A Novel Predictive Modeling for Student Attrition by Utilizing Machine Learning and Sustainable Big Data Analytics

• DOI: 10.20944/preprints202408.1298.v1
• Publication Date: 2024-08-22T00:30:12Z
• Authors: Chiang Liang Kok; Chee Kit Ho; Leixin Chen; Yit Yan Koh; Bowen Tian
• Keywords: Predictive Analytics; Attrition; Data Analysis; Learning Analytics

Student attrition poses significant societal and economic challenges, leading to unemployment, lower earnings, other adverse outcomes for individuals communities. To address this, predictive systems leveraging machine learning Big Data aim identify at-risk students early intervene effectively. This project focuses on extracting key parameters from past dropout data construct a model alert authorities promptly. Two preliminary trials refine models, establish evaluation standards, optimize hyperparameters. These facilitate systematic exploration of performance quality assessment. Achieving 100% accuracy in prediction, the study identifies academic as primary influencer, with early-year subjects like Mechanics Materials, Design Machine Elements, Instrumentation Control having impact. The longitudinal effect these underscores importance intervention. Proposed solutions include engagement support or restructuring courses better accommodate novice learners, aiming reduce rates.