Modelos híbridos inteligentes para el aprendizaje personalizado en la educación superior

Overview & Synopsis

This research addresses the need to manage student diversity and academic trajectories in higher education through personalized learning, overcoming the risks of algorithmic reductionism and decontextualized automation that depersonalize the educational process. Through an applied instructional design approach and a systematic review of the technical literature, this study proposes and substantiates the architecture of an intelligent hybrid model that coherently articulates and integrates massive analytical data sources from learning management systems (LMS), educational ontologies, explicit pedagogical rules, and machine learning algorithms. The conceptual results demonstrate that the development and implementation of adaptive environments and intelligent tutors make it possible to model dynamic student profiles and structure flexible learning paths that continuously adjust according to students’ achievement levels. In this context, we successfully designed highly efficient early-warning systems based on data mining that promptly identify signs of academic risk and vulnerability, thereby significantly reducing dropout rates and enhancing student retention. It is concluded that the true effectiveness of intelligent hybrid models is not limited to their metric or predictive accuracy, but rather lies substantially in active faculty mediation, algorithmic transparency, decision explainability, and ethical and institutional governance of information. Technological personalization gains viability and social value only when it is established as a tool aimed at strengthening equity, inclusion, and informed human decision-making within the university ecosystem.