DocumentCode :
3303200
Title :
Detecting Fraud in Financial Reports
Author :
Skillicorn, D.B. ; Purda, L.
Author_Institution :
Sch. of Comput., Queen´´s Univ., Kingston, ON, Canada
fYear :
2012
fDate :
22-24 Aug. 2012
Firstpage :
7
Lastpage :
13
Abstract :
Fraud in public companies has a large financial impact, and yet is only weakly detected by those who look for it, many incidents have been detected only when whistleblowers have come forward. We examine the problem of detecting fraud from the textual component of the quarterly and annual reports that public companies are required to file. Using an empirically derived set of words, we achieve prediction accuracy up to 88% on a per-report basis. Frauds rarely involve only a single quarter, so it is actually more useful to consider prediction performance on a per-incident basis. The truthfulness probability of our measure shows consistent decreases in the quarters leading up to a fraud, creating opportunities for proactive enforcement. We also compare the prediction performance of our word list with Pennebaker´s deception model, and with a set of fixed lists suggested in the literature, only two of which have any predictive power.
Keywords :
business data processing; company reports; financial data processing; fraud; probability; public finance; security of data; Pennebaker deception model; annual report; financial impact; financial report; fraud detection; prediction accuracy; prediction performance; public company; quarterly report; textual component; truthfulness probability; Accuracy; Companies; Labeling; Predictive models; Support vector machines; Writing; Management discussion and analysis; SEC; deception; financial fraud; fixed word lists; prediction;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligence and Security Informatics Conference (EISIC), 2012 European
Conference_Location :
Odense
Print_ISBN :
978-1-4673-2358-1
Type :
conf
DOI :
10.1109/EISIC.2012.8
Filename :
6298880
Link To Document :
بازگشت