on how harnessing the convergence of generative AI and IoT should ensure job security for years to come for any ready-for-IoT AI/ML practitioner. Presentation slides are attached to this post. | source | ||
| 84 | The Intersection of Workload Placement Between Kubernetes and the SAS Viya Platform | Rob Collum | Presentation: SAS Viya relies on Kubernetes to provide a robust environment that is elastic, highly available and extensible. One way that Kubernetes achieves these goals is through sophisticated workload management controls. By default, SAS Viya takes advantage of these controls in specific ways to ensure a great software experience. But there's no one-size-fits-all way to deploy SAS Viya. That's why understanding these controls can be useful to further fine-tune the environment to your site's specific needs. Configuring Kubernetes for workload placement works well up to a certain point. But there are areas where Kubernetes can't "see" what's happening. Instead of trying to manage the workload at the infrastructure level, configuration needs to occur higher at the application level. In SAS Viya, we have a multilevel approach with many levers and switches to configure workload placement, including multitenancy, CAS distribution of data across nodes, SAS Workload Management jobs controlled through the use of queues, priority and preemption, and additional SAS Viya platform controls for concurrency and resource utilization. | source | ||
| 85 | The Nexus of Data Quality and Analytical Excellence: Leveraging SAS Viya for Trustworthy Insights | Chalamayya Batchu | Presentation: This insightful presentation delves into the indispensable connection between data quality and analytical excellence, highlighting SAS Viya's significant role in our organization's pursuit of reliable insights. Attendees will gain practical strategies to tackle data quality challenges and optimize their analytical outcomes based on our extensive utilization of SAS Viya. The session showcases the robust data quality capabilities of SAS Viya, including data profiling, cleansing, validation and governance, which have been successfully integrated into our organization's analytics workflow. Discover how our organization has effectively unlocked valuable insights, made informed data-driven decisions and achieved a higher level of analytical excellence. The presentation will feature specific examples and actionable best practices from our experiences with SAS Viya, providing attendees with valuable insights and guidance. This session is particularly relevant for data scientists, analysts and business professionals who aim to address compromised data quality issues and drive their organizations toward data-driven success. Experience our journey as we explore the critical relationship between data quality and analytical excellence. We'll discuss how SAS Viya has become an integral part of our organization's quest for trustworthy insights. | source | ||
| 86 | The SAS Viya ETL Playbook | Charu Shankar | Presentation: ETL (extract, transform and load) is an integral process for data engineers to extract data from different sources, transform the data into a trusted resource, and load that data into systems that end users such as data scientists can use for computation and analysis. In all the buzz around analytics, ETL is often relegated to the background, but data scientists depend deeply on this solid foundational task before they can deep dive into analytics. Come to this session to learn to leverage the power of the cloud to extract, transform and load data using SAS programs executed in the SAS Viya Compute Server. The good news is that if you are already programming in SAS9, you'll feel right at home in Viya! You will learn to: Presented by Charu Shankar at SAS Explore 2023. | source | ||
| 87 | The State of Generative AI And Design Principle for Responsible AI | Ray Wang | Presentation: As organizations begin their journey into artificial intelligence (AI), ethics often enter the design process. Learn the key adoption trends in AI and how organizations have delivered on decision velocity through analytics, automation, and AI. Understand the key business outcomes for AI and what strategies will be needed for organizations to succeed in AI. In addition, learn how to incorporate design points that will help facilitate the humanization of artificial intelligence and provide appropriate checks and balances for responsible AI. | source | ||
| 88 | To Calculate or to Aggregate? Creating Data Items in SAS Visual Analytics | Teri Patsilaras, Nicole Ball |
Presentation: SAS Visual Analytics is a powerful tool that enables you to explore and visualize data. In addition, it contains many data preparation capabilities, like creating calculated items and aggregated measures. For new and even seasoned users, it can be difficult to determine which one you should use. In this presentation, the presenters explore the differences between these two data items and discuss scenarios when you should create one versus the other. Presentation slides are attached to this post. | source | ||
