Effective Feature Prediction Models for Student Performance

Abstract

The ability to accurately predict how students will perform has a significant impact on the teaching and learning process, as it can inform the instructor to devote extra attention to a particular student or group of students, which in turn prevents those students from failing a certain course. When it comes to educational data mining, the accuracy and explainability of predictions are of equal importance. Accuracy refers to the degree to which the predicted value was accurate, and explainability refers to the degree to which the predicted value could be understood. This study used machine learning to predict the features that best contribute to the performance of a student, using a dataset collected from a public university in Jeddah, Saudi Arabia. Experimental analysis was carried out with Black-Box (BB) and White-Box (WB) machine-learning classification models. In BB classification models, a decision (or class) is often predicted with limited explainability on why this decision was made, while in WB classification models decisions made are fully interpretable to the stakeholders. The results showed that these BB models performed similarly in terms of accuracy and recall whether the classifiers attempted to predict an A or an F grade. When comparing the classifiers' accuracy in making predictions on B grade, the Support Vector Machine (SVM) was found to be superior to Naïve Bayes (NB). However, the recall results were quite similar except for the K-Nearest Neighbor (KNN) classifier. When predicting grades C and D, RF had the best accuracy and NB the worst. RF had the best recall when predicting a C grade, while NB had the lowest. When predicting a D grade, SVM had the best recall performance, while NB had the lowest.