MOOCs and online courses have notoriously high attrition. One challenge is that it can be difficult to tell if students fail to complete because of disinterest or because of course difficulty. Starting from the Deep Knowledge Tracing framework, we account for student engagement by including course interaction covariates. With these, we find that we can predict a student’s next item response with over 88% accuracy. Using these predictions, targeted interventions can be offered to students and targeted improvements can be made to courses.
This is a project prize winner for CS 230, Spring 2018.