Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2020

Abstract

As students progress in their university programs, they have to face many course choices. It is important for them to receive guidance based on not only their interest, but also the "predicted" course performance so as to improve learning experience and optimise academic performance. In this paper, we propose the next-term grade prediction task as a useful course selection guidance. We propose a machine learning framework to predict course grades in a specific program term using the historical student-course data. In this framework, we develop the prediction model using Factorization Machine (FM) and Long Short Term Memory combined with FM (LSTM-FM) that make use of both student and course attributes as well as past student-course grade data. Our experiment results on a real-world data of an autonomous university in Singapore show that both methods yield better prediction accuracy than the baseline methods. Our methods are also robust to handle cold start courses with the average prediction error can be as low as three quarter grade di erence from the ground truth.

Keywords

Grade prediction, Factorization machine, Long short term memory

Discipline

Categorical Data Analysis | Databases and Information Systems | Numerical Analysis and Scientific Computing

Research Areas

Data Science and Engineering

Publication

Proceedings of the Thirteenth International Conference on Educational Data Mining (EDM 2020): Virtual conference, July 10-13

First Page

700

Last Page

703

ISBN

9781733673617

City or Country

Virtual

Copyright Owner and License

LARC and Authors

Additional URL

https://educationaldatamining.org/edm2020/proceedings/

Download

Share

COinS