Análisis de datos para la optimización eficiente de horarios y aprendizaje automático.

Abstract

In recent years, the integration of machine learning (ML) techniques into school management systems offers several opportunities to enhance efficiency and decision-making in the educational field. Applying ML in education can yield significant benefits. However, it is important to note that the successful integration of ML techniques into school management systems requires a robust data infrastructure, proper data collection, and consideration of ethical and privacy issues. Furthermore, ML should not replace human interaction in education but rather complement and improve it by providing educators and students with additional tools for educational success. Due to the increased complexity in the curriculum of the Computer Systems Engineering program, it is necessary to carry out a more reliable and automated prediction of semester schedules. To address the manual scheduling generation problem, a comprehensive analysis of the existing process was conducted. This involved gathering relevant information on how semester schedules are currently generated in the educational institution. The current approach used for scheduling was studied, along with an analysis of the problems and limitations associated with the manual process. Various ML techniques that could be applied to the scheduling generation problem were investigated. This could include optimization algorithms, clustering or classification algorithms, genetic algorithms, or other machine learning approaches that can be adapted to the specific problem.