Student academic performance prediction has become an important area in educational analytics due to the increasing need for early identification of student success and academic improvement. Traditional methods of evaluating student performance are time-consuming and often fail to provide accurate predictive insights. This paper proposes a machine learning-based student academic performance prediction system that analyzes previous semester CGPA, attendance percentage, internal assessment marks, and study hours to predict future academic outcomes. The system utilizes data analysis and predictive algorithms to estimate student performance and determine success probability. The proposed system helps educational institutions monitor student progress, identify academically weak students, and improve decision-making processes. The system provides accurate, scalable, and efficient academic analysis for educational environments.

Keywords — Machine Learning, Student Performance Prediction, Educational Analytics, CGPA Prediction, Artificial Intelligence, Academic Analysis