Unlocking Enigmatic Pathways: Empowering Student Dropout Analysis with Machine Learning and Energizing Holistic Investigation

Student dropout is a significant concern in educational institutions as it hampers academic achievement and limits future opportunities for students. Predicting student dropout using machine learning techniques has gained attention as a valuable tool for early identification and intervention. In this paper, for student dropout from school from Gujarat demographic location has been proposed to bridge the gap for the lack of unavailability of dataset for the said research problem. This paper presents an abstract overview of the process involved in developing a student dropout prediction model using machine learning. The proposed machine learning architecture incorporates the Multiple linear Regression and Polynomial Regression to address this issue and predict the future dropout analysis based on age group, caste, school, demographic location, and gender. The proposed implementation succeded to achieve the R
²
value of 0.9976 and MAE to 0.2311 while Regression Score to 0.9976 on the newly created dataset EduDropX.