Vol.14, No.4, November 2025.                                                                                                                                                                          ISSN: 2217-8309

                                                                                                                                                                                                                        eISSN: 2217-8333

TEM Journal

TECHNOLOGY, EDUCATION, MANAGEMENT, INFORMATICS

Association for Information Communication Technology Education and Science

Interpreting the Machine Learning Approaches to Predict CGPA of the University Students

Ranjit Paul, Sadiq Hussain, Kamala Devi Kannan, Bijoy Kumar Mondal, Arun K. Baruah, Silvia Gaftandzhieva

© 2025 Silvia Gaftandzhieva, published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. (CC BY-NC-ND 4.0)

Citation Information: TEM Journal. Volume 14, Issue 4, Pages 3438-3447, ISSN 2217-8309, DOI: 10.18421/TEM144-50, November 2025.

Received: 30 November 2024.
Revised: 20 June 2025.
Accepted: 27 June 2025.
Published: 27 November 2025.

Abstract:

This study focuses on building a model to predict Cumulative Grade Point Average (CGPA) categories and identify students who might struggle academically during their time at university. The study uses student-related data to classify CGPA into specific grades (O, A+, A, B+, B, C+, C and F) and tested different machine learning methods like Naive Bayes, JRIP, J48, Random Forest, and CatBoost. Since some grades, like C and A+, had fewer students, a single-point crossover technique to balance the dataset were used. The models were assessed with ten-fold cross-validation, and CatBoost performed the best after balancing the data. To determine which factors played the largest role in the predictions, SHapley Additive exPlanations (SHAP) were used. It shows that the semester grade point average (SGPA) is one of the primary factors, especially highlighting those students in their 3rd semester who need extra support to achieve a better overall CGPA. These results show how early predictions can help universities support students and improve their academic success and retention.

Keywords – Machine Learning, classification, SHAP, cumulative grade point average, universities.

-----------------------------------------------------------------------------------------------------------

Full text PDF >  

-----------------------------------------------------------------------------------------------------------