AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
We have investigated the current practices in financial fraud detection using intelligent approaches, both statistical and computational

Intelligent Financial Fraud Detection Practices: An Investigation.

Lecture Notes of the Institute for Computer Sciences Social Informatics and Telecommunications Engin..., (2015): 186-203

Cited by: 24|Views203
EI

Abstract

Financial fraud is an issue with far reaching consequences in the finance industry, government, corporate sectors, and for ordinary consumers. Increasing dependence on new technologies such as cloud and mobile computing in recent years has compounded the problem. Traditional methods of detection involve extensive use of auditing, where a ...More

Code:

Data:

0
Introduction
  • Introduction and Background

    Financial fraud is an issue that has wide reaching consequences in both the finance industry and daily life.
  • Computational intelligence (CI)based as well as conventional data mining approaches have been proven to be useful because of their ability to detect small anomalies in large data sets [14].
  • There are many different types of financial fraud, as well as a variety of data mining methods, and research is continually being undertaken to find the best approach for each case.
  • The common financial fraud categories and the popular data mining as well as computational intelligence-based techniques used for financial fraud detection are depicted in Fig. 1 and Fig. 2 respectively
Highlights
  • Introduction and Background

    Financial fraud is an issue that has wide reaching consequences in both the finance industry and daily life
  • The common financial fraud categories and the popular data mining as well as computational intelligence-based techniques used for financial fraud detection are depicted in Fig. 1 and Fig. 2 respectively
  • Fraud detection is an important part of the modern finance industry
  • We have investigated the current practices in financial fraud detection using intelligent approaches, both statistical and computational
  • Each technique was shown to be reasonably capable at detecting various forms of financial fraud
  • Further research into the differences between each type of financial fraud could lead to a generic framework which would greatly enhance the scope of intelligent detection methods for this problem domain
Methods
  • Method Investigated

    Credit card transaction Logistic model fraud from a real world Support vector machines example

    Random forests [12]

    Financial statement fraud Decision trees from a selection of Greek Neural networks manufacturing firms

    Bayesian belief networks [19]

    Financial statement fraud Support vector machine with financial items from Genetic programming a selection of public Neural network

    Chinese companies

    Group method of data handling 88.14-93.00%

    Logistic model

    Neural network [7]

    Financial statement fraud Text mining with singular valida- 95.65%.
  • Financial statement fraud Decision trees from a selection of Greek Neural networks manufacturing firms.
  • Financial statement fraud Support vector machine with financial items from Genetic programming a selection of public Neural network.
  • Suitable for categorical classification problems like fraud detection.
  • Used for classification and prediction.
  • Useful for determining which method is best applied to the problem domain.
  • Provide both clustering and classification abilities, to neural networks.
Conclusion
  • The authors have investigated the current practices in financial fraud detection using intelligent approaches, both statistical and computational.
  • Though their performance differed, each technique was shown to be reasonably capable at detecting various forms of financial fraud.
  • Further research into the differences between each type of financial fraud could lead to a generic framework which would greatly enhance the scope of intelligent detection methods for this problem domain
Tables
  • Table1: Accuracy results for fraud detection practices
  • Table2: Sensitivity results for fraud detection practices
  • Table3: Specificity results for fraud detection practices
  • Table4: Classification based on detection algorithm used
  • Table5: Classification based on fraud type investigated
Download tables as Excel
Study subjects and analysis
samples: 100
This has had an affect both on the fraud types that have been investigated as well as the datasets used for the purpose. In the published literature many of the financial fraud simulations consisted of less than a few hundred samples, typically with comparable amounts of fraudulent and legitimate specimens. This is contrary to the realities of the problem domain, where fraud cases are far outweighed by legitimate transactions [3]

