Academic Machine Learning Models

This project addresses the need to capitalize on the vast academic information collected by the Universidad Politécnica Salesiana (UPS) over its 22+ years of operation. The primary goal is to transform this currently underutilized institutional data into predictive and prescriptive tools through the implementation of Machine Learning. It seeks to resolve the lack of awareness regarding the value of existing data by proposing models that optimize key university management processes. The solution involves applying AI techniques to generate predictions and recommendations that assist in streamlining faculty talent allocation, efficient timetable creation, and knowledge classification. The methodology is quantitative, encompassing a state-of-the-art review, creation/adaptation of data corpora, formulation of mathematical models, and development of end-user software. The expected impact includes optimized academic management and the structuring of academic corpora for future validation by the scientific community.<br/><br/><b>Goal</b>: <br/>To develop prediction and recommendation models based on Machine Learning techniques applied to the UPS institutional database to optimize academic management and diversify university analyses.<br/><br/><b>Research lines</b>: <br/>Computer systems and artificial intelligence