| 89 | Transition from SAS Enterprise Guide and SAS Data Integration Studio to SAS Studio on SAS Viya 4 | Alexey Vodilin | Presentation: Do you want to move to SAS Studio and benefit from the latest data engineering and analytics capabilities as well as from a cloud-native platform? The path is clear and open. We provide an automated process for importing your SAS Enterprise Guide and SAS Data Integration Studio projects into SAS Studio. You just need to feed your assets to it either interactively in SAS Environment Manager or in batch using import CLI. It will pick up your process flows and/or data integration jobs and automatically convert them to SAS Studio Flows with the equivalent steps. There are already many steps supported for like-to-like migration, and the list is growing every month. In this session, you will discover how to approach and execute migration using a real-world example. You'll also get tips on how to go beyond that with the latest features in SAS Studio. | source | ||
| 90 | Tricks for Report Builders: Best Practices and Visualization Skills for Designing Impactful Reports | Teri Patsilaras, Nicole Ball |
Presentation: Are you new to SAS Visual Analytics but not new to data visualization? In this SAS Explore presentation (slides are attached to this post), we helped SAS users hit the ground running and take advantage of automated features. We revealed the top five things to help you quickly transfer your skills and get the most out of SAS Visual Analytics. Report building best practices covered included: | source | ||
| 91 | Trustworthy AI and Privacy by Design for Computer Vision Solutions: A Case Study | Hamza Ghadyali | Presentation: Computer vision applications are everywhere. At SAS alone, we have developed solutions in the manufacturing, transportation, health care and retail industries, to name a few. Given the intrinsically sensitive nature of image data, concerts for privacy have become more prevalent. This session will show how we apply principles of trustworthy AI in computer vision solutions. We will explore the concepts of privacy-by-design in practice and show how it applies to a use case that involves tracking people. When AI is applied in situations that directly impact lives, we need to take extra precautions in designing our solutions from both a modeling and deployment perspective. | source | ||
| 92 | Ultra-Agile Approach for the Deployment of Real-Time Analytics Projects | Aaron Allsbrook, Steven Enck |
Presentation: Deploying real-time analytics projects at scale requires many steps, including data processing, model development, creation of a real-time process flow and deployment. This can be a tall order. Through the power of the end-to-end capabilities in SAS, we've made this process simple and straightforward. We'll demonstrate using a project delivered in collaboration with ClearBlade, a SAS partner. By entering just a few simple inputs, machine learning models are trained and deployed in real time to monitor energy output across all assets in the SAS solar farm. The ultra-agile approach retrieves data, builds comprehensive analytic datasets, trains models using a selected Model Studio pipeline, registers champion models to Model Manager, builds a real-time Event Stream Processing project and generates a deployable container that can be run in Docker or on a VM. Want to monitor the health of those models? Receive daily updates. Have a few minutes to attend? That's all you'll need to deploy world-class analytics in real time. | source | ||
| 93 | Unleashing Potential: Join the SAS Hackathon 2024 | Peter Lundqvist | Presentation: This session delved into the thrilling world of the SAS Hackathon. It provided invaluable insights from past use cases, results from successful teams and made a case to participate in 2024 - like gaining access to the state-of-the-art SAS Viya in the cloud and the guidance of a seasoned SAS mentor. In its latest iteration in 2023, the SAS Hackathon brought together a diverse mix of over 1,400 enthusiasts from 75 countries, representing 140 organizations. We had a wide array of participants ranging from seasoned data scientists to business analysts, marketers, industry professionals and students. Our monthlong, all-digital hackathon stimulates minds, challenges teams across multiple industries to deploy technology, and addresses real-world business and humanitarian problems. Teams bring their use cases and data, sparking curiosity and innovation. By leveraging AI in the cloud, they are empowered to transform data into actionable insights that enhance decision making and improve lives. The SAS Hackathon is not merely a competition; it's about a global community coming together to effect change. All participants are winners, gaining knowledge, experience and lasting connections that continue to serve their organizations and communities well into the future. Join us in this session and take the first step toward becoming a part of this transformative event in 2024. Presentation slides are attached. Learn more about Hackathon 2024 | source | ||
| 94 | Unlocking Actionable Intelligence at Scale - Streamlining Delivery of SAS Visual Analytics Insights | Robby Powell, Brad Morris |
