Analysis of financial statement and prewarning of audit risks based on artificial neural network

Abstract

The marketization of social capital has resulted in frequent audit failures, and financial statement frauds. One of the key steps of auditing is the identification of material misstatement risk of financial statement. However, there is no unified analysis framework or quantitative method for identifying this risk. Therefore, this paper aims to analyze financial statement and prewarn audit risks in an accurate manner. Firstly, the items of financial statement were analyzed in three aspects of the target enterprise: balance statement, income statement, and cash flow statement. Next, the authors probed deep into the core indices of the post audit risk verification and evaluation of the business process, constructed a scientific evaluation index system for audit risks of financial statement, and quantified the 89 tertiary indices, 21 secondary indices, and 3 primary indices. After that, an audit risk prediction model for financial statement was established based on neural network. Experimental results show the effectiveness of the proposed model for audit risk prewarning, and applicable to other tasks of financial auditing.