PREDICTING ACADEMIC OUTCOMES IN COLLEGE STUDENTS WITH MACHINE LEARNING: THE ROLE OF STUDY AND SLEEP HOURS

Abstract

This study examines the application of machine learning models to predict academic performance in college students, with a focus on the impact of study hours and sleep hours as key factors influencing academic success.Tradtional method uses annual test base methods. This research aims to provide a more comprehensive approach by incorporating study habits and sleep patterns into the evaluation. Different machine learning algorithms, including Logistic Regression, Random Forest, Support Vector Machine (SVM), and Decision Tree, used to predict students' academic outcomes based on these factors. The findings demonstrate that study and sleep hours significantly affect academic performance, with different models offering varying levels of accuracy in predictions. The study highlights the importance of factors in academic prediction and suggests that machine learning can be a valuable tool for identifying at-risk students early. By providing insights into the factors influencing academic success, the research also offers practical implications for educators and administrators, enabling them to design more targeted interventions and support strategies. The results of this study contribute to the developing field of educational data science, offering a data-driven approach to improving student success and fostering a proactive learning environment.