แบบจำลองการขุดข้อมูลทางการศึกษาโดยใช้อัลกอริทึมต้นไม้ตัดสินใจเพื่อพยากรณ์ผลสัมฤทธิ์ทางการเรียนของนักเรียน

Yaowapha Sriburin; Chaimongkhon  Pinasa; Anuphum  Kumyoung; Praewnapa  Riangrila

Authors

Yaowapha Sriburin Educational Innovation Research, Faculty of Education, Loei Rajabhat University
Chaimongkhon Pinasa Faculty of Education, Loei Rajabhat University
Anuphum Kumyoung Faculty of Education, Loei Rajabhat University
Praewnapa Riangrila Faculty of Education, Loei Rajabhat University

Keywords:

Educational Data Mining Model, Decision Tree Algorithm, Academic Performance Prediction

Abstract

This article aims to (1) present conceptual frameworks of educational data mining, decision tree algorithms, and their application within Altair AI Studio; and (2) demonstrate the development of a predictive model for student academic performance utilizing decision tree algorithms in Altair AI Studio. Data were purposively collected from existing information systems of Grade 6 students across three schools. To address the issue of incomplete records, 1,000 synthetic data points were generated using ChatGPT to augment the dataset. Model development consisted of five steps: (1) data collection, (2) data preparation, (3) model building with an 80:20 training-testing split, (4) model evaluation via 10-fold cross-validation, and (5) deployment as an application on the One Compiler platform for user to input student information and predict academic performance in advance. Evaluation results indicated the model demonstrated moderate predictive accuracy, achieving an accuracy of 64.70%, a root mean square error (RMSE) of 0.478, and a standard deviation (S.D.) of ±0.010. This model provides valuable support for educational planning, counseling, and enhanced educational quality in the digital era.

Downloads

Download data is not yet available.

References

ชัยมงคล ปินะสา, สำราญ มีแจ้ง, และน้ำทิพย์ องอาจวาณิชย์. (2567). การประยุกต์ใช้โครงข่ายประสาทเทียมในการคัดเลือกข้อสอบข้อถัดไป สำหรับการทดสอบแบบปรับเหมาะด้วยคอมพิวเตอร์แบบพหุมิติ. วารสารการวัดผลการศึกษา มหาวิทยาลัยมหาสารคาม. 30(1); 1-15.

Abdullahi, A. M., Htet, S. A., Naing, N. N. N., Hossain, M. S., Ismail, S., & Zaaba, M. A. M. (2024). A prediction of customer segmentation using random forest in RapidMiner. 2023 IEEE 21st Student Conference on Research and Development (SCOReD), 33-38. https://doi.org/10.1109/SCOReD60679.2023.10563451

Adekitan, A. I., & Salau, O. (2019). The impact of engineering students' performance in the first three years on their graduation result using educational data mining. Heliyon, 5(2), 1-21. https://doi.org/10.1016/j.heliyon.2019.e01250

Askinadze, A., & Conrad, S. (2018). Respecting data privacy in educational data mining: an approach to the transparent handling of student data and dealing with the resulting missing value problem. 2018 IEEE 27th International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE), 160-164. https://doi.org/10.1109/WETICE.2018.00037

Batool, S., Rashid, J., Nisar, M. W., Kim, J., Kwon, H.-Y., & Hussain, A. (2023). Educational data mining to predict students' academic performance: A survey study. Education and Information Technologies, 28(1), 905-971. https://doi.org/10.1007/s10639-022-11152-y

Bjaoui, M., Sakly, H., Said, M., Kraiem, N., & Bouhlel, M. S. (2020). Depth insight for data scientist with RapidMiner «an innovative tool for AI and big data towards medical applications». Proceedings of the 2nd International Conference on Digital Tools & Uses Congress, 28, 905-971. https://doi.org/10.1145/3423603.3424059

Chen, S., & Lin, X. (2023). Application of decision tree algorithm in educational data mining. Curriculum and Teaching Methodology, 6(8), 120-127. https://doi.org/10.23977/curtm.2023.060818

Conijn, R., Snijders, C., Kleingeld, A., & Matzat, U. (2016). Predicting student performance from LMS data: A comparison of 17 blended courses using Moodle LMS. IEEE Transactions on Learning Technologies, 10(1), 17-29. https://doi.org/10.1109/TLT.2016.2616312

Corina Simionescu, M. D., Bogdănel Constantin Grădinaru, Marius Silviu Măciucă. (2024). Educational data mining in European union – achievements and challenges: A systematic literature review. International Journal of Advanced Computer Science and Applications, 15(3). https://doi.org/10.14569/IJACSA.2024.0150386

Dol, S. M., & Jawandhiya, P. M. (2024). Systematic review and analysis of EDM for predicting the academic performance of students. Journal of The Institution of Engineers (India): Series B, 105(4), 1021-1071. https://doi.org/10.1007/s40031-024-00998-0

Dutt, A., Ismail, M. A., & Herawan, T. (2017). A systematic review on educational data mining. IEEE Access, 5, 15991-16005. https://doi.org/10.1109/ACCESS.2017.2654247

Hasan, H. R., Rabby, A. S. A., Islam, M. T., & Hossain, S. A. (2019). Machine learning algorithm for student's performance prediction. 2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT), 27, 1-7. https://doi.org/10.1109/ICCCNT45670.2019.8944629

Hu, Y.-H. (2022). Effects and acceptance of precision education in an AI-supported smart learning environment. Education and Information Technologies, 27(2), 2013-2037. https://doi.org/10.1007/s10639-021-10664-3

Joy, T. T., Rana, S., Gupta, S., & Venkatesh, S. (2019). A flexible transfer learning framework for Bayesian optimization with convergence guarantee. Expert Systems with Applications, 115, 656-672. https://doi.org/10.1016/j.eswa.2018.08.023

Klein, M., Gerlitz, L., & Spychalska-Wojtkiewicz, M. (2021). Cultural and creative industries as boost for innovation and sustainable development of companies in cross innovation process. Procedia Computer Science, 192, 4218-4226.