Machine Learning Model for Predicting the Achievement of the Graduate Profile Through Academic Performance in University Students

Arana M.; Camborda M.; Calderon S.; Castro F.; Arana M.; Huaricapcha B. · Proceedings - 10th International Symposium on Accreditation of Engineering and Computing Education, ICACIT 2024 (2024) · DOI: 10.1109/icacit62963.2024.10788599

Resumen

The profile of the graduate allows to understand the objective of training during the teaching-learning process in the higher educational institutions, which, in turn, shows the competences acquired by the students. In order to predict the achievement of the captured profile, the present research sought to implement a model in machine learning to predict the achievement of the profile of the graduate in the students of the Faculty of Systems Engineering of the National University of the Center of Peru (hereinafter nominated as FIS-UNCP), having as input indicators academic performance. The research was carried out following the scientific method, of a quantitative approach, explanatory-predictive level, where the design was nonexperimental longitudinal trend, the chosen population took into account the 355 students of the FIS-UNCP enrolled during the 2023-II academic semester. After the investigation, the result was obtained that the predictive model presents a 97.50% accuracy in the forecasts, with a specificity of 100%, evidencing that the model succeeds in predicting the achievement of the profile of the graduate having as inputs to the indicators of the academic performance of the students. In conclusion, with a T-value=3.239 and P-value=0.001, it can be stated that academic performance significantly influences the achievement of the graduate profile based on a prediction model with machine learning in FIS-UNCP students.

Instituciones: Universidad Continental; Universidad Peruana Los Andes; Universidad Nacional del Centro del Perú