DROPOUT PREDICTION FOR VOCATIONAL STUDENTS : A CASE STUDY KHON KAEN VOCATIONAL COLLEGE. USING MACHINE LEARNING METHOD
Article Sidebar
Main Article Content
Abstract
This research aimed to develop and compare the performance of models for predicting student dropout in vocational education at Khon Kaen Vocational College using machine learning techniques. The dataset comprised 2,802 records of students at the Certificate of Vocational Education, Higher Certificate of Vocational Education, and Bachelor of Technology levels from the academic years 2021–2023, consisting of 20 variables collected from Khon Kaen Vocational College. Five machine learning techniques were employed to construct the models: Decision Tree, Naive Bayes, Random Forest, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM). Model performance was evaluated using cross-validation. The experimental results revealed that the Random Forest technique achieved the highest prediction accuracy at 97.83%, followed by Decision Tree at 97.58%, SVM at 96.53%, and Naive Bayes at 95.79%, while KNN yielded the lowest accuracy at 84.40%. The comparison indicated that the model developed using the Random Forest technique outperformed the other techniques employed in this study.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
สงวนสิทธิ์ โดย สถาบันการอาชีวศึกษาภาคตะวันออกเฉียงเหนือ 1
306 หมู่ 5 ถนนมิตรภาพ หนองคาย-อุดรธานี ตำบลโพธิ์ชัย อำเภอเมืองหนองคาย จังหวัดหนองคาย 43000
โทร 0-4241-1445,0-4241-1447
ISSN : 3027-6861 (print) ISSN : 3027-687X (online)
References
R. Kladchuen and C. Saenraj, “A comparison of algorithm efficiency and appropriate feature selection for predicting academic achievement of vocational students”, Thanyaburi University Research Journal, 17(1), , 2018, p1–10. (in Thai)
C. Boonprason and C. Saenraj, “Analysis of predicting undergraduate student dropout using data mining techniques”, King Mongkut’s University of Technology North Bangkok Academic Journal of Industrial Education, 9(1), 2018, p142–151. (in Thai)
Office of Vocational Education Standards and Qualifications, Criteria and Guidelines for Managing Vocational Education at the Certificate and Higher Certificate Levels, Topic 1 : Vocational Education Management, 1st ed. Bangkok : Office of Vocational Education Standards and Qualifications, 2019. (in Thai)
A. Juthaphad, “Development of an information system for predicting the number of new students using decision tree classification rules”, Proceedings of the 12th Naresuan Research National Conference: Research and Innovation for National Development, Phitsanulok: Naresuan University, 2016, p31–45. (in Thai)
T. Iadcharoen, “A study of the performance of predicting interest in products from business accounts on the LINE application using machine learning techniques”, Dept. of Engineering Management, College of Innovation in Technology and Engineering, Dhurakij Pundit University, Bangkok, 2022. (in Thai)
K. Wongsawasdi, “Analysis of diabetic patient data using machine learning techniques”, Khon Kaen University Research and Development Journal, 11(1), 2019, p23–34. (in Thai)
N. Chanamarn and P. Sithidej, “Analysis of learning factors through feature selection and forecasting”, Sakon Nakhon Rajabhat University Journal, 6(12), 2014, p31–45. (in Thai)
J. Charoenying, “Forecasting academic achievement using data mining techniques with RapidMiner”, Master’s Thesis, Srinakharinwirot University, 2020. [Online]. Available:https://irthesis.swu.ac.th/dspace/bitstream/123456789/1231/1/gs591130025.pdf. (in Thai)
T. Srisuwan, “Development of an online payment fraud detection system using machine learning techniques”, Thammasat University Research and Development Journal, 12(3), 2022, p67–79. (in Thai)
P. Thawananon et al., “Application of ensemble learning models to forecast stock price trends in the Stock Exchange of Thailand”, Journal of Information Science and Technology, 7(1), 2017, p12–21. (in Thai)
P. Thongsri, “Application of machine learning techniques to forecast electricity demand”, King Mongkut’s University of Technology Thonburi Research and Development Journal, 13(4), 2018, p89–101. (in Thai)
S. Toompetchrat et al., “Forecasting TOEIC examination results of English major students at Rangsit University using data mining techniques”, Proceedings of the Rangsit University National Conference 2017, Pathum Thani : Rangsit University, 2017. p98–105. (in Thai)
S. Saengsuwan, “Development of an online product recommendation system using machine learning techniques”, Chiang Mai Rajabhat University Research and Development Journal, 10(2), 2021, p45–58. (in Thai)
P. Pianphailun et al., “Comparison of models for predicting O-NET scores using data mining techniques”, Proceedings of the 2nd National Conference of Kanchanaburi Rajabhat University, Kanchanaburi : Kanchanaburi Rajabhat University, 2017, p188–194. (in Thai)
N. Rojanaburanon, Guide to Data Analysis with RapidMiner Studio 9. [Online]. https://www.gotoknow .org/posts/660127. (Accessed 10 Mar 2025). (in Thai)
