Peter E.

Key Skills

Freelancer Overview

CHAPTER ONE INTRODUCTION 1.1 Background of the Study Academic success prediction as an application of educational data mining (EDM) plays an important role in educational institution, as it creates an opportunity for identifying students that may graduate with poor results or may not graduate at all, so that early intervention may be deployed to improve their academic outcomes (Adekitan & Salau, 2019). The accurate prediction of student academic success has significant implications for quality of education, better educational services, assist educators and learning experts, and designing of learning interventions (Romero & Ventura, 2007; Giannakas et al., 2021). However, traditional approaches to academic success prediction often rely on simplistic conventional statistical models that fail to capture the complexity of student performance. In recent years, the application of advanced machine learning techniques in EDM, such as decision tree (DT) models and artificial neural network (ANN) models, has shown promise in improving the accuracy and effectiveness of academic success prediction (Papadogiannis et al., 2020). These models have the potential to uncover intricate patterns and nonlinear relationships among various factors that influence student performance, leading to more precise predictions. Despite the growing interest in utilizing optimized DT and ANN models for academic success prediction, there remains a need for further research in this area. Existing studies have p

Education