Innovative machine learning approach and evaluation for predicting the Study and Work life balance among Students within the South Korean Higher Education system

Work-life balance is important to maintaining a sustainable balance between student study and work life. There are various positive factors associated with it like it increases the productivity of students and reduces the mental pressure on the student. In this research, we aim to find out the factors which affect the student's work-life balance and predict the work-life balance with the help of Machine learning algorithms. The dataset was collected by taking a survey of the students of Hannam University. After that SelectKBest algorithm finds the most crucial factors in predicting the student work-life balance. Three machine learning algorithms are used Balanced random forest classifier, logistic regression, and neural network. To evaluate the performance, metrics like accuracy, precision, recall, and f1 score were used. The result shows that the SLB_3 was the most important factor, and the neural network performed best among all, with an accuracy of 83%. On the other hand, logistic regression and balanced random forest classifier have got an accuracy of 80.85% and 72.34%, respectively.