Reference
  • Bai B, Yen J, and Yang X (2008) False financial statements: characteristics of China's listed companies and CART detecting approach. International Journal of Information Technology & Decision Making 7, 339-59.
    Google ScholarLocate open access versionFindings
  • Bermúdez L, Pérez J, Ayuso M, Gómez E, and Vázquez F (2008) A Bayesian dichotomous model with asymmetric link for fraud in insurance. Insurance: Mathematics and Economics 42, 779-86.
    Google ScholarLocate open access versionFindings
  • Bhattacharyya S, Jha S, Tharakunnel K, and Westland JC (2011) Data mining for credit card fraud: A comparative study. Decision Support Systems 50, 602-13.
    Google ScholarLocate open access versionFindings
  • Bose I and Wang J (2007) Data mining for detection of financial statement fraud in Chinese Companies. Paper presented at the International Conference on Electronic Commerce, Administration, Society and Education, Hong Kong, 15-17 August 2007.
    Google ScholarLocate open access versionFindings
  • Cecchini M, Aytug H, Koehler GJ, and Pathak P (2010) Making words work: Using financial text as a predictor of financial events. Decision Support Systems 50, 164-75.
    Google ScholarLocate open access versionFindings
  • Duman E and Ozcelik MH (2011) Detecting credit card fraud by genetic algorithm and scatter search. Expert Systems with Applications 38, 13057-63.
    Google ScholarLocate open access versionFindings
  • Glancy FH and Yadav SB (2011) A computational model for financial reporting fraud detection. Decision Support Systems 50, 595-601.
    Google ScholarLocate open access versionFindings
  • Holton C (2009) Identifying disgruntled employee systems fraud risk through text mining: A simple solution for a multi-billion dollar problem. Decision Support Systems 46, 853-64.
    Google ScholarLocate open access versionFindings
  • Hoogs B, Kiehl T, Lacomb C, and Senturk D (2007) A genetic algorithm approach to detecting temporal patterns indicative of financial statement fraud. Intelligent Systems in Accounting, Finance and Management 15, 41-56.
    Google ScholarLocate open access versionFindings
  • Humpherys SL, Moffitt KC, Burns MB, Burgoon JK, and Felix WF (2011) Identification of fraudulent financial statements using linguistic credibility analysis. Decision Support Systems 50, 585-94.
    Google ScholarLocate open access versionFindings
  • Jans M, van der Werf JM, Lybaert N, and Vanhoof K (2011) A business process mining application for internal transaction fraud mitigation. Expert Systems with Applications 38, 13351-9.
    Google ScholarLocate open access versionFindings
  • Kirkos E, Spathis C, and Manolopoulos Y (2007) Data mining techniques for the detection of fraudulent financial statements. Expert Systems with Applications 32, 995-1003.
    Google ScholarLocate open access versionFindings
  • Koh HC and Low CK (2004) Going concern prediction using data mining techniques. Managerial Auditing Journal 19, 462-76.
    Google ScholarLocate open access versionFindings
  • Ngai E, Hu Y, Wong Y, Chen Y, and Sun X (2011) The application of data mining techniques in financial fraud detection: A classification framework and an academic review of literature. Decision Support Systems 50, 559-69.
    Google ScholarLocate open access versionFindings
  • Paasch CA (2010) In Credit card fraud detection using artificial neural networks tuned by genetic algorithms. Vol. pp. HONG KONG UNIV. OF SCI. AND TECH.(HONG KONG), 16. Panigrahi S, Kundu A, Sural S, and Majumdar AK (2009) Credit card fraud detection: A fusion approach using Dempster–Shafer theory and Bayesian learning. Information Fusion 10, 354-63.
    Google ScholarLocate open access versionFindings
  • 17. Pinquet J, Ayuso M, and Guillen M (2007) Selection bias and auditing policies for insurance claims. Journal of Risk and Insurance 74, 425-40.
    Google ScholarLocate open access versionFindings
  • 18. Quah JT and Sriganesh M (2008) Real-time credit card fraud detection using computational intelligence. Expert Systems with Applications 35, 1721-32.
    Google ScholarLocate open access versionFindings
  • 19. Ravisankar P, Ravi V, Raghava Rao G, and Bose I (2011) Detection of financial statement fraud and feature selection using data mining techniques. Decision Support Systems 50, 491-500.
    Google ScholarLocate open access versionFindings
  • 20. Sánchez D, Vila M, Cerda L, and Serrano J-M (2009) Association rules applied to credit card fraud detection. Expert Systems with Applications 36, 3630-40.
    Google ScholarLocate open access versionFindings
  • 21. Sohl JE and Venkatachalam A (1995) A neural network approach to forecasting model selection. Information & Management 29, 297-303.
    Google ScholarLocate open access versionFindings
  • 22. Vatsa V, Sural S, and Majumdar AK (2005) A game-theoretic approach to credit card fraud detection. In Information Systems Security. Vol. pp. 263-76. Springer.
    Google ScholarLocate open access versionFindings
  • 23. Viaene S, Ayuso M, Guillen M, Van Gheel D, and Dedene G (2007) Strategies for detecting fraudulent claims in the automobile insurance industry. European Journal of Operational Research 176, 565-83.
    Google ScholarLocate open access versionFindings
  • 24. Whitrow C, Hand DJ, Juszczak P, Weston D, and Adams NM (2009) Transaction aggregation as a strategy for credit card fraud detection. Data Mining and Knowledge Discovery 18, 30-55.
    Google ScholarLocate open access versionFindings
  • 25. Wu SX and Banzhaf W (2008) Combatting financial fraud: a coevolutionary anomaly detection approach. In Proceedings of the 10th annual conference on Genetic and evolutionary computation. (ed.), Vol. pp. 1673-80, ACM.
    Google ScholarLocate open access versionFindings
  • 26. Yang W-S and Hwang S-Y (2006) A process-mining framework for the detection of healthcare fraud and abuse. Expert Systems with Applications 31, 56-68.
    Google ScholarLocate open access versionFindings
  • 27. Yeh I and Lien C-h (2009) The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients. Expert Systems with Applications 36, 2473-80.
    Google ScholarLocate open access versionFindings
  • 28. Yue D, Wu X, Wang Y, Li Y, and Chu C-H (2007) A review of data mining-based financial fraud detection research. In Wireless Communications, Networking and Mobile Computing, 2007. WiCom 2007. International Conference on. (ed.), Vol. pp. 5519-22, IEEE Press.
    Google ScholarLocate open access versionFindings
  • 29. Zhang D and Zhou L (2004) Discovering golden nuggets: data mining in financial application. Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on 34, 513-22.
    Google ScholarLocate open access versionFindings
  • 30. Zhou W and Kapoor G (2011) Detecting evolutionary financial statement fraud. Decision Support Systems 50, 570-5.
    Google ScholarLocate open access versionFindings
Your rating :
0

 

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科