Factors Influencing Academic Performance: An Empirical Study Using Predictive Analytics

Introduction: Student academic performance is commonly measured using indicators like credit scores, class rankings, or passing thresholds, each offering insight into a student’s comprehension and progress. These measures give a numeric evaluation of a student's understanding of the course content, enabling educators and institutions to monitor growth over time. Moreover, the capacity to forecast academic performance proves highly beneficial for both students and teachers, as it enables early interventions and course corrections. This predictive ability can lead to tailored learning strategies, ultimately enhancing educational outcomes and supporting overall student success. Method: To carry out a statistical analysis on the dataset (kaggel), the first step will involve cleaning and preprocessing the data to address any missing or non-numeric entries. Once the dataset is refined, hypothesis testing and ANOVA will be employed to pinpoint the key factors that influence student performance. Result: Initial findings suggest that study hours and attendance are significant predictors of exam scores, with higher values generally leading to better performance. Additionally, motivational factors, parental involvement, and access to academic resources showed varying degrees of influence, highlighting their potential role in shaping educational outcomes. Conclusion: Through descriptive statistics, correlation analysis, and regression models, the dataset offers insights that can be used by educators and policymakers to enhance teaching strategies and student support systems. By identifying key factors that affect student outcomes, the dataset provides a foundation for future research and practical interventions aimed at improving academic performance in educational settings