Domain Adaptation for Real-Time Student Performance Prediction

TL;DR

This paper presents a domain adaptation approach using GritNet architecture for real-time student performance prediction across different courses without requiring labeled data, demonstrating effective generalization and early-week prediction accuracy.

Contribution

It introduces an unsupervised domain adaptation method for GritNet, enabling transfer of student performance models between courses without labeled data.

Findings

GritNet generalizes well across different courses and programs.

The method improves early-week prediction accuracy.

Effective for real-time performance prediction in online education.

Abstract

Increasingly fast development and update cycle of online course contents, and diverse demographics of students in each online classroom, make student performance prediction in real-time (before the course finishes) and/or on curriculum without specific historical performance data available interesting topics for both industrial research and practical needs. In this research, we tackle the problem of real-time student performance prediction with on-going courses in a domain adaptation framework, which is a system trained on students' labeled outcome from one set of previous coursework but is meant to be deployed on another. In particular, we first introduce recently-developed GritNet architecture which is the current state of the art for student performance prediction problem, and develop a new \emph{unsupervised} domain adaptation method to transfer a GritNet trained on a past course to a new course without any (students' outcome) label. Our results for real Udacity students' graduation predictions show that the GritNet not only \emph{generalizes} well from one course to another across different Nanodegree programs, but enhances real-time predictions explicitly in the first few weeks when accurate predictions are most challenging.