Education is a crucial factor in shaping the future growth of students. Educational institutions are actively trying to provide high-quality learning experiences. Faculty members play a vital role in influencing both the performance and overall development of students. The education sector generates a vast amount of data, which can be leveraged to predict and address undesirable behaviors among students. Effective use of data analytics is essential for predicting undesirable behavior among students. The prediction results help to identify students who are at risk or likely to drop out, allowing for timely interventions to improve their behavior. These insights also assist faculty members in enhancing the teaching-learning process, ultimately contributing to better student behavior and academic outcomes. This study involved data collection from undergraduate students enrolled in BCom, BBA, BBA(CA), and BSc(CS) programs. To predict instances of undesirable student behavior, several machine learning classification algorithms were implemented. A comparative analysis of these algorithms was conducted, and the results were illustrated through graphical representations. The present study also includes a discussion of the interpretations of its research findings.