Bootstrapping Your Analytics


Join Malcolm Brown, EDUCAUSE Learning Initiative director, and Veronica Diaz, ELI associate director, as they moderate this webinar with Vernon Smith, vice president of academic affairs at Rio Salado College, a nationally recognized community college with over 69,000 enrollments, 42,000 of which are online. Previously, he served as dean of instruction overseeing institutional effectiveness, strategic planning, accreditation, and early-college programs. As faculty chair for foreign languages, he was a pioneer in online language courses and programs; he also served as faculty senate president. He has an extensive background in distance learning issues and practices, including effective assessment and retention strategies and predictive modeling for student success.

Smith's research interests include high-quality, cost-effective production models for online courses, the unbundling of the faculty role, adjunct faculty issues, academic integrity, and teaching and learning. Smith serves on the board of directors of EDUCAUSE and on the membership and data working groups for Transparency by Design, a national accountability initiative.

Will data analytics and predictive modeling drive the next wave of innovation in higher education? If so, how do you get started? Like the sophisticated systems used by Netflix or, these “learner analytics” have been made possible by capturing and utilizing the large amounts of actionable information on student behaviors and performance from multiple data sources. These predictive models create new possibilities for student engagement, personalization, and interventions for student success and completion. Vernon Smith will share the journey at Rio Salado College, a Maricopa Community College with over 42,000 online students, and how it has bootstrapped its data-mining and predictive-modeling efforts since 2008, emerging as an early adopter and leader with models that predict student success by the eighth day of class with 70% accuracy. He will also help identify steps to build your own predictive models tailored to your institution.

Download Resources