Student Performance Prediction using Machine Learning

This paper focuses on improving student performance prediction, based on their performance characteristics. Due to various distractions, students may divert from their actual track. This might even lead to a course drop out. Predicting students' performance will help in self-analysis. The dataset used consists of data about students' performance from the academic and other classroom activities during the course time. Educational data mining algorithms are used to predict student performance which is a module in automated intelligent education systems. EDM is a methodology which is used to mine valuable information and patterns or forms from a massive educational database. Subsequently, the student's performance is predicted from the obtained useful information and patterns. The aim of our study is to discover the performance of students using some classification techniques and discovering the best one which yields optimal results. The result of this study is extremely significant and hence provides a greater insight for evaluating the student performance and underlines the significance of data mining in education. It also shows that how students attributes affect the student performance.