Detection of financial statement fraud and feature selection using data mining techniques

Recently, high profile cases of financial statement fraud have been dominating the news. This paper uses data mining techniques such as Multilayer Feed Forward Neural Network (MLFF), Support Vector Machines (SVM), Genetic Programming (GP), Group Method of Data Handling (GMDH), Logistic Regression (L...

Full description

Saved in:
Bibliographic Details
Published in:Decision Support Systems 2011, Vol.50 (2), p.491-500
Main Authors: Ravisankar, P., Ravi, V., Raghava Rao, G., Bose, I.
Format: Article
Language:English
Subjects:
Applied sciences
Artificial intelligence
Computer science
control theory
systems
Connectionism. Neural networks
Data mining
Data processing. List processing. Character string processing
Exact sciences and technology
Feature selection
Financial fraud detection
Financial statements
Fraud
Genetic algorithms
Genetics
Logistics
Memory organisation. Data processing
Multilayers
Neural networks
News
Operational research and scientific management
Operational research. Management science
Portfolio theory
Regression
Regression analysis
Software
Studies
Support vector machines
SVM
t-statistic
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, high profile cases of financial statement fraud have been dominating the news. This paper uses data mining techniques such as Multilayer Feed Forward Neural Network (MLFF), Support Vector Machines (SVM), Genetic Programming (GP), Group Method of Data Handling (GMDH), Logistic Regression (LR), and Probabilistic Neural Network (PNN) to identify companies that resort to financial statement fraud. Each of these techniques is tested on a dataset involving 202 Chinese companies and compared with and without feature selection. PNN outperformed all the techniques without feature selection, and GP and PNN outperformed others with feature selection and with marginally equal accuracies.
ISSN:0167-9236
1873-5797
DOI:10.1016/j.dss.2010.11.006