Model for Curriculum Analysis Based on Process and Data Mining

The article addressed the importance of curricular aspects in academic management, highlighting its role in learning and optimizing the curriculum. Student performance was analyzed by studying enrollment, academic progress and risk factors such as dropout, poor performance and failure of subjects. The application of process mining and data analysis made it possible to identify hidden patterns, facilitating pedagogical interventions to improve educational quality. Key concepts were defined, differentiating between curricular management and data analysis. At the curricular level, successful graduation, student dropout, and strategic curriculum planning were detailed. Regarding data management, predictive analytics was highlighted as a tool for decision-making in higher education. The study used a quantitative approach, structured in three phases: exploration, design and validation. In the exploratory phase, previous studies on graduation, curricular management and dropout were reviewed. During the design phase, process mining techniques were integrated to evaluate the student trajectory and detect bottlenecks. Finally, in the validation phase, the model was applied in an academic program, demonstrating its effectiveness in detecting curricular problems. The results indicated that the CRISP-DM methodology was the most used in educational data mining, providing a structured framework for the identification and resolution of academic problems.Keywords: Process mining, curriculum management, data analytics.