Seminar (Dept. of Accounting)

Theme：A MACHINE LEARNING APPROACH OF MEASURING AUDIT QUALITY: EVIDENCE FROM CHINA

Speaker：Zhang Min, Professor, School of Business, Renmin University of China

Time：2021-09-15 10:00

Address：Room 302, Mingde Business Building

Language：Chinese

ABSTRACT:

Based on traditional observable audit quality proxies (e.g., audit adjustment and non-clean audit opinion), this study develops machine learning models to predict audit quality with a wide range of data describing detailed characteristics of accounting firms, individual audit partners, public companies in China. It constructs a new measure of audit quality, the surprise score, which is the difference between the predicted probability and the actual value. Contrary to the traditional observable proxies that indirectly measure the audit quality, the proposed measure is driven by unobservable factors directly affecting the audit quality. This study also demonstrates the application of the proposed measure by examining the association between the surprise score and audit failures proxied by penalties due to accounting violations. It finds that the proposed measure outperforms traditional ones in terms of predicting penalties.