95% of researchers rate our articles as excellent or good
Learn more about the work of our research integrity team to safeguard the quality of each article we publish.
Find out more
ORIGINAL RESEARCH article
Front. Educ.
Sec. Higher Education
Volume 10 - 2025 | doi: 10.3389/feduc.2025.1551596
This article is part of the Research Topic Applying Lean Six Sigma and Industry 4.0 Concepts to Enhance Higher Education View all 4 articles
Role of Artificial Intelligence in Enhancing Competency Assessment and Transforming
Provisionally accepted- Yibin Vocational and Technical College, Yibin, China
The study investigates the competency assessment outcome of AI-driven training, student engagement, and demographic factors. Previous studies have examined these factors individually, but this research integrates them to assess their combined impact on competency scores. Variables such as competency scores, AI-driven training, student engagement, gender, and vocational training levels were systematically collected following FAIR principles.Python libraries were used for cleaning and preprocessing the dataset; missing values were filled and outliers were handled using the Tukey method. The use of EDA further disclosed strong positive correlations with student engagement and competency scores resulting from AI-driven training. Nonetheless, since it is an observational study, these associations must not be taken to be causal. Inferential statistics -like t-tests and ANOVA -were established by gender and vocational training level. Machine learning algorithms were used to predict competency scores, and Random Forests showed the highest predictive power compared to linear regression (R² = 0.68 vs. 0.41). This suggests the necessity of modeling nonlinear relationships in competency prediction. Inferential statistics (ANOVA, t-tests) revealed gender and vocational training-level effects. Random Forests outperformed linear regression (R² = 0.68 vs. 0.41), uncovering non-linear relationships. KMeans clustering revealed three student groups necessitating individualized interventions: Cluster 1 (high AI engagement/low competency) requires skill-building support; Cluster 2 (balanced engagement/competency) is served by ongoing adaptive training; and Cluster 3 (low engagement/high competency) requires engagement-fostering strategies. These results highlight the importance of AI-supported training and student interaction to improve competency attainment. These findings have practical implications for vocational education and training institutions by promoting personalized learning approaches that are responsive to the various needs of students. Ethical considerations of AI-based evaluation, including bias and fairness, are worthy of exploration.
Keywords: AI-driven training, student engagement, competency assessment, Predictive Modeling, Clustering analysis, educational outcomes
Received: 26 Dec 2024; Accepted: 31 Mar 2025.
Copyright: © 2025 YAN, TIAN, SUN and SONG. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
HAOHENG TIAN, Yibin Vocational and Technical College, Yibin, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.