Advancing Student Guidance Using Classification Data Mining Techniques

Academic advising is pivotal in higher education, influencing student retention, satisfaction, and overall academic success. Traditional advising often focuses on course enrollment, neglecting broader student needs. This study evaluates advising effectiveness by examining advisor-counsel relationships, identifying dropout touch-points, and implementing proactive re-enrollment strategies. To overcome shortcomings in virtual advising, a data-driven approach, employing machine learning algorithms (ML), is proposed. Decision trees, artificial neural networks, and random forests are assessed using a unique dataset to preemptively identify students requiring intensive advising. Results indicate the random forest model’s superior performance with a 97.30% accuracy, emphasizing its accuracy in predicting students’ counseling needs.