Desarrollo y evaluación de un algoritmo educativo basado en inteligencia artificial para mejorar la enseñanza de la división en estudiantes de secundaria utilizando Python y Google Cola

This study aimed to design, implement and evaluate educational algorithms based on artificial intelligence (AI) to improve the teaching of division operation to high school students. The interactive tool in Python and Google Colab proved to be highly effective, with a robust and efficient approach. The algorithm incorporated random number generation, precise calculations, intuitive user interaction, exception handling, and an iterative practice loop. Validation of the splitting model using precision, completeness, and F1 Score testing yielded promising results, with a balance between precision and completeness. Statistical analysis, supported by Student's t-test, revealed a significant difference in learning performance between the control and experimental groups. Students using the AI tool showed a significant increase in understanding and application of division compared to traditional methods. The tool not only improved mathematical accuracy, but also encouraged active participation and deep understanding. These results have substantial pedagogical implications, supporting the idea that the integration of artificial intelligence technologies in mathematics teaching can offer significant advantages. Educators and course designers can consider implementing similar tools to enrich the learning experience and improve educational outcomes. However, the importance of addressing ethical and privacy considerations when implementing these technologies is highlighted. In summary, this study supports the feasibility and positive impact of artificial intelligence on mathematical learning, marking a significant advance in educational technological integration. Este estudio se propuso diseñar, implementar y evaluar algoritmos educativos basados en inteligencia artificial (IA) para mejorar la enseñanza de la operación de división a estudiantes de secundaria. La herramienta interactiva en Python y Google Colab demostró ser altamente efectiva, con un enfoque robusto y eficiente. El algoritmo incorporó generación aleatoria de números, cálculos precisos, interacción intuitiva con el usuario, manejo de excepciones y un bucle de práctica iterativo. La validación del modelo de división mediante pruebas de precisión, exhaustividad y F1 Score arrojó resultados prometedores, con un equilibrio entre precisión y exhaustividad. El análisis estadístico, respaldado por la prueba t de Student, reveló una diferencia significativa en el rendimiento de aprendizaje entre los grupos de co