Analysis of the causes of dropout of students from the engineering faculty of the metropolitan technological institute (ITM)

Abstract

The fundamental purpose of this project is to develop a model aimed at analyzing and understanding the reasons behind academic dropouts in the ITM Faculty of Engineering. To achieve this, the creation of dashboards will be implemented that will simplify decision-making at the institutional level. The process is structured in various phases, beginning with an exploratory analysis where statistically significant variables are identified. Subsequently, the Dashboard is built, where the results are presented in a precise and understandable manner, using graphs, tables and visualizations. In the results of the exploratory analysis, variables such as Age, Stratum, Level, Seniority, PP and Origin are revealed, which present correlations with academic status. These findings are fundamental to understanding behavioral patterns and influential factors in student dropout. The next step involves the implementation of a Machine Learning Model, where six key variables are used for its design and training. It is highlighted that seniority, age and level are identified as crucial variables in predicting academic "State". It is anticipated that the performance of the model will improve with the incorporation of more data, and the exploration of new variables is suggested to enrich the predictions. In conclusion, this project offers a comprehensive approach that combines statistical analysis and machine learning models to understand and prevent academic attrition.