PREDICTING VOCATIONAL EDUCATION SELECTION DECISIONS USING MACHINE LEARNING: EVIDENCE FROM SECONDARY SCHOOL STUDENTS IN THAILAND
Veredas do Direito · 06.05.2026 · 23 (7) · e236174
DOI: 10.18623/rvd.v23.6174 ↗Kurz gefasst
Fachartikel in der Zeitschrift Veredas do Direito, online erschienen am 06.05.2026. Verfasst von Ekanong Kongprasom und 2 weiteren Autor:innen.
Abstract (Originalsprache)
This study aimed to examine the factors associated with students’ decisions to pursue vocational education and to develop machine learning models for predicting vocational education selection among secondary school students in Thailand. A quantitative research design was employed using primary data collected through structured questionnaires from 437 students across public and private educational institutions nationwide. The sample was selected through multistage stratified random sampling to ensure regional representativeness. Independent variables included demographic characteristics and perceptual factors related to vocational education, career expectations, family background, and educational support. Four machine learning classification algorithms were applied for predictive modeling: Logistic Regression, Decision Tree, Random Forest, and Naïve Bayes. Data were divided into training and testing sets at a ratio of 75:25, and model performance was evaluated using Accuracy, Precision, Recall, and F1-Score. The findings revealed that social recognition, retention-related perceptions, job security expectations, family environment, and guidance support were among the factors most strongly associated with students’ vocational education decisions. Correlation analysis indicated that all perceptual variables were positively related to vocational education selection, with social recognition demonstrating the strongest association. Among the predictive models, Random Forest achieved the highest performance, with an Accuracy of 0.908, Precision of 0.919, Recall of 0.978, and F1-Score of 0.948, outperforming Logistic Regression, Decision Tree, and Naïve Bayes. These results suggest that vocational education decision-making may involve nonlinear and multidimensional relationships among influencing factors. This study contributes to the literature by integrating educational decision-making theory with machine learning-based predictive analytics in vocational education. The findings provide practical implications for policymakers, vocational institutions, and school counselors in designing data-driven guidance strategies and educational planning systems.
Zitieren
APA
Kongprasom, E., Khamrod, S., & Tanyapornhirun, N. (2026). PREDICTING VOCATIONAL EDUCATION SELECTION DECISIONS USING MACHINE LEARNING: EVIDENCE FROM SECONDARY SCHOOL STUDENTS IN THAILAND. Veredas do Direito, 23(7), e236174. https://doi.org/10.18623/rvd.v23.6174
Vancouver
Kongprasom E, Khamrod S, Tanyapornhirun N. PREDICTING VOCATIONAL EDUCATION SELECTION DECISIONS USING MACHINE LEARNING: EVIDENCE FROM SECONDARY SCHOOL STUDENTS IN THAILAND. Veredas do Direito. 2026;23(7):e236174. doi:10.18623/rvd.v23.6174
BibTeX
@article{Kongprasom2026,
author = {Kongprasom, Ekanong and Khamrod, Sittikorn and Tanyapornhirun, Nitdanee},
title = {PREDICTING VOCATIONAL EDUCATION SELECTION DECISIONS USING MACHINE LEARNING: EVIDENCE FROM SECONDARY SCHOOL STUDENTS IN THAILAND},
journal = {Veredas do Direito},
year = {2026},
volume = {23},
number = {7},
pages = {e236174},
doi = {10.18623/rvd.v23.6174}
}
EUVIMED