Notre Dame has worked with our First Year of Studies program with over 2000 students to provide visualizations to identify students at risk in an effort to intervene early enough to make a change. We will demo current visualizations and how they assist our First Year program. We are also combining data from multiple sources to provide an integrated view of student learning activities in the LRW. (still in our testing phase)
The LAMP Consortium’s SOLÉ (Supporting On Line Engagement) system extracts data from the Sakai Session and Events tables to provide a weekly dashboard about on-line courses. The focus is on instructors and their engagement with students, a critical component of successful on-line courses. By providing weekly feedback, instructors are able to modify the ways they engage student while it can still make a difference, rather than waiting until after the class is completed. This Lightning Talk will briefly show how SOLÉ works and explain the philosophy behind its design.
Marist College has completed a new version of its early alert system of academically at-risk students. The new release, coded MUSE (Marist Universal Student Experience) implements a predictive modeling architecture based on a stacked ensemble (a machine learning method that involves training a second stage learner to find the optimal combination of a collection of based learners). The solution spans extraction, transforming and loading into a warehouse (ETL stage) that feeds the revamped predictive modeling architecture, which in turn delivers results (predictions of at risk students) as well as student activity metrics, that can be visualized through a presentation layer integrated into the learning management system.
The Apereo Foundation - http://www.apereo.org/
To post to this group, please contact [hidden email]
You received this message because you are subscribed to the Google Groups "Apereo Announcements" group.
To unsubscribe from this group and stop receiving emails from it, send an email to [hidden email].