Predicting the risk of student dropout in the engineering programs at the C´ordoba Regional Faculty

Abstract

This study aims to estimate the risk of academic dropout among students at the National Technological University, C´ordoba Regional Faculty (UTN FRC), using data from the institutional academic system and complementary sources. The objective is to develop predictive models based on data science and machine learning techniques that allow for individual prediction of the probability of dropout, facilitating timely interventions. The methodological approach considers the analysis of historical student records, incorporating relevant academic, administrative, and contextual variables. The scope of the project ranges from the construction and validation of prediction models to the implementation of an early warning system that provides key information to academic management teams for decision-making. The proposed system seeks to identify risk patterns and support institutional strategies aimed at improving student retention. Through the incorporation of artificial intelligence into educational management, the aim is to contribute to strengthening academic trajectories in technological higher education.