Predicting school dropout rates in primary education using artificial intelligence techniques

Hidalgo-Hidalgo K.J.; Huaricancha-Estrella R.; Abarca-Torres A.R.; Huaman-Alegria M.; Espino-Oncebay P.; Rodriguez-Baca L.S. · International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2025 (2025) · DOI: 10.1109/iceccme64568.2025.11277965

Resumen

This study aimed to analyze the consequences of a predictive mechanism using artificial intelligence (AI) for risk classification in reducing early school leaving in a National Educational Institution. This study is aligned with Sustainable Development Goal 12: Responsible Production and Consumption. It was applied, with a quantitative approach, pre-experimental design, and explanatory scope. The population consisted of 121 elementary school students. Techniques such as direct observation through a field notebook and registration cards were used. Attendance and monthly consent indicators were analyzed. The descriptive results showed an increase in the average monthly attendance from 0.016 to 0.988, with a decrease in absenteeism from 0.998 to 0.002. The model achieved an average accuracy of 82.28%, a robust performance. In conclusion, the predictive system proved to be effective in anticipating cases.

Instituciones: Universidad César Vallejo