In today's quickly evolving job and educational scenario, striking a healthy work-life balance is becoming more and more crucial. The purpose of this project is to investigate the variables affecting students' work-life balance and to determine the best machine learning methods for doing so. At Hannam University in South Korea, 231 students participated in a survey that produced a dataset with 59 characteristics. The dataset was cleaned up, and its size was reduced, using data preparation techniques. The top 15 relevant characteristics were determined using the SelectKBest feature selection method. Using performance criteria including precision, recall, F1 score, and accuracy, three classification algorithms—Logistic Regression, Balanced Random Forest Classifier, and Neural Network—were trained and assessed. The findings showed that work-life balance was highly impacted by variables such place of residence, number of majors, time spent in college, and weekend class attendance. The Neural Network performed best among the methods, demonstrating how well it can forecast work-life balance based on the discovered features. In order to create interventions and policies that support a better balance between academic and personal duties, stakeholders in the education and employment sectors would benefit greatly from understanding the implications of these findings.