Machine Learning Classifiers Do Not Improve the Prediction of Academic Risk: Evidence from Australia

Machine learning methods tend to outperform traditional statistical models at prediction. In the prediction of academic achievement, ML models have not shown substantial improvement over logistic regression. So far, these results have almost entirely focused on college achievement, due to the availability of administrative datasets, and have contained relatively small sample sizes by ML standards. In this article we apply popular machine learning models to a large dataset ($n=1.2$ million) containing primary and middle school performance on a standardized test given annually to Australian students. We show that machine learning models do not outperform logistic regression for detecting students who will perform in the `below standard' band of achievement upon sitting their next test, even in a large-$n$ setting.
15 pages, 2 tables, 6 figures. Note that previous versions of this paper contained an error in our codes. The error has been rectified and the paper substantially rewritten