Predictors of graduate employment outcomes: a study on universities of applied sciences in China using a machine learning approach
Identifying predictors of graduate employment outcomes is crucial for higher education institutions focusing on industry-ready graduates, such as the universities of applied sciences (UAS) in China. Using data from 1,817 graduates across three Chinese UAS, we employed the LightGBM machine learning model to identify key determinants of employment outcomes through the lens of the Graduate Capital Model. The results revealed seven key predictors, in descending order of feature importance: student leadership experience, professional certificates obtained, career counseling received, parental education level, academic practice, frequency of interaction with instructors, and perceived improvement from innovation and entrepreneurship education. MANOVA further showed that graduates in full-time roles significantly outperformed their non-employed and part-time counterparts on these factors, with those in major-unrelated full-time work often leading. The findings underscore that employability is not determined by a single factor but by the dynamic interplay of human, social, cultural and identity capital. This study provides empirical evidence for Chinese UAS to strategically improve their graduate employment outcomes. The findings may also benefit other higher education institutions prioritizing employability.
Authors
- Hui Chen (ORCID: https://orcid.org/0000-0002-1492-9385)
- Jian Li (ORCID: https://orcid.org/0000-0002-6521-5956)
Institutions
- Beijing Normal University (CN)
Publication Details
- Journal
- Higher Education Research & Development
- Published
- 2026-11-13
- DOI
- https://doi.org/10.1080/07294360.2026.2760275
- Primary Topic
- Higher Education and Employability
- Type
- article
- Field-Weighted Citation Impact
- 0.00