Forecasting the Academic Performance by Leveraging Educational Data Mining

Abstract

The study aims to recognize how efficiently Educational Data Mining (EDM) integrates into Artificial Intelligence (AI) to develop skills for predicting students' performance. The study used a survey questionnaire and collected data from 300 undergraduate students of Al Neelain University. The first step's initial population placements were created using Particle Swarm Optimization (PSO). Then, using adaptive feature space search, Educational Grey Wolf Optimization (EGWO) was employed to choose the optimal attribute combination. The second stage uses the SVM classifier to forecast classification accuracy. Different classifiers were utilized to evaluate the performance of students. According to the results, it was revealed that AI could forecast the final grades of students with an accuracy rate of 97% on the test dataset. Furthermore, the present study showed that successful students could be selected by the Decision Tree model with an efficiency rate of 87.50% and could be categorized as having equal information ratio gain after the semester. While the random forest provided an accuracy of 28%. These findings indicate the higher accuracy rate in the results when these models were implemented on the data set which provides significantly accurate results as compared to a linear regression model with accuracy (12%). The study concluded that the methodology used in this study can prove to be helpful for students and teachers in upgrading academic performance, reducing chances of failure, and taking appropriate steps at the right time to raise the standards of education. The study also motivates academics to assess and discover EDM at several other universities.