Prediction of Pedagogical Improvement through University Teacher Training with Machine Learning Tools

Arana M.; Camborda M.; Arana M.; Huaricapcha B.; Calderón S.; Camarena M. · ICACIT 2025 - Proceedings: 11th International Symposium on Accreditation of Engineering and Computing Education (2025) · DOI: 10.1109/icacit66767.2025.11369723

Resumen

In today’s digital age, the training of university teachers is crucial for maintaining educational quality, especially in pedagogical development. The present research seeks to make predictions in order to determine the real impact of these skills on pedagogical development. This study aimed to determine how teacher training, using machine learning tools, influences the improvement of pedagogical development in the Systems Engineering Faculty of the Universidad Nacional del Centro de Perú (FIS-UNCP). The research adopted a quantitative approach, applied type and longitudinal non-experimental design, with a sample of 26 FIS-UNCP teachers. The results revealed that teacher training significantly influences pedagogical improvement, with a predictive model that reached 91.26% accuracy and an error margin of 8.74%. The dimensions of training, planning, thematic content, methodology, and evaluation also had a significant influence on pedagogical development.

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