Presentation: Unlock the insights you discover in SAS Viya that allow your end users to take informed action. Publish insights at scale through your custom-designed web apps using familiar cloud, developer and DevOps technologies. In this session, you'll see how to use SAS Visual Analytics and the SAS Viya SDK for JavaScript to deploy your insights at scale. Do you have hundreds, thousands or tens of thousands of end users? It doesn't matter because you're leveraging commodity web server infrastructure. Join and see how to use SAS Viya on Microsoft Azure and tools such as VS Code, GitHub and Microsoft Azure services to manage an interactive web app. | source | ||
| 95 | Using JSON Data With SAS | Chris Hemedinger | Presentation: JSON is a key interchange format between applications and API-based services. SAS has built-in tools to convert JSON to SAS data for analytics and convert data from SAS to JSON output to integrate with other applications. You will learn what JSON is and how it is used, how to use the JSON LIBNAME engine to read JSON into SAS data sets, how to use JSON maps to control how SAS reads and interprets the raw JSON data, and how to use PROC JSON to create JSON output in SAS. Presentation slides are attached to this article. For more information see: |
source | ||
| 96 | Using Machine Learning and Customized Reporting to Guide Product Development and New Product Usage | Cameron Devers, Robert Blanchard |
Presentation: The performance of a drill bit depends on the manufacturing design, how customers use it and where they use it. The drill bit industry has no "one size fits all." Therefore, drill bits are customized for the customer's usage. To add difficulty to the problem, conveying the strengths of certain designs is not straightforward and usually requires highly technical knowledge commonly possessed by a drill bit design engineer. In this presentation, we detailed how we created design metrics to bring customer-facing transparency to the design process, using machine learning to recommend new product usage based on similar product designs. We brought everything together to easily extract insight from our data using SAS Visual Analytics for reports. Presentation slides are attached to this post. | source | ||
| 97 | Using SAS Decisions to Generate Batch Responses from Azure OpenAI | Bogdan Teleuca | Presentation: This presentation showcased how to invoke an Azure OpenAI model from within a SAS decision, enabling you to unleash the capabilities of GPT. Learn how to pass a series of prompts in batch to the Azure OpenAI REST API and witness the results being stored in a table effortlessly. Discover how you can dynamically control input parameters by retrieving them from a table, ensuring flexibility and customization. Before sending the prompt, there was a demonstration of the unique ability to calculate the number of tokens and the cost, empowering you to make informed decisions and optimize resources. Presentation slides are attached to this post. Watch the recorded presentation, including several short demonstrations: (function() { var wrapper = document.getElementById('lia-vid-6340121611112w600h338r319'); var videoEl = wrapper ? wrapper.querySelector('video-js') : null; if (videoEl) { if (window.videojs) { window.videojs(videoEl).ready(function() { this.on('loadedmetadata', function() { this.el().querySelectorAll('.vjs-load-progress div[data-start]').forEach(function(bar) { bar.setAttribute('role', 'presentation'); bar.setAttribute('aria-hidden', 'true'); }); }); }); } }})(); (view in My Videos) You can install these using pip: Specifically for SAS Viya, if you use the SAS Configurator for Open Source (which creates and executes a sas-pyconfig job), you would need to add the new packages in the change-configuration.yaml . Sample prompts and generated output: Sample prompts and generated output: A retrieval augmented generation (RAG) methodology can be used to refine the answers received. You can use your own data as a source of information. You can direct the Azure OpenAI model to use only search results from the document to construct the answer. In other words, you can ask questions on your own unstructured data. We have used the SAS Intelligent Decisioning documentation as a source. As you can see, when you use RAG, the answer is much more precise. SAS Intelligent Decisioning is delivering great capabilities, when it comes to combining models, rule sets, data queries, decision points, code files. | source | ||
| 98 | Using SAS to Extract Data From the Census Data API | Ahmed Al-Attar | Presentation: Over the past few years, the Census Data Application Programming Interface (API) team has been hard at work aligning themselves with the Digital Government Strategy, growing their list of publicly available data sets and providing access to key US statistics. The Census API makes key demographic, socioeconomic and housing statistics more accessible than ever before, with more data sets continuously added over time. This session demonstrated the reusable collection of SAS programs and macros that can run from SAS 9.4 M4 on both Linux and Windows platforms. Extract data from the Census Data API to create SAS datasets in as little as three steps. Presentation slides are attached to this post. | source | ||
