Predicting student satisfaction in career choices using machine learning: a case study

Student satisfaction plays a crucial role in successful educational and career decision-making. This study investigates how artificial intelligence, specifically Support Vector Machine (SVM) models, can be used to predict student satisfaction with university choices by considering socio-economic, environmental, and cultural factors. An innovative hybrid approach is proposed, combining psychometric rigor with machine learning (ML) techniques to proactively assess satisfaction related to academic orientation. Data were collected from 125 students enrolled at a technology-oriented university and analyzed through three main stages. First, the reliability of the satisfaction measurement instrument was assessed. Second, key factors influencing student satisfaction were identified using statistical analysis. Third, an SVM-based predictive model was developed, with 70% of the data used for training and 30% for testing. The results reveal significant positive associations between overall student satisfaction and variables such as student background, social support, prior knowledge, and preference for group work. The SVM model achieved a prediction accuracy of 89%, demonstrating strong predictive performance. These findings highlight the potential of artificial intelligence as a valuable tool for educational guidance and suggest that SVM-based models can effectively anticipate student satisfaction, as well as other factors essential to academic and career success.