Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Detecting manager’s fraud risk using text analysis: evidence from Iran

Detecting manager’s fraud risk using text analysis: evidence from Iran In accounting and finance, researchers have used many ways to detect manager’s fraud risk. Until now, many researchers have used some data mining methods in these two fields to detect this risk. The purpose of this paper is to compare the precision of two data mining methods in detecting such a risk.Design/methodology/approachFor this purpose, this paper analyzed the texts of board’s reports and used two methods including the convex optimization (CVX) method and least absolute shrinkage and selection operator (LASSO) regression method. In this way, the words of these reports, which have the greatest power in explaining the manager’s high fraud risk index, were identified. Using these words, this paper presented a model that could detect manager’s high fraud risk index in companies.FindingsThe results indicated that both methods can detect the manager’s high fraud risk index with a precision between 82.55 and 91.25 percent. The LASSO method was significantly more precise than the CVX method.Research limitations/implicationsThe lack of access to an official and reliable list of firms suspected to fraud and the lack of access to the Microsoft Word (MS Word) file of board’s reports were two of the most important limitations of this study.Practical implicationsRegulatory bodies and independent auditors can consider the proposed methods in this study for assessing the fraud risk for a firm or other legal parties.Originality/valueThis paper avoided using merely financial statements data to detect the manager’s fraud risk index and focused on texts of board’s reports for the detection process. The capabilities of data mining and text mining methods for detecting the manager’s fraud risk index using board’s reports were tested in this paper. By comparing CVX and LASSO results, this paper indicated that methods with a binary-dependent variable have more power and are more precise than methods with continuous-dependent variables for detecting fraud. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Applied Accounting Research Emerald Publishing

Detecting manager’s fraud risk using text analysis: evidence from Iran

Download PDF
18 pages

Loading next page...
 
/lp/emerald-publishing/detecting-manager-s-fraud-risk-using-text-analysis-evidence-from-iran-oKG0iNDS19
Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
0967-5426
DOI
10.1108/jaar-01-2018-0016
Publisher site
See Article on Publisher Site

Abstract

In accounting and finance, researchers have used many ways to detect manager’s fraud risk. Until now, many researchers have used some data mining methods in these two fields to detect this risk. The purpose of this paper is to compare the precision of two data mining methods in detecting such a risk.Design/methodology/approachFor this purpose, this paper analyzed the texts of board’s reports and used two methods including the convex optimization (CVX) method and least absolute shrinkage and selection operator (LASSO) regression method. In this way, the words of these reports, which have the greatest power in explaining the manager’s high fraud risk index, were identified. Using these words, this paper presented a model that could detect manager’s high fraud risk index in companies.FindingsThe results indicated that both methods can detect the manager’s high fraud risk index with a precision between 82.55 and 91.25 percent. The LASSO method was significantly more precise than the CVX method.Research limitations/implicationsThe lack of access to an official and reliable list of firms suspected to fraud and the lack of access to the Microsoft Word (MS Word) file of board’s reports were two of the most important limitations of this study.Practical implicationsRegulatory bodies and independent auditors can consider the proposed methods in this study for assessing the fraud risk for a firm or other legal parties.Originality/valueThis paper avoided using merely financial statements data to detect the manager’s fraud risk index and focused on texts of board’s reports for the detection process. The capabilities of data mining and text mining methods for detecting the manager’s fraud risk index using board’s reports were tested in this paper. By comparing CVX and LASSO results, this paper indicated that methods with a binary-dependent variable have more power and are more precise than methods with continuous-dependent variables for detecting fraud.

