Analysis of Factors Influencing Student Performance in Higher Education Using Machine Learning Techniques

Thesis Abstract

Abstract
The academic performance of students in higher education is influenced by various factors that can significantly impact their success and outcomes. This research study aims to analyze the factors that influence student performance in higher education using machine learning techniques. The application of machine learning in educational research has gained significant attention due to its ability to analyze large datasets and identify patterns that may not be easily recognizable through traditional statistical methods. By harnessing the power of machine learning algorithms, this study seeks to provide insights into the complex interactions between student performance and a range of factors, including demographic characteristics, academic background, study habits, and other relevant variables. The primary objectives of this research are to identify the key factors that influence student performance in higher education, develop predictive models using machine learning algorithms to forecast student outcomes, and provide recommendations for educational institutions to improve student success rates. Through a comprehensive literature review, this study examines existing research on student performance in higher education, machine learning applications in educational data analysis, and relevant theories and frameworks related to student success. The research methodology includes data collection from a sample of students in higher education institutions, data preprocessing to clean and prepare the dataset for analysis, feature selection to identify the most influential variables, model training using machine learning algorithms such as decision trees, random forests, and neural networks, and model evaluation to assess the predictive performance of the developed models. The findings of this study reveal the significant factors that impact student performance, including academic background, study habits, socio-economic status, and other variables. The predictive models generated through machine learning techniques demonstrate promising results in forecasting student outcomes and identifying at-risk students who may require additional support and interventions. The implications of these findings for educational practice and policy are discussed, highlighting the potential benefits of leveraging machine learning to enhance student success in higher education. In conclusion, this research contributes to the growing body of knowledge on factors influencing student performance in higher education and demonstrates the utility of machine learning techniques in analyzing educational data. By leveraging the insights gained from this study, educational institutions can implement targeted interventions and support mechanisms to improve student outcomes and promote academic success.