Deep Learning to Predict Student Outcomes

In the world of MOOCs, an automated machine which reliably predicts student outcomes in real-time (or early stages), would be a valuable tool for making smart decisions about when (and with whom) to make live educational interventions as students interact with online coursework, with the aim of increasing engagement, providing motivation, and empowering students to succeed. Thus, in this talk, we first recast the student outcome prediction problem as a sequential event prediction problem, introduce a GritNet architecture, and develop an unsupervised domain adaptation method to transfer a GritNet trained on a past course to a new course without any (students' outcome) label. Our results for real Udacity students' graduation predictions show that the GritNet not only generalizes well from one course to another across different Nanodegree programs, but enhances real-time predictions explicitly in the first few weeks when accurate predictions are most challenging. In contrast to prior works, the GritNet does not need any feature engineering, and it can operate on any student interaction data associated with a timestamp.