Predicting Performance on MOOC Assessments using Multi-Regression Models

TL;DR

This paper introduces a personalized linear multiple regression model that predicts student assessment scores in MOOCs in real-time by analyzing prior activity and participation data, aiding in understanding student performance.

Contribution

The study presents a novel real-time, personalized regression model for predicting MOOC assessment scores based on student activity logs, improving prediction accuracy over baseline methods.

Findings

The model outperforms baseline approaches in prediction accuracy.

Key features related to study habits are identified as significant predictors.

The approach demonstrates potential for real-time performance prediction in MOOCs.

Abstract

The past few years has seen the rapid growth of data min- ing approaches for the analysis of data obtained from Mas- sive Open Online Courses (MOOCs). The objectives of this study are to develop approaches to predict the scores a stu- dent may achieve on a given grade-related assessment based on information, considered as prior performance or prior ac- tivity in the course. We develop a personalized linear mul- tiple regression (PLMR) model to predict the grade for a student, prior to attempting the assessment activity. The developed model is real-time and tracks the participation of a student within a MOOC (via click-stream server logs) and predicts the performance of a student on the next as- sessment within the course offering. We perform a com- prehensive set of experiments on data obtained from three openEdX MOOCs via a Stanford University initiative. Our experimental results show the promise of the proposed ap- proach in comparison to baseline approaches and also helps in identification of key features that are associated with the study habits and learning behaviors of students.