In this paper, we focus on using learning analytics and data mining techniques to predict student performance. This study investigates approaches for predicting student learning outcomes, assesses the accuracy of several models, identifies the most important elements influencing student success, and highlights limitations in the field while providing suggestions for further research. The significance of this review arises from its thorough approach to monitoring student performance. In addition to traditional indicators such as GPA and grades, there is an increasing emphasis on learning outcomes, which provide a more comprehensive view of academic accomplishment. While there has been significant progress in this area, the review emphasizes that there is still much to learn about the reliability of learning outcomes as predictors. This report provides a detailed analysis of a dataset designed to represent student accomplishment in higher education. We have looked at student data, focusing on important variables including age, gender, year of study, GPA, major, study hours, attendance rate, and participation in extracurricular online activities. The primary objective was to discover the relationships between these factors and student GPA.