Team Name WPIntelliAgent Track Banking Use Case A multi-agent AI system where different AI agents to  analyze a business decision from different perspectives. Using SAS Viya analytics and GenAI, the agents compare their recommendations and provide the best data-driven decision. Technology SAS Viya, Python Agentic AI Region AP Team lead Sanket Mandhare Team members @Lynn3 , @Woodpecker24 , @Shantanu5 , @RaviIyer , @yashkk07 , @Sonali4 , @Lokeshp25  Social media handles   Is your team interested in participating in an interview? N Optional: Expand on your technology expertise     ... View more

Starting with October 22, 2026, SAS Customer Intelligence 360 includes updates to the Unified Data Model (UDM) for schema 23. See the sections below for details about the updates.   Updates to the UDM   These are updates to the existing tables in the UDM:   Table Updates DAILY_USAGE MONTHLY_USAGE Added these columns: ae_destinations_total_id_cnt ae_destinations_total_row_cnt DBT_DOCUMENTS Documented these columns as being part of the table's composite key: do_page_url document_download_dttm DIRECT_CONTACT Added these columns: journey_id journey_occurrence_id EMAIL_SEND Added these columns: optout_shortcode tracking_disabled EVENT_ERRORS Documented the event_id column as the table's primary key. IDENTITY_ATTRIBUTES SEGMENT_MEMBERSHIP Changed the length of the user_identifier_val column to VARCHAR(256). JOURNEY_ENTRY JOURNEY_EXIT JOURNEY_NODE_ENTRY JOURNEY_SUPPRESSION Added the segment_id column. MD_ACTIVITY_X_ACTIVITY_NODE Documented these columns as the table's composite key: activity_id activity_node_id MD_ACTIVITY_X_ACTIVITY_NODE_ALL Documented these columns as the table's composite key: activity_id activity_version_id activity_node_id MD_BUSINESS_CONTEXT MD_BUSINESS_CONTEXT_ALL Added the enable_billing column. MD_SPOT MD_SPOT_ALL Added the reserved_1_txt column to the 18 th position.   Note: Before schema 23, this column was present in the downloaded data in the 18 th position, but the values were always empty.   If you have any on-premises processes that rely on column definitions from the JSON schemas, make sure that you are loading data into the correct columns. MD_TARGET_ASSIST Documented the task_id column as the table's primary key. ORDER_DETAILS Contains these updates: Added the row_no column. Documented the row_no column as part of the table's composite key (along with the event_id column) PAGE_DETAILS_EXT Documented these columns as part of the table's composite key: detail_id session_id load_dttm RESPONSE_HISTORY Documented the response_id column as the table's primary key. SESSION_DETAILS_EXT Documented the session_id column as the table's primary key.   Updates to the CDM   Table Updates CDM_BUSINESS_CONTEXT Added the enable_billing column. CDM_CONTACT_HISTORY Added these columns: journey_id journey_occurrence_id   ... View more

Part of our #SASVoice | Learning from Our Customers series, sharing practical lessons from real customer situations.   The Challenge Large technology transformations create a challenge that software alone cannot solve: many people may need to change how they work at the same time.   A large public sector organization faced exactly this challenge as part of a major analytics modernization initiative.   Success depended on more than implementing new technology. Employees needed to understand the change, build confidence in using new capabilities and have access to the right support throughout the transition.   Preparing a large and diverse user community while maintaining day-to-day operations required a structured and scalable approach.   The Approach Workforce readiness became part of the transformation strategy from the beginning. Rather than treating training as a separate activity after the technology implementation, learning was integrated into the broader change effort.   Different user groups received learning opportunities aligned with their roles and responsibilities. The focus was not simply on completing training, but on helping employees develop practical skills and understand how new capabilities could support their work.   The Outcomes By investing in workforce readiness early in the transformation journey, the organization created a stronger foundation for adoption.   Benefits included: Improved user preparedness Greater confidence among employees Better support for organizational change More structured skills development across the user community   Lessons Learned A large transformation cannot focus only on the technology being introduced. It also needs to consider the people expected to use it. Addressing workforce readiness early helps make learning part of the transformation itself rather than a reaction after new technology has already been introduced. For large user communities, this becomes even more important: different roles may require different learning paths, levels of support and ways of applying new skills.   Learn More Planning an analytics transformation that affects a large user community? Explore how SAS Premium Learning Subscription can support scalable skills development across different teams and roles. ➡️ Learn more about SAS Premium Learning Subscription: https://www.sas.com/gms/redirect.jsp?detail=PLN69124_570064647   Editor's Note: This article is based on real customer experiences. Specific customer details have been anonymized to focus on the business challenge, approach and lessons learned.     ... View more

Can Data Help Us Predict Which Communities Need Better Healthcare?   Meet The Data Fusionist, the student team from Lamar University in Texas, USA who analyzed data to help identify communities at risk of chronic diseases. This was their topic for the global student competition, the Curiosity Cup 2026, where they earned a spot among the 13 Finalists from around the world. The team worked with publicly available data from the US Centers for Disease Control and Prevention (CDC), analyzing 78,815 census tracts across the United States. They combined information on nine chronic conditions, including diabetes, obesity, high blood pressure, asthma and depression, to create a community-level risk index. They also considered factors such as health behaviors, healthcare access and socioeconomic conditions.   Using SAS Viya for Learners and SAS Viya Workbench for Learners, the students compared five models to classify communities into low-, medium- and high-risk categories. Gradient Boosting performed best, achieving an AUC-ROC score of 0.9772 and a macro-averaged F1 score of 0.9231 on the validation data. The team also transformed the results into maps to make geographical patterns easier to understand.   One of their key findings was 1,303 emerging risk hotspots: areas classified as low risk by the team's index but predicted by the model to fall into the medium- or high-risk category.   These findings could help public health professionals identify communities that warrant further investigation and explore where preventive services and support might be prioritized.   The project demonstrates how data analytics, machine learning and geographical visualization can turn complex public health data into insights that are easier to interpret and potentially useful for decision-making. It is a great example of students applying their technical skills to explore a real-world challenge and contribute to more informed public health planning.   Congratulations to Siyapze Ngongo, Muna Kandel, and to their Faculty Advisor Sujing Wang. You can read the whole project, including the graphs and other details, as a PDF just under the main headline of this article. ... View more

Hello, I have    data test; z='x+y'; x=1; y=2; w=input(z,comma9.); run;  I need w=3, but for some reason it is just a missing value, w=.   Thanks ... View more