This session will conduct a case analysis of Texas universities, exploring how institutions use data to drive structural and systematic changes, rather than just identifying individual students as "at risk." In the era of big data, machine learning, and predictive analytics, public policy increasingly depends on data-driven predictions to tackle resource allocation, accountability, and success in public goods. Education, a central focus of public policy, is particularly complex and multidimensional. In postsecondary education, predictive analytics plays a critical role in promoting student success by enhancing persistence through early alert systems. While traditional early alert systems and logistic regressions are commonly used for student tracking and intervention, using big data to assess institutional effectiveness is a newer approach. Predictive models vary significantly across institutions based on factors like institutional type (e.g., two-year vs. four-year, technical schools vs. online programs), regional context, and resource availability, as datasets and student populations differ. Policymakers and institutional leaders need more insight into how campus-level offices use changes to institutional policies and practices to meet state-mandated accountability for postsecondary success. This session will focus on understanding how faculty, staff, and administrators use data to address institutional challenges, optimize operational effectiveness, and foster an environment that promotes student success.

• Attend this session to understand how predictive analytics can transform institutional practices and improve student outcomes.

• Expect to learn how Texas universities leverage data to make systemic changes that benefit student success.

• Discover the innovative ways faculty, staff, and administrators use data to overcome challenges and enhance operational efficiency.