Optimizing Student Performance Prediction Using Binary Waterwheel Plant Algorithm for Feature Selection and Machine Learning

Abstract

This paper deals with a pivotal part of educational data analytics, aiming to increase the accuracy and interpretability of student performance prediction models. The cornerstone of our method is the innovative application of binary waterwheel plant algorithm bWWPA in the feature selection. As we can see, an essential part of any model is the predicted values, which correctly define all the characteristics of this model. Practically, we begin with solid data pre-processing, which incorporates data cleaning and missing values, duplicate removal, and data transformation in order to get model input as optimally as possible. Preceding the application of bWWPA, we employ an ensemble of regression machine learning models. Set up a baseline for predictive capability, getting initial outcomes with an average Mean Squared Error (MSE) of 0.064. The following feature selection phase proceeds, showing the algorithm. Ability to recognize important elements and, as a result, improve model effectiveness and explain power. The comparative analyses after feature selection point to refined gains in the model, and the performance is reporting a lower MSE of 0.032 with the refined models. These findings, methodologically, add to student performance prediction. Accordingly, it emphasizes the decisive status of feature selection in improving models. The paper's significance extends to teachers, institutions, and researchers, giving insights into more precise and relevant student success-supporting interventions.