Analyzing and Predicting Academic Dropout at the Universidad de Córdoba

Given the circumstances created by the pandemic, it was in the university’s interest to study, analyze and predict the academic performance of the students based on their online activities on both the Learning Management Systems (LMS) and the academic platform Power Campus. Also, the development of technological tools to attain a deep understanding of the academic behaviour of the students and to propose institutional strategies of continuous improvement is highly desirable.

Given the latter, models for predicting academic dropout were developed. These models took into account several variables such as grades, gender, semester, online activity on both the LMS and Power Campus platforms, among others. Further, a dashboard was built so that users could get useful insights into the academic behavior of the university´s community. This dasboard can be understood as a tool that helps their users perform a friendly exploratory data analysis (EDA) of the academic information captured by the institution's servers.

As expected, the main goal of the project was to help the institution in the reduction of academic dropout. It is worthwhile to mention that, among around one hundred projects, this work was selected as one of the best five data science projects of the fifth cohort of the Data Science for All program. For more information, please visit the following site: DS4A Capstone Project Spotlight.