Machine Learning-Based Prediction of Students' Self-Actualization Using Maslow's Hierarchy of Needs

Abstract

Self-actualization is at the top of Maslow's Hierarchy of Needs, signifying a person's realization of potential, creativity and personal growth. Self-actualization is traditionally measured with subjective psychological instruments that are hard for scaling in educational settings. The present study suggests a machine learning approach to develop a predictive model for evaluating students’ self-actualization level based on psychological, socio-economic and academic variables based on Maslow's hierarchy theory. An institution of Mehran University of Engineering and Technology (MUET), Pakistan was chosen and a structured questionnaire was designed on the basis of Maslow's hierarchy of needs to collect data from 506 university students. Various supervised machine learning algorithms such as Gradient Boosting Classifier, Random Forest, Support Vector Machine (RBF), Logistic Regression and Decision Tree were trained and tested with accuracy, precision, recall and F1 score. The Gradient Boosting Classifier gave the highest accuracy of 95.1% and F1 score of 88.9% during the experiment, beating all other models. Results prove that ML techniques can be used to model the psychological need fulfillment. This research offers a data-driven, scalable solution that may be used for predicting student self-actualization, thereby providing early intervention opportunities to promote academic and psychological wellness in higher education.