Developing a data-driven digital fashion skills framework for fashion education: evidence from PCA, neural networks, and learner clustering

The rapid digital transformation in the fashion industry has increased the demand for graduates with industry-relevant digital fashion skills. This study aims to develop a data-driven Digital Fashion Skills Framework for Fashion Education, using Principal Component Analysis (PCA), Artificial Neural Networks (ANN), and cluster analysis. When PCA was applied, it was evident that Digital Design Skills, CAD Skills, and VR Proficiency were the most influential, with the first two components accounting for 30.2% of the total variance. Furthermore, ANN also demonstrated its relevance in predicting digital skills readiness. Then, cluster analysis separated students into three learner profiles (low, medium, and high skill groups), indicating different levels of readiness for the digital fashion workflow. These findings provide evidence that digital fashion skills development is not homogeneous and requires different learning pathways. The proposed framework offers practical guidance for curriculum development, digital learning design, and workforce preparation in contemporary fashion education.