Resumen

Introduction:Higher education is transforming with the adoption of virtual modalities and the integration of technologies such as artificial intelligence (AI), machine learning (ML), neural networks (NN), and big data (BD). These technologies are redefining access and student retention, offering personalized solutions to enhance the educational experience in virtual environments.Methodology:This systematic review, based on the PRISMA method, examines how the interaction of AI, ML, NN, and BD influences the prediction and management of student dropout, highlighting the applications of learning analytics (LA) to improve educational interventions. Results:The results show that AI, ML, and BD are effective in predicting and managing school dropout, allowing for more personalized interventions. Analyzing large volumes of data helps identify crucial patterns for designing retention strategies. Discussion: Despite the significant improvements in personalized learning and resource optimization offered by these technologies, they face ethical and operational challenges that must be considered. Conclusions:The integration of AI, ML, NN, and BD in higher education is a promising approach to enriching the student experience and outcomes, emphasizing the importance of strategic investments and a robust ethical framework for effective implementation.

Palabras clave