Addressing the complexities of student performance prediction, this research develops a novel Hybrid Learning Model (HLM), utilizing machine learning methods to offer a comprehensive educational analysis. Leveraging machine learning techniques to predict and enhance student performance in educational settings. The study is rooted in the recognition that education plays a pivotal role in shaping future generations and acknowledges the complexity involved in predicting student outcomes due to the multifaceted nature of learning processes and various influencing factors. Traditional models have predominantly focused on singular aspects of student performance, necessitating a more comprehensive approach. This research introduces a sophisticated system that integrates multiple performance indicators, including class participation, task performance, quizzes, and exams. Central to this model is the use of Linear Regression, a machine learning technique celebrated for its simplicity and efficiency, to establish relationships between dependent and independent variables, thereby predicting student outcomes effectively. The system is specifically tailored for educational contexts and does not consider non-academic factors like psychological conditions or family circumstances. Despite these limitations, the HLM promises significant advancements in predicting and enhancing student performance, with the potential to transform educational technology. This dissertation contributes a novel, multifaceted tool for educational improvement, subject to validation and refinement through real-world application and data analysis.

Keywords: Hybrid Educational Technology, Student Performance Prediction, Educational Data Analysis, Machine Learning in Education.

Views (58)