Predicting university student dropouts in Latin America using machine learning

Abstract

In the university context, student dropout has become one of the most recurring problems, both in the short and long term. The objective of this research was to develop a predictive model using the random forest (RF) algorithm to identify patterns associated with university dropout. To achieve this, the knowledge discovery in databases (KDD) methodology was applied, which encompasses the stages of selection, preprocessing, transformation, data mining, and interpretation of results. The RF model demonstrated superior performance compared to other evaluated models, achieving an accuracy of 87%, a precision of 86%, a recall of 85%, an F1-score of 85%, and an receiver operating characteristic (ROC) area under the curve (AUC) of 0.91, highlighting its high predictive capability compared to other techniques analyzed. Therefore, the application of the proposed model is recommended in various university institutions in order to identify potential dropout cases at an early stage.