# Dropout Prediction over Weeks in MOOCs via Interpretable Multi-Layer Representation Learning

arXiv: https://arxiv.org/abs/2002.01598 · HTML: https://mlsanity.com/paper/2002.01598/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2020.

## Built on by (most cited first, 2 of 2)

- [Click-Based Student Performance Prediction: A Clustering Guided Meta-Learning Approach](https://mlsanity.com/paper/2111.00901/) (2021)
- [Knowledge-Guided Dynamic Systems Modeling: A Case Study on Modeling River Water Quality](https://mlsanity.com/paper/2103.00792/) (2021)

## Abstract (arXiv)

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.