Artificial intelligence for student dropout prevention

Abstract

This study addresses the issue of student dropout, a complex phenomenon with serious social and educational consequences. It highlights the need to find innovative solutions to prevent it. The main objective of the study is to develop an artificial intelligence-based system that can proactively identify students at risk of dropping out, in order to implement timely intervention strategies. Machine learning techniques are used to analyze large datasets of students. This data includes academic, sociodemographic, and contextual information. From this data, predictive models are trained to identify patterns associated with dropout and thus predict which students are most likely to drop out. Preliminary results show that machine learning models, especially those based on decision trees, are able to identify students at risk of dropping out with considerable accuracy. Additionally, it has been identified that factors such as academic performance and socioeconomic conditions are determinants in the decision to drop out of school. Our findings demonstrate the potential of artificial intelligence to significantly reduce student dropout rates. By enabling the early identification of at-risk students, our predictive models facilitate timely interventions. However, it is essential to acknowledge that dropout is a complex issue influenced by multiple factors, requiring a multifaceted approach involving various stakeholders.