Predicting Student Dropout Using Machine Learning Algorithms

Abstract

This article comprehensively examines the use of machine learning algorithms to predict and reduce student dropout rates. These methods, developed to monitor and support student achievement in education, also aimedto enhance success rates in education and ensure more effective student engagement in the learning process. Bigdata analysis and machine learning models provide important contributions to the development of strategic solutions to the problem of school dropout by predicting student movements and trends.This study uses a dataset consisting of 4424 student data and has 37 features. The dataset is divided into three classes: "Dropout", "Enrolled" and "Graduate" according to the students' school dropout status. Decision Tree (DT), Random Forest (RF) and Artificial Neural Network (ANN) competitions, which are frequently used in such training studies in the literature, are aimed at this dataset. According to the obtained operations, DT showed moderate performance with an accuracy rate of 70.1%. The RF algorithm showed higher success with an accuracy rate of 75.5%. The highest success was achieved by the ANNalgorithm with an accuracy rate of 77.3%. ANN's flexible structure has produced superior results compared to other algorithms for this dataset, its ability provide successful classification in complex datasets.The article ultimately demonstrates how machine learning-based prediction models can have a significant impact on student achievement and offer a powerful tool for reducing school dropouts.