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

Learn More →

Identifying financial statement fraud with decision rules obtained from Modified Random Forest

Identifying financial statement fraud with decision rules obtained from Modified Random Forest Financial statement fraud (FSF) committed by companies implies the current status of the companies may not be healthy. As such, it is important to detect FSF, since such companies tend to conceal bad information, which causes a great loss to various stakeholders. Thus, the objective of the paper is to propose a novel approach to building a classification model to identify FSF, which shows high classification performance and from which human-readable rules are extracted to explain why a company is likely to commit FSF.Design/methodology/approachHaving prepared multiple sub-datasets to cope with class imbalance problem, we build a set of decision trees for each sub-dataset; select a subset of the set as a model for the sub-dataset by removing the tree, each of whose performance is less than the average accuracy of all trees in the set; and then select one such model which shows the best accuracy among the models. We call the resulting model MRF (Modified Random Forest). Given a new instance, we extract rules from the MRF model to explain whether the company corresponding to the new instance is likely to commit FSF or not.FindingsExperimental results show that MRF classifier outperformed the benchmark models. The results also revealed that all the variables related to profit belong to the set of the most important indicators to FSF and that two new variables related to gross profit which were unapprised in previous studies on FSF were identified.Originality/valueThis study proposed a method of building a classification model which shows the outstanding performance and provides decision rules that can be used to explain the classification results. In addition, a new way to resolve the class imbalance problem was suggested in this paper. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Data Technologies and Applications Emerald Publishing

Identifying financial statement fraud with decision rules obtained from Modified Random Forest

An, Byungdae; Suh, Yongmoo
Data Technologies and Applications , Volume 54 (2): 21 – Jun 2, 2020
Download PDF
21 pages

Loading next page...
 
/lp/emerald-publishing/identifying-financial-statement-fraud-with-decision-rules-obtained-ripFU79bpu
Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
2514-9288
DOI
10.1108/dta-11-2019-0208
Publisher site
See Article on Publisher Site

Abstract

Financial statement fraud (FSF) committed by companies implies the current status of the companies may not be healthy. As such, it is important to detect FSF, since such companies tend to conceal bad information, which causes a great loss to various stakeholders. Thus, the objective of the paper is to propose a novel approach to building a classification model to identify FSF, which shows high classification performance and from which human-readable rules are extracted to explain why a company is likely to commit FSF.Design/methodology/approachHaving prepared multiple sub-datasets to cope with class imbalance problem, we build a set of decision trees for each sub-dataset; select a subset of the set as a model for the sub-dataset by removing the tree, each of whose performance is less than the average accuracy of all trees in the set; and then select one such model which shows the best accuracy among the models. We call the resulting model MRF (Modified Random Forest). Given a new instance, we extract rules from the MRF model to explain whether the company corresponding to the new instance is likely to commit FSF or not.FindingsExperimental results show that MRF classifier outperformed the benchmark models. The results also revealed that all the variables related to profit belong to the set of the most important indicators to FSF and that two new variables related to gross profit which were unapprised in previous studies on FSF were identified.Originality/valueThis study proposed a method of building a classification model which shows the outstanding performance and provides decision rules that can be used to explain the classification results. In addition, a new way to resolve the class imbalance problem was suggested in this paper.

Journal

Data Technologies and Applications – Emerald Publishing

Published: Jun 2, 2020

Keywords: Financial statement fraud; Random forest; Decision rules; Feature importance; Machine learning; Predictive model

