In the field of education, every institution stores a significant amount of data in digital form on the academic performance of students. If this data is correctly analysed to discover any pattern related to student learning, it can assist the institution in achieving a favorable outcome in the future. Because of this, the use of data mining techniques makes it much simpler to unearth previously concealed information or detect patterns in student data. We use a variety of data mining methods, such as Naive Bayes, Random Forest, Decision Tree, Multilayer Perceptron, and Decision Table, to predict the academic performance of individual students. In the real world, a dataset may contain many features, yet the mining process may only place significance on some of those aspects. The correlation attribute evaluator, the information gain attribute evaluator, and the gain ratio attribute evaluator are some of the feature selection methods that are used in data mining to remove features that are not important for the mining process. Other feature selection methods include the gain ratio attribute evaluator and the gain ratio attribute evaluator. In conclusion, each classification algorithm that is designed using some feature selection methods enhances the overall predictive performance of the algorithms, which in turn improves the performance of the algorithms overall.

The purpose of this study is to conduct an empirical investigation and comparison of the effectiveness of various classifiers and ensembles of classifiers in predicting academic performance. The study will evaluate the performance and efficiency of ensemble techniques that employ several classifiers against the performance and efficiency of a single classifier. Reducing student attrition is a serious concern for educational institutions worldwide. Educators are looking for strategies to boost student retention and graduation rates. This is only achievable if at-risk students are appropriately recognized early on. However, most commonly used predictive models are inefficient and inaccurate due to intrinsic classifier limitations and the usage of minor factors. The study contributes to the body of knowledge by proposing the development of optimized ensemble learning model that can be used for improving academic performance prediction. Overall, the findings demonstrate that the approach of employing optimized ensemble learning (OEL) model approaches is extremely efficient and accurate in terms of predicting student performance and aiding in the identification of students who are in the fear of attrition.