Multisource evidence theory‐based fraud risk assessment of China's listed companies

Abstract

AbstractFinancial fraud has great negative impact on capital markets. It misleads investors and the government and will hurt the development of the capital market in China. To detect corporate fraud, an artificial intelligence‐based method is proposed to evaluate the fraud risk. A new model for assessing the fraud risk of listed companies in China is put forward. The proposed approach collects multisource evidence from inside and outside listed companies. The internal evidence for fraud risk assessment is gathered by a machine‐learning method. The external evidence for fraud risk assessment is obtained by a web crawler. An evidence theory‐based is employed for integrating the multisource evidence. The Fraud Risk Assessment Model based on Multisource Evidence Theory is established. The proposed model is applied to assess the fraud risk of the listed companies in China. The results indicate that the proposed model is effective at evaluating the fraud risk of listed companies, and it also has a higher precision, recall, and F‐1 measure than the traditional probability model.