Using Analytics to Support Academic Advising for At-Risk STEM Students

Recent efforts using learning analytics have been limited in scope (e.g., well-defined problem spaces) and in scale (targeting individual courses, using proprietary software). We will describe an early warning system in use in the "STEM Academies," academic support programs aimed at increasing success and retention of undergraduate students identified as at-risk. The Student Explorer system leverages data from an open-source LMS to provide academic advisors with real-time feedback about student performance and engagement. Specifically, we use LMS data to track student performance across courses and provide a timely way to intervene with those students struggling academically.

Learning Objectives:
* Learn how LMS-generated data can be used to monitor student engagement and performance
* Learn the iterative process we have undertaken to work with the advising experts on our campus to capture their wisdom about factors related to student success in gateway STEM courses and embody that knowledge in the Student Explorer displays
* Learn how student engagement and performance is coded and categorized within the Student Explorer system
* Learn how to leverage existing academic advising staff to provide just-in-time intervention and promote student use of campus support resources
* Learn about the SoLAR and the various ways they can continue the conversation about learning analytics by interacting with that community