Research on Precision Intervention of Learning Behaviors among Higher Vocational Students Based on Academic Profiles Using K-means Clustering
Year: 2026
Type: conference-paper
Abstract: Higher vocational education increasingly requires data-informed academic management to improve learning outcomes and reduce administrative friction. However, existing evaluation approaches often rely heavily on final performance indicators, which limits the timeliness and precision of intervention. Against this backdrop, this study proposes a data-driven framework for academic profiling and precision intervention targeting higher vocational students. Multidimensional data—including baseline attributes, online learning activities, and classroom behavioral performance—were integrated to construct learner representations. K-means clustering (with cluster selection validated by standard criteria) was employed to identify categorical academic profiles. Based on the resulting learner groups and their characteristic patterns, corresponding personalized intervention strategies were developed. Rather than stopping at student categorization, the framework links data-driven profiling with actionable instructional support. This approach enhances the relevance and timeliness of academic guidance, reduces management friction in graduation and academic review processes, and provides an operational reference for ML-enabled precision teaching in higher vocational education.
Author: Yongping Zhang
Language: English
Subfield: Computer Science Applications
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W7160162843