An Analysis on Financial Statement Fraud Detection for Chinese Listed Companies Using Deep Learning

Wu Xiuguo,Du Shengyong

doi:10.1109/access.2022.3153478

Abstract

Financial fraud has extremely damaged the sustainable growth of financial markets as a serious problem worldwide. Nevertheless, it is fairly challenging to identify frauds with highly imbalanced dataset because ratio of non-fraud companies is very high compared to fraudulent ones. Intelligent financial statement fraud detection systems have therefore been developed to support decision-making for the stakeholders. However, most of current approaches only considered the quantitative part of the financial statement ratios while there has been less usage of the textual information for classifying, especially those related comments in Chinese. As such, this paper aims to develop an enhanced system for detecting financial fraud using a state-of-the-art deep learning models based on combination of numerical features that derived from financial statement and textual data in managerial comments of 5130 Chinese listed companies’ annual reports. First, we construct financial index system including both financial and non-financial indices that previous researches usually excluded. Then the textual features in MD&A section of Chinese listed company’s annual reports are extracted using word vector. After that, powerful deep learning models are employed and their performances are compared with numeric data, textual data and combination of them, respectively. The empirical results show great performance improvement of the proposed deep learning methods against traditional machine learning methods, and LSTM, GRU approaches work with testing samples in correct classification rates of 94.98% and 94.62%, indicating that the extracted textual features of MD&A section exhibit promising classification results and substantially reinforce financial fraud detection.

Highlights

With the boom of the securities market in last decades, more and more companies raise capital and expand the operation scale through listing, especially in fast growing counties like China
The detection of financial statement fraud is considered a binary classification problem with four potential classification outcomes: (i) True positive (TP): it denotes the correct classification of a fraudulent company; (ii) False negative (FN): it denotes the incorrect classification of a fraudulent company as a non-fraudulent company; (iii) True negative (TN): it denotes the correct classification of a non-fraudulent company; (iv) False positive (FP): it denotes the incorrect classification of a non-fraudulent company as a fraudulent company
The accuracy is widely used in model predictive power comparisons, which is defined as the percentage of correctly classified instances: Accuracy=TP+TN

Summary

Introduction

With the boom of the securities market in last decades, more and more companies raise capital and expand the operation scale through listing, especially in fast growing counties like China. Accompanied by financial market development, fraudulent financial reports have cast rapidly, and have had negative impacts on capital markets and a loss of shareholder value [1,2]. In China, the number of criminals involved with fraudulent activities in 2019 is more than 961 with a value of more than $8 billion [4]. There are minor variations in its definition, a financial statement fraud is referred as “deliberate fraud committed by management that injures investors and creditors through misleading financial statements” [2]. One of the main causes of fraud is the failure of CPAs and auditors through issuances of inaccurate audit reports. Companies with rapid growth may exceed the monitoring process ability to provide proper supervision

Objectives

Methods

Results

Discussion

Conclusion