GritNet: Student Performance Prediction with Deep Learning

TL;DR

GritNet is a deep learning model using BLSTM for early and accurate student performance prediction in online courses, outperforming traditional methods especially in initial weeks.

Contribution

The paper introduces GritNet, a novel deep learning approach for student performance prediction, recasting it as a sequential event prediction problem.

Findings

GritNet outperforms logistic regression in student prediction accuracy.

Significant improvements in early-week predictions.

Effective in real-world Udacity student data.

Abstract

Student performance prediction - where a machine forecasts the future performance of students as they interact with online coursework - is a challenging problem. Reliable early-stage predictions of a student's future performance could be critical to facilitate timely educational interventions during a course. However, very few prior studies have explored this problem from a deep learning perspective. In this paper, we recast the student performance prediction problem as a sequential event prediction problem and propose a new deep learning based algorithm, termed GritNet, which builds upon the bidirectional long short term memory (BLSTM). Our results, from real Udacity students' graduation predictions, show that the GritNet not only consistently outperforms the standard logistic-regression based method, but that improvements are substantially pronounced in the first few weeks when accurate predictions are most challenging.