Chinese University Major Decision and Its Effect on Wages: Modeling Interaction Between Major Specificity and Education-Job Relevancy Using Machine Learning Approaches

Abstract

China’s expanding access to higher education and economic slowdown have resulted in growing social concerns about employment opportunities for fresh graduates. This study investigates the effect of choice of major on starting wages in the Chinese labor market. Analyzing a sample of 45,000 observations from Nanjing, China, we use machine learning techniques to uncover a significant interaction between major specificity (i.e. the specificity of the knowledge and skills each major entails) and education-job relevancy in determining wages. We first take the OLS and Heckman models as the baseline, before employing the KNN and Random Forest model fits. The interaction is then measured by the adjusted Friedman’s H-index and finally visualized by network plots and thermal graphs. This research achieves three goals. First, we find that family background, measured by hukou and/or parent education, has no significant impact on major selection and university tier. This finding not only address potential endogeneity concerns, but also has important implications for the study of class mobility in contemporary China. Specifically, it indicates that the impact of the rural-urban social stratification created by the hukou policy has diminished, and that China’s higher education system facilitates social equity. Second, this is the first study to use innovative methods to examine the pricing of 206 specific majors in the Chinese labor market. Third, this research provides guidance for individuals choosing their major, governments concerned with educational resource allocation and employment opportunities, and foreign scholars with limited knowledge of China’s graduate job market.