Mathematical Applications And Modelling In Higher Education

Abstract

In today's educational landscape, student achievement rates are important indicators in institutional efficiency. Forecasting students' academic performance concluded data analysis is growth valuable for teachers and decision-makers. The purpose of this study is to grow and implement an advanced mathematical application & modeling technique to predict students' educational grades accurately using their online behaviors. To train our proposed model, we gathered a dataset that included 112 college students' final grades, as well as records of their online educational interaction and attendance at online lectures. Data normalization is used to pre-process the acquired information. We present an innovative Effective Remora optimization-driven Random Forest (ER-RF) mathematical-based technique for predicting students' educational grades. The established procedure is implemented using Python software. During the result analysis phase, we assess the efficacy of our model across various parameters. Additionally, we conduct comparative analyses with existing methodologies. The obtained findings demonstrate the efficacy and superiority of the suggested framework.