Improving On-Time Undergraduate Graduation Rate For Undergraduate Students Using Predictive Analytics

TL;DR

This study develops and evaluates predictive models to identify undergraduate students at risk of not graduating on time in Puerto Rico, aiming to improve graduation rates using data-driven techniques.

Contribution

The paper introduces a predictive analytics approach with the best boosting model to accurately forecast students at risk of delayed graduation.

Findings

Boosting model achieved highest predictive performance.

Oversampling improved model accuracy.

Pre-college factors are significant predictors.

Abstract

The on-time graduation rate among universities in Puerto Rico is significantly lower than in the mainland United States. This problem is noteworthy because it leads to substantial negative consequences for the student, both socially and economically, the educational institution and the local economy. This project aims to develop a predictive model that accurately detects students early in their academic pursuit at risk of not graduating on time. Various predictive models are developed to do this, and the best model, the one with the highest performance, is selected. Using a dataset containing information from 24432 undergraduate students at the University of Puerto Rico at Mayaguez, the predictive performance of the models is evaluated in two scenarios: Group I includes both the first year of college and pre-college factors, and Group II only considers pre-college factors. Overall, for both scenarios, the boosting model, trained on the oversampled dataset, is the most successful at predicting who will not graduate on time.