Student performance prediction using machine learning | |
| Author | Maskey, Albin Raj |
| Call Number | AIT RSPR no.IM-24-05 |
| Subject(s) | Educational tests and measurements--Thailand--Data processing Academic achievement--Thailand--Data processing Deep learning (Machine learning) |
| Note | A research study submitted in partial fulfillment of the requirements for the degree of Master of Science in Information Management |
| Publisher | Asian Institute of Technology |
| Abstract | This study developed and evaluated machine learning models for predicting master’s students’ academic performance (CGPA at the 3rd semester) across departments and in the School of Engineering and Technology (SET) at the Asian Institute of Technology. Through analysis of data from 1,332 students (2018–2023), the best-performing models for each department and the overall SET dataset were identified.The Stacking Ensemble model achieved an R2 score of 0.2768 and an MSE of 0.1052 for the overall SET dataset. For individual departments, the best models and their respective performance metrics were: Support Vector Regression (SVR) for Civil and Infrastructure Engineering (R2 = 0.1567, MSE = 0.1134), Stacking Ensemble for Information and Communication Technology (R2 = 0.3674, MSE = 0.0907), Random Forest for Water Resources and Environmental Engineering (R2 = 0.3126, MSE = 0.1028), and SVR for Industrial Systems Engineering (R2 = 0.2429, MSE = 0.1184).Various machine learning models, including Decision Trees, Random Forest, Support Vector Regression, XGBoost, and Stacking Ensemble, were implemented in the research. Previous academic performance, English proficiency scores, and scholarship status emerged as significant predictors. A localized web prediction system was developed to demonstrate the findings, providing insights into the practical application of the models. The results highlight the importance of department-specific analyses while showing that previous GPA is not always the primary predictor of CGPA. |
| Year | 2024 |
| Type | Research Study Project Report (RSPR) |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Information Management (IM) |
| Chairperson(s) | Chantri Polprasert |
| Examination Committee(s) | Chutiporn Anutariya,;Rabgyal, Tenzin |
| Scholarship Donor(s) | AIT Scholarship, |
| Degree | Research studies project report (M. Sc.) - Asian Institute of Technology, 2024 |