Predicting Academic Performance of Students Using Modified Decision Tree based Genetic Algorithm
Harikumar Nagarajan, Zaid Alsalami, Shweta Dhareshwar, Kalidas Sandhya, Punitha Palanisamy
Abstract
Students’ academic performance prediction has been a significant area of research in educational data mining, in which machine learning (ML) techniques are used to examine data from educational institutions. The research project uses supervised machine learning techniques to forecast students’ grades and marks. The purpose of this study is to investigate the standard of learning as it relates to the objectives of sustainability. The system has produced a large amount of data, which must be carefully examined in order to extract the most important information for planned and future development. One well-known and useful use in the EDM is the forecasting of students’ grades and marks based on their prior educational records. It turns into a fantastic source of information that can be used in a variety of ways to raise the national education level. The regression framework and Decision Tree (DT)-classifier are trained using the labeled academic history data of the student (30 optimal characteristics). In order to maximize the decision tree algorithm’s output, the research proposes a modified version of the method that uses a Genetic Algorithm (GA) to assess students’ academic achievement. The outcomes demonstrate the effectiveness and relevance of the improved decision tree method for more straightforward and accurate student performance prediction.