DEVELOPMENT OF A MACHINE LEARNING BASED MODEL FOR SIWES ELIGIBILY PREDICTION

ABSTRACT For students in Nigerian institutions, the Students Industrial Work Experience Scheme (SIWES) is important in closing the gap between academic understanding and real-world industry experience. However, Adeleke University’s current manual selection process for SIWES participation proves to be ineffective and subjective, making it difficult to ensure productivity and equal opportunity. This study focuses on creating a machine learning-based model to predict students’ eligibility for the SIWES program in order to address these problems. This study makes use of predictive analytics to facilitate the selection process using data gathering techniques, model creation, and testing procedures to ensure accuracy in the assessment of candidates. The predictive power of several machine learning algorithms, such as Support Vector Machines, Decision Trees, and Logistic Regression, was evaluated as revealed by the result of the study. The result shows that Logistic Regression was the most successful in predicting student eligibility, with high accuracy, precision, recall, and F1 score. In conclusion, the aim of the study was achieved in creating a machine learning model that improves the SIWES selection process’s effectiveness and equity. The approach improves the overall efficiency of student transfers into the workforce by automating eligibility predictions, which also simplifies operations.