Detecting anomalies in financial statements using machine learning algorithm

The purpose of this paper is to evaluate the possibility of rating the credit worthiness of a firm’s quarterly financial report using a dynamic anomaly detection method.,The study uses a data set containing financial statements from Quarter 1 – 2001 to Quarter 4 – 2016 of 937 Vietnamese listed firms. In sum, 24 fundamental financial indices are chosen as control variables. The study employs the Mahalanobis distance to measure the proximity of each data point from the centroid of the distribution to point out the extent of the anomaly.,The finding shows that the model is capable of ranking quarterly financial reports in terms of credit worthiness. The execution of the model on all observations also revealed that most financial statements of Vietnamese listed firms are trustworthy, while almost a quarter of them are highly anomalous and questionable.,The study faces several limitations, including the availability of genuine accounting data from stock exchanges, the strong assumptions of a simple statistical distribution, the restricted timeframe of financial data and the sensitivity of the thresholds for anomaly levels.,The study opens an avenue for ordinary users of financial information to process the data and question the validity of the numbers presented by listed firms. Furthermore, if fraud information is available, similar research can be conducted to examine the tendency for companies with anomalous financial reports to commit fraud.,This is the first paper of its kind that attempts to build an anomaly detection model for Vietnamese listed companies.

[1]  Z. Rezaee,et al.  The role of corporate governance in convergence with IFRS: evidence from China , 2012 .

[2]  David B. Farber,et al.  Restoring Trust after Fraud: Does Corporate Governance Matter? , 2004 .

[3]  Peter Bajorski.  Statistics for Imaging, Optics, and Photonics , 2011 .

[4]  M. Jacob.  Tax Regimes and Capital Gains Realizations , 2016 .

[5]  B. Green,et al.  Assessing the risk of management fraud through neural network technology , 1997 .

[6]  M. Lokanan.  Theorizing Financial Crimes as Moral Actions , 2017 .

[7]  M. Dacin,et al.  Psychological Pathways to Fraud: Understanding and Preventing Fraud in Organizations , 2011 .

[8]  Taek Mu Kwon,et al.  The Efficacy of Red Flags in Predicting the SEC's Targets: An Artificial Neural Networks Approach , 2000, Intell. Syst. Account. Finance Manag..

[9]  Steven Dellaportas.  Conversations with inmate accountants: Motivation, opportunity and the fraud triangle , 2013 .

[10]  Lynnette D. Purda.  Accounting Variables , Deception , and a Bag of Words : Assessing the Tools of Fraud Detection * , 2014 .

[11]  Peter Bajorski,et al.  Statistics for Imaging, Optics, and Photonics: Bajorski/Statistics for Imaging , 2011 .

[12]  David West,et al.  Neural network ensemble strategies for financial decision applications , 2005, Comput. Oper. Res..

[13]  Richard A. Riley,et al.  Financial Statement Fraud: Insights from the Academic Literature , 2008 .

[14]  S. Dolan,et al.  The Role of Power in Financial Statement Fraud Schemes , 2015 .

[15]  Evgeny Lyandres,et al.  Investment Opportunities and Bankruptcy Prediction , 2013 .

[16]  Marimuthu Palaniswami,et al.  Selecting bankruptcy predictors using a support vector machine approach , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[17]  Zhongmou Li.  Anomaly detection and predictive analytics for financial risk management , 2016 .

[18]  M. Beasley.  An Empirical Analysis of the Relation between Board of Director Composition and Financial Statement Fraud , 1998 .

[19]  Donald R. Jones,et al.  Reliance on Decision Aids: An Examination of Auditors' Assessment of Management Fraud , 1997 .

[20]  Mark I. Hwang,et al.  A fuzzy neural network for assessing the risk of fraudulent financial reporting , 2003 .

[21]  Yves Gendron,et al.  The construction of the risky individual and vigilant organization: A genealogy of the fraud triangle , 2014 .

[22]  P. Murphy,et al.  Attitude, Machiavellianism and the Rationalization of Misreporting , 2012 .

[23]  I. Harymawan,et al.  Do Reputable Companies Produce a High Quality of Financial Statements , 2017 .

[24]  Alessandro Danovi,et al.  Z-Score Models' Application to Italian Companies Subject to Extraordinary Administration , 2013 .

[25]  Z. Rezaee.  Causes, consequences, and deterence of financial statement fraud , 2005 .

[26]  M. D. Beneish,et al.  The Predictable Cost of Earnings Manipulation , 2007 .

[27]  Yanchun Zhang,et al.  Support Vector Machine for Outlier Detection in Breast Cancer Survivability Prediction , 2008, APWeb Workshops.

[28]  Fatah Behzadian,et al.  An Investigation of Expectation Gap between Independent Auditors and Users from Auditing Services Related to the Quality of Auditing Services Based on Their Role and Professional Features in Auditing Process , 2017 .

