Educational Data Mining for Dropout Prediction: Trends, Opportunities, and Challenges

Abstract

Today, we face academic, social, and economic losses associated with student dropouts. Several studies have applied data mining techniques to educational datasets to understand dropout profiles and recognize at-risk students. To identify the contextual (academic levels, modalities, and systems), technical (tasks, categories of algorithms, and tools), and data (types, coverage, and volume) characteristics related to these works, we performed a systematic literature review, considering institutional and academic degree dropout. Internationally recognized repositories were searched, and the selected articles demonstrated, among other characteristics, a greater exploration of educational, demographic, and economic data of undergraduate students from classification techniques of decision tree ensembles. In addition to not having identified any study from underdeveloped countries among the selected ones, we found shortcomings in the application of predictive models and in making their predictions available to academic managers, which suggests an underutilization of the efforts and potential of most of these studies in educational practice.