Analysis of Factors Affecting Students’ Academic Performance and Score Prediction Using Machine Learning

Abstract

In recent years, the increasing availability of educational data has created new opportunities for applying Machine Learning (ML) techniques to analyze and predict students’ academic performance. Understanding the factors that influence student achievement is crucial for educators, institutions, and policymakers to improve learning outcomes and design effective academic interventions. This research focuses on analyzing how students’ exam performance is affected by various demographic and educational factors using machine learning approaches. The dataset used in this study was collected from a publicly available educational dataset consisting of 1,000 student records with demographic attributes such as gender, race or ethnicity, parental level of education, lunch type, and test preparation course completion, along with scores in mathematics, reading, and writing. Comprehensive data preprocessing techniques, including categorical encoding, feature scaling, and train–test splitting, were applied to prepare the dataset for modeling. Exploratory Data Analysis (EDA) was conducted to identify patterns, correlations, and trends among the variables. Several machine learning models were then implemented and evaluated to predict students’ academic performance, including traditional regression-based models and ensemble learning techniques. Model performance was assessed using standard evaluation metrics such as accuracy, mean squared error, and coefficient of determination (R²). The experimental results demonstrate that machine learning models can effectively capture the relationships between demographic factors and academic outcomes. The proposed approach achieved high predictive performance, highlighting the significant influence of test preparation courses, parental education level, and lunch type on students’ exam scores. The findings suggest that ML-based predictive systems can serve as valuable decision-support tools in educational settings. This study emphasizes the potential of machine learning to enhance educational analytics by providing data-driven insights into student performance, supporting early intervention strategies, and contributing to the development of personalized and inclusive learning environments.