Dropout Prediction over Weeks in MOOCs via Interpretable Multi-Layer Representation Learning
This work addresses dropout prediction for MOOC platforms, offering an interpretable method that is incremental in improving efficiency and interpretability over existing techniques.
The paper tackles the problem of predicting student dropout in MOOCs within the next week using clickstream data, achieving performance similar to complex models with a simpler approach based on unsupervised multi-layer representation learning.
Massive Open Online Courses (MOOCs) have become popular platforms for online learning. While MOOCs enable students to study at their own pace, this flexibility makes it easy for students to drop out of class. In this paper, our goal is to predict if a learner is going to drop out within the next week, given clickstream data for the current week. To this end, we present a multi-layer representation learning solution based on branch and bound (BB) algorithm, which learns from low-level clickstreams in an unsupervised manner, produces interpretable results, and avoids manual feature engineering. In experiments on Coursera data, we show that our model learns a representation that allows a simple model to perform similarly well to more complex, task-specific models, and how the BB algorithm enables interpretable results. In our analysis of the observed limitations, we discuss promising future directions.