When creating a new object, SAS Visual Investigator displays a button using the format “New [Object Name]”. In Hebrew, the word “New” must match the grammatical gender of the object name: Masculine: חדש Feminine: חדשה Currently, the translation does not distinguish between masculine and feminine object names. As a result, the button may display grammatically incorrect Hebrew. Requested enhancement: Please provide the ability to configure the translation of “New” according to the grammatical gender of each object type, or provide separate translation keys for the masculine and feminine forms. This is important for Hebrew localization, as displaying the incorrect gender is grammatically incorrect and negatively affects the user experience. ... View more

Ready to take the spotlight at SAS Innovate 2027? Now is the perfect time to get involved in SAS's biggest data and AI event of the year! ... View more

Watch this Ask the Expert session to discover how to move from idea to execution faster – without sacrificing control – by enabling always-on, intelligent decisioning across every customer touchpoint.     Watch the Webinar   In this webinar, you will learn how to: Replace static campaigns with always-on decisioning using real-time arbitration logic that balances business value, customer context and propensity scores. Unify fragmented customer data and channel-specific rules into a single decisioning layer so every touchpoint reflects a coherent, consistent view. Empower marketing teams to act independently with intuitive, low-code/no-code decisioning, reducing reliance on IT while accelerating speed from design to deployment. Continuously improve outcomes with adaptive learning approaches that evolve automatically as customer behavior shifts. The questions from the Q&A segment held at the end of the webinar are listed below and the slides from the webinar are attached.   1. Can predictive machine learning or generative AI models be used for arbitration? Yes. You can use scores generated by your own predictive models, regardless of which models produced them, as long as the results provide the required customer, action and score combination.   You can also call externally hosted models through web services from within the decision flow. Custom nodes can execute Python code, providing additional flexibility for integrating external services and models.   2. Is there a limit to the number of attributes that can be used in eligibility criteria? There is no defined limit that I’m aware of, but you need to balance flexibility with manageability and performance. Using thousands of attributes, particularly attributes containing large amounts of data, could affect real-time execution.   Because these decisions are intended to run in milliseconds, you should test performance in the test runtime environment before deploying them to production.   3. As a SAS administrator, what can I do to make these tools easier for business users and programmers to use? Administrators can make the experience easier by properly configuring and documenting the decision data sources used by the system. Business users should be able to create rules without needing to understand the underlying data mapping.   Provide clear, meaningful display names for attributes and supply representative test data when appropriate. Test data can also be anonymized. When meaningful test values are available, the interface can present users with selectable values, reducing the need to manually enter data and helping them create rules more consistently.   4. When adaptive learning replaces the traditional arbitration formula, what guardrails remain in effect? Eligibility rules, action-level constraints and contact rules are applied before adaptive learning. These rules determine the final set of eligible actions, and adaptive learning operates only on that remaining set.   Organizations can choose how many constraints to configure, but any configured guardrails are applied before the adaptive learning process selects an action.   5. How can you audit or explain why a particular action was selected for a customer, especially when adaptive learning is involved? Each decision has an associated decision history table and supporting logs. The system records the information received when the decision was invoked, along with the rules that were executed.   This history can be used to determine which action a customer received, why it was selected and what the customer’s state was at that point in time. The information supports explainability and auditing, and it can also help marketing users identify rules that may need to be adjusted to improve action performance.   Recommended Resources Register now: SAS MarTech Connect 2026 - Spark innovation, build your network, and share your ideas The Forrester Wave™: Customer Analytics Technologies, Q2 2026 SAS Thought Leadership & SAS Community Articles on Data Science & Martech Follow SAS CI 360 on LinkedIn to explore insights shaping smarter marketing SAS Learning Subscription for CI Please see additional resources in the attached slide deck.   Want more tips? Be sure to subscribe to the Ask the Expert board to receive follow up Q&A, slides and recordings from other SAS Ask the Expert webinars. ... View more

SAS Viya column lineage is only available for flows that are stored in Content. However, Git is only available for flows on NFS. Unfortunately, these are mutually exclusive options. Are more people running into this issue, and are there any ideas for possible workarounds ... View more

I tried cdisc datasets website but it provides synthetic datasets separate from study protocol, SAP etc. so they are not associated for the same clinical trial. ... View more