Predictive models for the detection of problems in autonomous learning in higher education students virtual modality

Abstract

The concept of autonomous learning has been resignified in recent years as a result of the expansion of the different forms of face-to-face, blended learning and online learning. Virtual education in higher education institutions has become an effective option to increase and diversify opportunities for access and learning, however, in this type of modality persists high rates of attrition, repetition and low average performance. academic. Recent research shows that the problem is accentuated because most students have difficulty planning, executing and monitoring their learning process autonomously. From this perspective, the research focuses on the analysis and development of a predictive model to identify problems in the autonomous learning and academic performance of university students studying a distance or virtual study modality. Unlike other studies, this work uses pedagogical techniques and algorithms from the analysis of learning to analyze and interpret academic data generated in virtual contexts. From this, information will be obtained and discovered to improve and optimize learning in order to contribute to the success of students with adequate prediction and intervention strategies