MOOC Dropout Prediction: Lessons Learned from Making Pipelines Interpretable

Dropout prediction in MOOCs is a well-researched problem where we classify which students are likely to persist or drop out of a course. Most research into creating models which can predict outcomes is based on student engagement data. Why these students might be dropping out has only been studied through retroactive exit surveys. This helps identify an important extension area to dropout prediction— how can we interpret dropout predictions at the student and model level? We demonstrate how existing MOOC dropout prediction pipelines can be made interpretable, all while having predictive performance close to existing techniques. We explore each stage of the pipeline as design components in the context of interpretability. Our end result is a layer which longitudinally interprets both predictions and entire classification models of MOOC dropout to provide researchers with in-depth insights of why a student is likely to dropout.