Models for early prediction of at-risk students in a course using standards-based grading

TLDR

Predictive modeling can identify at‑risk students early, but adapting such models to standards‑based grading—an educationally advantageous system—has not yet been explored, and minimizing false negatives while controlling false positives is critical. The study compares predictive methods for identifying at‑risk students in a standards‑based grading course. The authors compared seven predictive methods using only in‑semester performance data, applying feature selection to reduce variables and improve generalizability. The Naïve Bayes classifier and an ensemble of SVM, K‑NN, and Naïve Bayes achieved the best performance among the seven tested models.

Abstract

Using predictive modeling methods, it is possible to identify at-risk students early and inform both the instructors and the students. While some universities have started to use standards-based grading, which has educational advantages over common score-based grading, at–risk prediction models have not been adapted to reap the benefits of standards-based grading in courses that utilize this grading. In this paper, we compare predictive methods to identify at-risk students in a course that used standards-based grading. Only in-semester performance data that were available to the course instructors were used in the prediction methods. When identifying at-risk students, it is important to minimize false negative (i.e., type II) error while not increasing false positive (i.e., type I) error significantly. To increase the generalizability of the models and accuracy of the predictions, we used a feature selection method to reduce the number of variables used in each model. The Naive Bayes Classifier model and an Ensemble model using a sequence of models (i.e., Support Vector Machine, K-Nearest Neighbors, and Naive Bayes Classifier) had the best results among the seven tested modeling methods.