Journal

Journal of Applied Accounting Research – Emerald Publishing

Published: Jun 4, 2019

Keywords: Text mining; Data mining

References

  • Data mining applications in accounting: a review of the literature and organizing framework
    Amani, F.A.; Fadlalla, A.M.
  • Opportunities for artificial intelligence development in the accounting domain: the case for auditing
    Baldwin, A.A.; Brown, C.E.; Trinkle, B.S.
  • Large-sample evidence on firms’ year-over-year MD&A modifications
    Brown, S.; Tucker, J.
  • Making words work: using financial text as a predictor of financial events
    Cecchini, M.; Aytug, H.; Koehler, G.; Pathak, P.
  • The criminal violation of financial trust
    Cressey, D.R.
  • Beyond the numbers: measuring the information content of earnings press release language
    Davis, A.; Piger, J.; Sedor, L.
  • Beyond the fraud triangle: enhancing deterrence of economic crimes
    Dorminey, J.W.; Fleming, A.S.; Kranacher, M.-J.; Riley, R.A.
  • Application of logistic regression in identifying fraudulent financial reporting
    Etemadi, H.; Zalaghi, H.
  • Dividend policy and fraudulent financial reporting
    Farajzadeh, H.; Aghaei, L.
  • Regularization paths for generalized linear models via coordinate descent
    Friedman, J.; Hastie, T.; Tibshirani, R.
  • A computational model for financial reporting fraud detection
    Glancy, F.; Yadav, S.
  • Beyond the numbers: mining the annual reports for hidden cues indicative of financial statement fraud
    Goel, S.; Gangolly, J.
  • Can linguistic predictors detect fraudulent financial filings?
    Goel, S.; Gangolly, J.; Faerman, S.R.; Uzuner, O.
  • Do fraudulent firms produce abnormal disclosure?
    Hoberg, G.; Lewis, C.
  • A new measure of accounting quality
    Hribar, P.; Kravet, T.; Wilson, R.
  • Identification of fraudulent financial statements using linguistic credibility analysis
    Humphreys, S.; Moffit, K.; Burns, M.; Burgoon, J.; Felix, W.
  • Data mining: a conceptual overview
    Jackson, J.M.
  • Theory of the firm: managerial behavior, agency costs and ownership structure
    Jensen, M.C.; Meckling, W.H.
  • A model to detect potentially fraudulent/abnormal wires of an insurance company: an unsupervised rule-based approach
    Kim, Y.; Vasarhelyi, M.A.
  • Improving auditors’ fraud judgments using a frequency response mode
    Kochetova-Kozloski, N.; Messier, W.F.; Eilifsen, A.
  • Detecting deceptive discussions in conference calls
    Larcker, D.; Zakolyukina, A.
  • Annual report readability, current earnings, and earnings persistence
    Li, F.
  • Textual analysis of corporate disclosures: a survey of the literature
    Li, F.
  • Fraudulent financial reporting detection and business failure prediction models: a comparison
    Liou, F.M.
  • When is a liability not a liability? Textual analysis, dictionaries, and 10-Ks
    Loughran, T.; McDonald, B.
  • On a test of whether one of two random variables is stochastically larger than the other
    Mann, H.B.; Whitney, D.R.
  • Modeling and identifying effective factors affecting the intention of reporting financial fraudulent by accountant
    Namazi, M.; Ebrahimi, F.
  • A support vector machine-based model for detecting top management fraud
    Pai, P.F.; Hsu, M.F.; Wang, M.C.
  • Accounting variables, deception, and a bag of words: assessing the tools of fraud detection
    Purda, L.; Skillicorn, D.
  • Data mining & financial fraud
    Rahnamay Roodposhti, F.
  • The ability of financial ratios in detecting fraudulent financial reporting: logit analysis
    Safarzadeh, M.
  • Association rules for fraud detection
    Tackett, J.A.
  • Regression shrinkage and selection via the lasso
    Tibshirani, R.
  • Managerial ability, political connections, and fraudulent financial reporting in China
    Wang, Z.; Chen, M.-H.; Chin, C.L.; Zheng, Q.
  • Individual comparisons by ranking methods
    Wilcoxon, F.
  • The fraud diamond: considering the four elements of fraud
    Wolfe, D.T.; Hermanson, D.R.
  • Regularization and variable selection via the elastic net
    Zou, H; Hastie, T.
  • Auditing standard number 240: auditor’s responsibility regarding fraud and misconduct: Iranian audit organization