Predictive Power of Auditors’ industry-specific knowledge on Macroeconomic Growth: An Empirical Estimation Utilizing Machine Learning

Auditors’industry-specific knowledge is a critical production factor whose broader macroeconomic implications remain underexplored. Drawing on the co-production theory (or synergistic production theory), this study empirically investigates the link between Auditors’ industry-specific knowledge and economic growth using a comprehensive panel dataset of Chinese listed companies from 2009 to 2023. We employ a Generalized Random Forest (GRF) model — a machine learning methodology—to accurately predict and identify the non-linear relationship between these two variables. The findings reveal that auditors’industry-specific knowledge significantly promotes economic growth through two distinct pathways: (1) enhancing the efficacy of local audit firms and (2) optimizing the corporate governance mechanisms of the Audit Committee. This positive effect is particularly pronounced in the power and energy sector and in the Western regions of China, peaking notably in 2011. This research makes several innovative contributions. Firstly, it expands the theoretical framework for analyzing the macroeconomic effects of audit services. Secondly, it pioneers the application of machine learning methods (GRF) to precisely identify the complex, non-linear relationship in this context. Thirdly, it uncovers significant regional and sectoral heterogeneity in the impact of industry expertise. Based on these results, we recommend three policy actions: (1) strategically supporting the development of industry specialization within local audit firms; (2) enhancing the governance framework of audit committees; and (3) bolstering professional audit support during periods of economic downturn. This study offers crucial reference material for policymakers aiming to cultivate high-quality audit services and an independent knowledge infrastructure.