Prediction of Students’ Academic Performance Using Machine Learning: The Case of Wachemo University

Abstract

An educational institution must always have an estimated previous knowledge of enrolled students to predict their performance in future academics. The comparative analysis of results helped the weaker students to improve their passing which has eventually led to increased overall passing average of the course. In this research, the data was analyzed using classification models with mixing the internal and external data sources, and then compared the model to select the best prediction model that produced highest accuracy, which helped the university to identify the students likely to fail, and work on their academics accordingly in order to achieve better results. Accuracy of this classification algorithm is compared in order to check best performance. K-NN achieved the best prediction results, which are very satisfactory compared to those of similar approaches in both classification.