Using machine learning techniques for early identification of at-risk students in a course at the intermediary levels of education

Abstract

This thesis focuses on the use of machine learning techniques to identify at-risk students at intermediary levels of education. The goal of this project is to develop a predictive model that can identify students who may be struggling in the course before they reach a critical point that leads to lower grades or withdrawal. Based on the analysis of related literature, this study selected students’ personal characteristics and academic performance as input attributions at the intermediary level of education. Prediction models were developed using Artificial Neural Network (ANN), Decision Tree (DT) and Linear regression. A sample of 785 students was utilized in the procedures of model training and testing. The results of each model were presented in a confusion matrix and were analyzed by calculating the rates of accuracy, precision, recall, and F-measure. The results suggested all three machine learning methods were effective for student at-risk prediction, but DT presented a better performance. By identifying at risk students early, teachers can provide additional support and resources to prevent students from falling behind and dropping out. Ultimately, this research could have significant implications for improving student retention rates in intermediary education and helping students achieve their academic goals.