References

  • Metafraud: a meta-learning framework for detecting financial fraud
    Abbasi, A.; Albrecht, C.; Vance, A.; Hansen, J.
  • Female board presence and the likelihood of financial restatement
    Abbott, L.J.; Parker, S.; Presley, T.J.
  • Impact of the corporate governance on the financial statement fraud: a study focused on companies in Tanzania
    Abri, A.F.; Arumugam, D.; Balasingam, S.
  • Report to the Nations: 2018 Global study on occupation fraud and abuse
  • Corporate equal opportunities (non-) disclosure
    Adams, C.A.; Coutts, A.; Harte, G.
  • Bagging predictors
    Breiman, L.
  • Random forests
    Breiman, L.
  • Detecting management fraud in public companies
    Cecchini, M.; Aytug, H.; Koehler, G.J.; Pathak, P.
  • SMOTEBoost: improving prediction of the minority class in boosting
    Chawla, N.V.; Lazarevic, A.; Hall, L.O.; Bowyer, K.W.
  • Predicting corporate financial distress based on integration of decision tree classification and logistic regression
    Chen, M.
  • Application of random forest, Rough set theory, decision tree and neural network to detect financial statement fraud–taking corporate governance into consideration
    Chen, F.H.; Chi, D.-J.; Zhu, J.-Y.
  • Are individual investors uninformed? Evidence from trading behaviors by heterogeneous investors around unfaithful corporate disclosure
    Chung, C.Y.; Lee, J.; Park, J.
  • Detecting earnings management
    Dechow, P.M.; Sloan, R.G.; Sweeney, A.P.
  • Causes and consequences of earnings manipulation: an analysis of firms subject to enforcement actions by the SEC
    Dechow, P.M.; Sloan, R.G.; Sweeney, A.P.
  • Predicting material accounting misstatements
    Dechow, P.M.; Ge, W.; Larson, C.R.; Sloan, R.G.
  • Debt covenant violation and manipulation of accruals
    DeFond, M.L.; Jiambalvo, J.
  • Detecting financial restatements using data mining techniques
    Dutta, I.; Dutta, S.; Raahemi, B.
  • Financial restatements, audit fees, and the moderating effect of CFO turnover
    Feldmann, D.A.; Read, W.J.; Abdolmohammadi, M.J.
  • Detecting financial statements fraud: the evidence from Russia
    Feruleva, N.V.; Shtefan, M.A.
  • Financial statement restatements: trend, market impacts, regulatory responses, and remaining challenges
    GAO
  • How firms respond to financial restatement: CEO successors and external reactions
    Gomulya, D.; Boeker, W.
  • Mining corporate annual reports for intelligent detection of financial statement fraud–a comparative study of machine learning methods
    Hajek, P.; Henriques, R.
  • Information asymmetry, corporate governance, and shareholder wealth: evidence from unfaithful disclosures of Korean listed firms
    Han, S.H.; Kim, M.; Lee, D.H.; Lee, S.
  • Roles executives play: CEOs, behavioral complexity, and firm performance
    Hart, S.L.; Quinn, R.E.
  • Information asymmetry, corporate disclosure, and the capital markets: a review of the empirical disclosure literature
    Healy, P.M.; Palepu, K.G.
  • Nearest neighbors in random subspaces
    Ho, T.K.
  • A data complexity analysis of comparative advantages of decision forest constructors
    Ho, T.K.
  • Topological pattern discovery and feature extraction for fraudulent financial reporting
    Huang, S.-Y.; Tsaih, R.-H.; Yu, F.
  • An effective financial statements fraud detection model for the sustainable development of financial markets: evidence from Taiwan
    Jan, C.L.
  • Hanmiyagpum soaegjuju 200yeomyeong, jibdansosong jegi
    Kim, H.
  • Detecting financial misstatements with fraud intention using multi-class cost-sensitive learning
    Kim, Y.J.; Baik, B.; Cho, S.
  • Data mining techniques for the detection of fraudulent financial statements
    Kirkos, E.; Spathis, C.; Manolopoulos, Y.
  • Machine learning: a review of classification and combining techniques
    Kotsiantis, S.B.; Zaharakis, I.D.; Pintelas, P.E.
  • [2016 guggam] jin-ungseob "hanmiyagpum neuj-jang-gongsi josajung…gongsijedo bowan gomin
    Lee, M.
  • The effect of unfaithful disclosure on the cost of debt
    Lee, A.Y.; Chun, S.B.; Park, S.S.
  • Managerial incentives, CEO characteristics and corporate innovation in China's private sector
    Lin, C.; Lin, P.; Song, F.M.; Li, C.
  • Detecting the financial statement fraud: the analysis of the differences between data mining techniques and experts' judgments
    Lin, C.-C.; Chiu, A.-A.; Huang, S.Y.; Yen, D.C.
  • Financial fraud detection model: based on random forest
    Liu, C.; Chan, Y.; Alam Kazmi, S.H.; Fu, H.
  • Relation between audit effort and financial report misstatements: evidence from quarterly and annual restatements
    Lobo, G.J.; Zhao, Y.
  • Rule extraction from random forest: the RF + HC methods
    Mashayekhi, M.; Gras, R.
  • Financial reporting fraud detection: an analysis of data mining algorithms
    Mohammadi, M.; Yazdani, S.; Khanmohammadi, M.; Maham, K.
  • Application of data mining techniques in customer relationship management: a literature review and classification
    Ngai, E.W.; Xiu, L.; Chau, D.C.
  • A support vector machine-based model for detecting top management fraud
    Pai, P.-F.; Hsu, M.-F.; Wang, M.-C.
  • Detection models for unintentional financial restatements
    Papík, M.; Papíková, L.
  • Financial statement fraud detection: an analysis of statistical and machine learning algorithms
    Perols, J.
  • Mining lung cancer patient data to assess healthcare resource utilization
    Phillips-Wren, G.; Sharkey, P.; Dy, S.M.
  • Newer classification and regression tree techniques: bagging and random forests for ecological prediction
    Prasad, A.M.; Iverson, L.R.; Liaw, A.
  • Detection of financial statement fraud and feature selection using data mining techniques
    Ravisankar, P.; Ravi, V.; Rao, G.R.; Bose, I.
  • Causes, consequences, and deterence of financial statement fraud
    Rezaee, Z.
  • Predicting earnings management: the case of earnings restatements
    Richardson, S.; Tuna, A.; Wu, M.
  • The effects of external pressures, financial targets and financial distress on financial statement fraud
    Safiq, M.; Seles, W.
  • Bringing darkness to light: the influence of auditor quality and audit committee expertise on the timeliness of financial statement restatement disclosures
    Schmidt, J.; Wilkins, M.S.
  • Executive overconfidence and the slippery slope to financial misreporting
    Schrand, C.M.; Zechman, S.L.
  • The association between audit committee multiple-directorships, tenure, and financial misstatements
    Sharma, V.D.; Iselin, E.R.
  • Application of machine learning methods to risk assessment of financial statement fraud: evidence from China
    Song, X.P.; Hu, Z.H.; Du, J.G.; Sheng, Z.H.
  • Knowledge-based financial statement fraud detection system: based on an ontology and a decision tree
    Tang, X.B.; Liu, G.C.; Yang, J.; Wei, W.
  • Digital mapping of soil organic matter stocks using random forest modeling in a semi-arid steppe ecosystem
    Wiesmeier, M.; Barthold, F.; Blank, B.; Kogel-Knabner, I.
  • Mine classification with imbalanced data
    Williams, D.P.; Myers, V.; Silvious, M.S.
  • Binary PSO with mutation operator for feature selection using decision tree applied to spam detection
    Zhang, Y.; Wang, S.; Phillips, P.; Ji, G.