Analysing The Impact of Socio and Demographic Factors on Student Performance

India’s educational landscape is diverse and expansive, making it challenging to assess and monitor student performance consistently across institutions. Traditional evaluation methods often overlook the broader range of factors that influence academic outcomes, such as family background, health conditions, access to learning resources, and parental involvement. This study addresses the need for a more comprehensive and data-driven approach to student performance prediction by incorporating both academic and socio-demographic attributes. A real-world dataset containing multiple student-related variables was used to develop and compare various machine learning models. Algorithms such as CatBoost and XGBoost were implemented to determine the most effective predictive approach. Additionally, an interactive desktop application was developed to demonstrate the model’s practical utility. The findings of this research can help institutions identify at-risk students early and implement targeted academic support strategies.