Published Paper Details:

Abstract--The prediction of student academic outcomes has emerged as a crucial area of focus in educational data mining, aiming to foster better learning achievements and enable timely educational interventions. By employing a range of machine learning (ML) techniques, researchers can analyze diverse in- dicators--such as academic records, attendance trends, and behavioral data--to estimate future academic performance.This study presents an in-depth evaluation of various supervised machine learning techniques, emphasizing their application and effectiveness in predictive analysis. It underscores the importance of selecting relevant features to boost prediction accuracy and examines how these models are being utilized within actual learning environments. In addition, the paper outlines widely adopted datasets, explores key implementation challenges such as data integrity and the interpretability of models, and proposes future directions to improve the effectiveness and scalability of predictive systems.