[29]  M. Lokanan.  Testing for impression management in creative accounting: A case of the automobile industry , 2017 .

[30]  M. Lokanan.  Challenges to the fraud triangle: Questions on its usefulness , 2015 .

[31]  Yannis Manolopoulos,et al.  Data Mining techniques for the detection of fraudulent financial statements , 2007, Expert Syst. Appl..

[32]  D. Cooper,et al.  Fraud in Accounting, Organizations and Society: Extending the Boundaries of Research , 2013 .

[33]  Runze Li,et al.  Statistical Challenges with High Dimensionality: Feature Selection in Knowledge Discovery , 2006, math/0602133.

[34]  M. D. Beneish,et al.  The Detection of Earnings Manipulation , 1999 .

[35]  Sotiris Kotsiantis,et al.  Forecasting Fraudulent Financial Statements using Data Mining , 2007 .

[36]  M. Joshi,et al.  What influences the willingness of Vietnamese accountants to adopt International Financial Reporting Standards (IFRS) by 2025 , 2018 .

[37]  Z. Rezaee,et al.  Financial Statement Fraud: Prevention and Detection , 2002 .

[38]  Petr Hájek,et al.  Mining corporate annual reports for intelligent detection of financial statement fraud - A comparative study of machine learning methods , 2017, Knowl. Based Syst..

[39]  D. BeneishMessod,et al.  The Detection of Earnings Manipulation , 1999 .

[40]  M. D. Beneish,et al.  Earnings Manipulation and Expected Returns , 2013 .

[41]  M. Lokanan.  The demographic profile of victims of investment fraud , 2014 .

[42]  Vineet Agarwal,et al.  Comparing the Performance of Market-Based and Accounting-Based Bankruptcy Prediction Models , 2006 .

[43]  Christopher J. Skousen,et al.  Advances in Financial Economics , 2009 .

[44]  Iyad Zaarour,et al.  Towards a Machine Learning Approach for Earnings Manipulation Detection , 2017 .

[45]  M. Lokanan.  A fraud triangle analysis of the libor fraud , 2018 .

[46]  Edward I. Altman,et al.  FINANCIAL RATIOS, DISCRIMINANT ANALYSIS AND THE PREDICTION OF CORPORATE BANKRUPTCY , 1968 .

[47]  M. D. Beneish,et al.  Detecting GAAP violation: implications for assessing earnings management among firms with extreme financial performance , 1997 .

[48]  Damminda Alahakoon,et al.  Minority report in fraud detection: classification of skewed data , 2004, SKDD.

[49]  Kyung-shik Shin,et al.  An application of support vector machines in bankruptcy prediction model , 2005, Expert Syst. Appl..

[50]  G. R. Young,et al.  Forensic Accounting and Fraud Examination , 2007 .

[51]  Christopher J. Skousen,et al.  Detecting and Predicting Financial Statement Fraud: The Effectiveness of the Fraud Triangle and SAS No. 99 , 2008 .

[52]  Charalambos Spathis.  Detecting false financial statements using published data: some evidence from Greece , 2002 .

[53]  Xinwei Zheng,et al.  Market liquidity risk factor and financial market anomalies: Evidence from the Chinese stock market , 2010 .

[54]  Heather L. Pesch,et al.  Fraud Dynamics and Controls in Organizations , 2013 .

[55]  Jianguo Du,et al.  Application of Machine Learning Methods to Risk Assessment of Financial Statement Fraud: Evidence from China , 2014 .

[56]  Chad Albrecht,et al.  Fraud examination & prevention , 2004 .

[57]  Joseph V. Carcello,et al.  A Decision Aid for Assessing the Likelihood of Fraudulent Financial Reporting , 2000 .

[58]  John Salvatier,et al.  When Will AI Exceed Human Performance? Evidence from AI Experts , 2017, ArXiv.

[59]  I. Morozov.  Anomaly Detection in Financial Data by Using Machine Learning Methods , 2016 .

[60]  Tanveer A. Faruquie,et al.  Anomaly Detection in Finance: Editors' Introduction , 2017, ADF@KDD.

[61]  N. Wilson,et al.  Financial distress and bankruptcy prediction among listed companies using accounting, market and macroeconomic variables , 2013 .

[62]  Karla M. Zehms,et al.  Engagement Planning, Bid Pricing, and Client Response in the Market for Initial Attest Engagements , 2001 .

[63]  Kenneth O. Cogger,et al.  Neural network detection of management fraud using published financial data , 1998, Intell. Syst. Account. Finance Manag..

[64]  Johan L. Perols.  Financial Statement Fraud Detection: An Analysis of Statistical and Machine Learning Algorithms , 2011 .

[65]  Michael Power,et al.  The apparatus of fraud risk , 2013 .

[66]  Deniz Senturk-Doganaksoy,et al.  A genetic algorithm approach to detecting temporal patterns indicative of financial statement fraud , 2007, Intell. Syst. Account. Finance Manag..