| 99 | Using Transformers in SAS Viya to Predict Keywords From the Description of Movies and Series | Hans de Wit | Presentation: Text-based deep learning, driven by the growing emphasis on generative AI, has emerged as a pivotal point. In this context, transfer learning is crucial, harnessing the power of pre-trained transformer models like BERT. These NLP models are smaller and more cost-efficient than larger language models, making them deployable within existing customer infrastructure. We'll analyze a real business case within one of Telenor Norway's largest divisions. The essence of the task is to read text, interpret it, and classify it accordingly. Unlike traditional classification problems demonstrated in SAS previously, this problem involves multi-class classification. Leveraging SAS Viya, we deploy the problem using 'DLPY,' which utilizes the 'BERT' model from the Python library. The model's performance surpasses that of humans, achieving an impressive F1 score of 80% for over 80% of the tagging classes (430). Furthermore, we compare the model's performance against other SAS models like 'Boolean rules.' To extract key insights, text preprocessing becomes necessary, and we demonstrate how SAS Viya's 'match codes' enable easy implementation. Additionally, we address various data quality issues, including duplicate entries and more. This paper serves as a blueprint for leveraging transformers and customizing layers. The model's transferability extends to any text-related use case and when combined with SAS Viya's inherent preprocessing capabilities. | source | ||
| 100 | Visualization of Weather Data to Assess Green Energy Suitability | Will Hauwert, Luke Coldridge |
Presentation: As the desire for green energy increases, more people are looking to utilize renewable technology to generate their own energy. Using SAS Visual Analytics and the SAS Viya toolset, the team created a tool to assess suitability for green energy based on location, orientation and local sentiment. The tool considers where the user lives and the weather in their area, enabling individuals to decide on the best type of green energy for their location. The tool can stream live weather data from an API, providing users with an up-to-date picture of the potential energy level that would be generated at any given time from different types of renewable energy sources. Using SAS Intelligent Decisioning, the tool provides recommendations for given areas based on wind and solar factors specific to each region and sentiment analysis for the local area. This information is displayed in a SAS Visual Analytics dashboard, presenting the user with the recommendation and summary information. We incorporated an innovative vector plot to display the average wind speed and direction, providing users with insights into the optimal placement of a wind turbine. With this tool, individuals can explore and evaluate green energy options, making informed decisions tailored to their needs. This contributes to a sustainable future where renewable energy plays a crucial role. | source | ||
| 101 | What's New in SAS Studio on SAS Viya 4 | Vincent Rejany | Presentation: Ready for a modern web-based IDE where data engineers and analysts can ingest raw data and then transform and analyze it to produce high-quality and consistent insights for your business? Explore SAS Studio on Viya 4! We're adding new functionality with each release. Don't miss a chance to discover the latest updates, including: • New ELT steps for true data integration specialists. • A few new "old" tasks for data wrangling and visualization. • Brand new and powerful data quality steps. • Public API for Code Generation for SAS Studio Flows and Programs that unlocks seamless integration with third-party applications. • New controls and extensions of Custom Steps framework. • Extended capabilities for deploying and redeploying SAS Studio assets. • Support of views. • Explicit pass-through for the query step. | source |
This site serves as a convenient hosting location and does not work as a publisher. All copyrights belong to their respective owners.
The information on this site is provided for general reference purposes only. Whilst every effort is made to ensure that the site is up to date and accurate, no warrant, nor any responsibility or liability for, the accuracy or completeness of the content or for any loss which may arise from reliance on information contained in this site is provided. Links to other sites are provided for your convenience but no responsibility or liability for the content of those sites or of any external site which links to this site is accepted. References to any specific commercial product, process, service, or corporation are also for information only, and do not constitute endorsement, recommendation or favoring.
SAS is a registered trademark of SAS Institute Inc. SAS, Statistical Analysis System, and all other SAS Institute Inc. product or service names are registered trademarks or trademarks of SAS Institute Inc. in the USA and other countries. ® indicates USA registration.