Unsupervised neural networks approach for understanding fraudulent financial reporting
| Published date | 09 March 2012 |
| Pages | 224-244 |
| Date | 09 March 2012 |
| DOI | https://doi.org/10.1108/02635571211204272 |
| Author | Shin‐Ying Huang,Rua‐Huan Tsaih,Wan‐Ying Lin |
| Subject Matter | Economics,Information & knowledge management,Management science & operations |
Unsupervised neural networks
approach for understanding
fraudulent financial reporting
Shin-Ying Huang and Rua-Huan Tsaih
Department of Management Information Systems,
National Chengchi University, Taipei, Taiwan, ROC, and
Wan-Ying Lin
Department of Accounting, National Chengchi University, Taipei, Taiwan, ROC
Abstract
Purpose – Creditor reliance on accounting-based numbers as a persistent and traditional standard to
assess a firm’s financial soundness and viability suggests that the integrity of financial statements is
essential to credit decisions. The purpose of this paper is to provide an approach to explore fraudulent
financial reporting (FFR) via growing hierarchical self-organizing map (GHSOM), an unsupervised
neural network tool, to help capital providers evaluate the integrity of financial statements, and to
facilitate analysis further to reach prudent credit decisions.
Design/methodology/approach – This paper develops a two-stage approach: a classification stage
that well trains the GHSOM to cluster the sample into subgroups with hierarchical relationship, and a
pattern-disclosure stage that uncovers patterns of the common FFR techniques and relevant risk
indicators of each subgroup.
Findings – An application is conducted and its results show that the proposed two-stage approach
can help capital providers evaluate the reliability of fin ancial statements and accounting
numbers-based decisions.
Practical implications – Following the SOM theories, it seems that common FFR techniques and
relevant risk indicators extracted from the GHSOM clustering result are applicable to all samples
clustered in the same leaf node (subgroup). This principle and any pre-warning signal derived from the
identified indicators can be applied to assessing the reliability of financial statements and forming a
basis for further analysis in order to reach prudent decisions. The limitation of this paper is the
subjective parameter setting of GHSOM.
Originality/value – This is the first application of GHSOM to financial data and demonstrates an
alternative way to help capital providers such as lenders to evaluate the integrity of financial
statements, a basis for further analysis to reach prudent decisions. The proposed approach could be
applied to other scenarios that rely on accounting numbers as a basis for decisions.
Keywords Financial reporting,Knowledge management, Neuralnets, Financial statements,
Fraudulent financialreporting, Growing hierarchicalself-organizing map, Knowledge extraction
Paper type Research paper
1. Introduction
This paper focuses on exploring fraudulent financial reporting (FFR) via growing
hierarchical self-organizing map (GHSOM), an unsupervised neural network tool
(Dittenbach et al., 2000, 2002; Rauber et al., 2002), to help capital providers, for instance
The current issue and full text archive of this journal is available at
www.emeraldinsight.com/0263-5577.htm
The authors gratefully acknowledge the grant from the National Science Council, ROC (Project
No. NSC98-2410-H-004-049-MY2).
IMDS
112,2
224
Received 24 April 2011
Revised 6 September 2011
Accepted 7 September 2011
Industrial Management & Data
Systems
Vol. 112 No. 2, 2012
pp. 224-244
qEmerald Group Publishing Limited
0263-5577
DOI 10.1108/02635571211204272
the lenders, to evaluate the reliability of financial statements and to facilitate analysis
further to reach prudent credit decisions. FFR, or financial statement fraud, involves
the intentional misstatement or omission of material information from an
organization’s financial reports (Beasley et al., 1999). FFR can lead not only to
significant risks for stockholders and creditors, but also to financial crises for the
capital market. According to the Association of Certified Fraud Examiners (ACFE)
(2008), FFR is the most costly form of occupational fraud, with median losse s of
$2 million per scheme[1]. What investors and creditors do observe all too often lately is
instance where it appears the auditors and/or the audit committees were not effective.
These are the cases of fraud, material errors or misstatements, material omissions,
restatement of prior years’ earnings due to accounting oversights or improprieties,
or maybe just aggressive accounting called to the attention of the corporation by the
Securities and Exchange Commission (SEC) or shareholder advocates (Imhoff, 2003).
Anderson et al. (2004) found that creditor reliance on accounting-based debt covenants
suggests that debtors are potentially concerned with the integrity of financial
accounting reports. Lin et al. (2008a, b) indicate that financial statements are dressed
up to the point that they do not accurately reflect a company’s profitability, and
companies frequently hide material information or delay its disclosure. The 2008
Report to the Nation on Occupational Fraud & Abuse study conducted by the ACFE
reveals that more than half of the 959 fraud experts polled performed mor e
fraud-related investigations in 2008 than in 2007. About as many respondents also say
known perpetrators reported feeling financial pressure before they committed the
fraudulent acts. FFR has drawn much public as well as academic attention. Kalbers
(2009) concludes that academic research in earnings management and FFR has become
increasingly narrow in addressing important issues and problems in practice.
Creditor dependence on accounting numbers as a persistent and traditional
standard to assess firms’ health and viability suggests that the faithfulness of financial
statements is critical to credit decisions. The purpose of this study is to provide
an approach that helps capital providers such as creditors to evaluate the integrity of
financial statements and that facilitate further analysis to reach prudent credit
decisions. The proposed approach uncovers the common FFR techniques from each
subgroup of FFR samples clustered by GHSOM. By knowing that the financial
statement examined is classified into a certain FFR subgroup and its possible common
FFR techniques, help creditors form the basis for judgments and further analysis.
The remainder of this paper is organized as follows. Section 2 reviews the literature.
Section 3 presents the proposed approach. Section 4 reports the research results.
Section 5 provides the managerial and research implications based on the results. The
last section concludes with a summary of findings, implications and suggestions for
future works.
2. Literature review
2.1 Fraudulent financial reporting
Most of the priorFFR-related researchesfocus on the nature or the predictionof FFR. The
nature-relatedFFR researchoften uses the case study approachand provides a descriptive
analysis of the characteristics of FFR and techniques commonly used. For example, the
Committee of Sponsoring Organizations (COSO) of the Treadway Commission and
the ACFE regularlypublish their own analyseson FFR of the US companies. Based on the
Fraudulent
financial
reporting
225
To continue reading
Request your trial