April 28 - May 1 | Dallas, TX


Eggplant blocks with eggplant and violet blocks


Our conference sessions are top notch – and they aren’t one-size-fits-all. We offer lecture-style sessions for the classroom learner; 10-minute Quick Tip sessions for those who prefer a more abbreviated approach to learning; e-posters for the visual learner; and more. You’ll get practical knowledge and know-how to advance your capabilities and career.

Great news! Our session catalog is now live for Users Program. And you’ll have the ability to personalize your conference experience with sessions that fit your individual needs.

Here’s a sampling of some of the top-notch sessions that will be featured:

Session Offerings

The Economy of Data Science

Panelists: Bruce Bedford and Michael Dessauer
Moderator: Chuck Kincaid

Data science has been around long enough that it's getting integrated into many organizations to increase their competitive edge. As a result, those organizations are seeing many benefits and challenges. How do they integrate new processes into their current IT and business models? How much and how fast to expand analytics? How have they overcome the analytical talent shortage? How do they measure ROI for data science investments? When and how is data science profitable? Are other tech trends, such as the cloud, machine learning, blockchain, data lakes and cybersecurity helping or hurting the data science expansion? This panel will explore these questions and more around the economy of data science.

A Complete Introduction to SASPy and Jupyter Notebooks

Jason Phillips, The University of Alabama

Thanks to the official SASPy package, it’s trivial to incorporate SAS® into new workflows that use the simple yet elegant Jupyter Notebook coding and publication environment. There’s also a broader Python data science ecosystem that comes with it. This paper and presentation begins with an overview of Jupyter Notebooks for the uninitiated, then proceeds to explain the essential concepts in SASPy that enable communicating seamlessly with a SAS session from Python code. Included along the way is an examination of Python DataFrames and their practical relationship to SAS data sets, as well as the unique advantages offered by bringing your SAS work into the Notebook workspace and into productive unity with the broad appeal of Python syntax.

Cloud Monitoring of Your SAS® Environment

Michael Dixon, Selerity

Selerity specializes in SAS administration and IT support for customers around the world. We identify and mitigate potential issues that would otherwise impede usage of SAS by instrumenting all aspects of multiple SAS environments and centralizing this information in Datadog. This same monitoring platform caters to both SAS 9.4 and SAS® Viya® environments. From this central location we can monitor performance, the inner workings of SAS and review logs. We’re also able to perform root cause analysis by bringing all these things together in a unified view. This presentation will give insight into how multiple SAS environments, including a mixture of both SAS 9.4 and SAS Viya, can be monitored from a central platform and how to use this information to provide pre-emptive alerts.

Delivering Value Through Text Analytics in the Materials Manufacturing Industry

Michael Dessauer, The Dow Chemical Company

Global manufacturing companies generate vast amounts of data from both operations and enterprise resource planning systems that have large unstructured components to them. These text-based data sources can be difficult to integrate into traditional reporting and analysis workflows that require querying and numerical calculations. With the advancement and ease of entry into developing text-based analytics, Dow is employing several types of text modeling methods to increase margins, improve safety and enhance customer experience. In this talk, we’ll share several examples of how Dow uses internally and externally generated text data from large document repositories to develop supervised and unsupervised models that uncover insights for production, marketing, and environmental health and safety.

Enriching the Sports Industry With Data Intelligence

Giels Brouwer, SciSports

SciSports is revolutionizing the world of football by bringing advanced data analytics to an industry that used to be known as old-fashioned. Its Insight platform, a database covering over 200,000 football players, provides a wealth of data for clubs, scouts and managers all over the world. BallJames is the next product in this revolution: an advanced camera system, combined with SAS® Event Stream Processing capabilities, allows for powerful, real-time on-pitch analytics. This session will provide tangible insights on how SciSports changed the football industry. With the assistance of SciSports, the Belgium National Team became third on the FIFA World Cup; Memphis Depay became one of the best players in Europe; and over a hundred transfers were conducted based on our sports data intelligence.

Lessons Learned Architecting a Modern Data Analytics Platform in the Cloud Using MapR & SAS® Viya®

Shane Gibson, Pitch Black

Gibson was the technical lead on an Analytics 2.0 project for a large New Zealand government organization that was deploying a MapR converged data platform in Microsoft Azure, including a SAS Viya and SAS 9.4 platform via SAS global hosting in AWS. This presentation covers the technical architecture and lessons learned during the implementation of the integrated platforms. The presentation will discuss the following key areas: SAS Viya multitenancy architecture design; implementing SAS Viya and SAS 9.4 and why you need to consider the tradeoffs; implementing multicloud platforms and integration issues; defining authentication and authorization in a managed platform environment; data integration patterns between SAS Viya and a MapR data lake/data vault; and automation required to achieve a data ops vision.

Machine Learning and Predictive Analytics in SAS® Enterprise Miner™ and SAS/STAT®

David Cutler, Utah State University

SAS/STAT and SAS Enterprise Miner are two excellent environments for applying machine learning and other analytical procedures to a wide range of problems, from small data sets to the very large and very wide. In SAS Enterprise Miner one can move seamlessly from data cleaning and processing, through preliminary analyses and modeling, to comparing the predictive accuracy of several predictive methods and scoring new data sets. Many powerful machine/statistical learning tools, including gradient boosting machines, artificial neural networks and decision trees, are nodes in SAS Enterprise Miner. Other SAS procedures that are not nodes may be accessed through the SAS Code node. I will work through some examples from business and other areas to illustrate some of the many capabilities of SAS/STAT and SAS Enterprise Miner.

Back to Top