A genetic algorithm approach to detecting temporal patterns indicative of financial statement fraud: Research Articles

Authors:
Bethany Hoogs;Thomas Kiehl;Christina Lacomb;Deniz Senturk
Affiliations:
GE Global Research Center, Niskayuna, NY 12309, USA;GE Global Research Center, Niskayuna, NY 12309, USA;GE Global Research Center, Niskayuna, NY 12309, USA;GE Global Research Center, Niskayuna, NY 12309, USA
Venue:
International Journal of Intelligent Systems in Accounting and Finance Management
Year:
2007

Citing 0
Cited 6

Exploring Fraudulent Financial Reporting with GHSOM

PAISI '09 Proceedings of the Pacific Asia Workshop on Intelligence and Security Informatics
A business process mining application for internal transaction fraud mitigation

Expert Systems with Applications: An International Journal
Beyond The Numbers: Mining The Annual Reports For Hidden Cues Indicative Of Financial Statement Fraud

International Journal of Intelligent Systems in Accounting and Finance Management
Forecasting fraudulent financial statements with committee of cost-sensitive decision tree classifiers

SETN'12 Proceedings of the 7th Hellenic conference on Artificial Intelligence: theories and applications
Estimating discretionary accruals using a grouping genetic algorithm

Expert Systems with Applications: An International Journal
Topological pattern discovery and feature extraction for fraudulent financial reporting

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

This study presents a genetic algorithm approach to detectingfinancial statement fraud. The study uses a sample comprising atarget class of 51 companies accused by the Securities and ExchangeCommission of improperly recognizing revenue and a peer class of339 companies matched on industry and size (revenue). Variablesinclude 76 comparative metrics, based on specific financial metricsand ratios that capture company performance in the context ofhistorical and industry performance, and nine companycharacteristics. Time-based patterns detected by the geneticalgorithm accurately classify 63% of the target class companies and95% of the peer class companies. Copyright © 2007 John Wiley& Sons, Ltd.