 |
    |
Forecasting Fraudulent Financial Statements with Committee of Cost-Sensitive Decision Tree Classifiers
Elias Zouboulidis1 and Sotiris Kotsiantis2
1Hellenic Open University, Greece
[email protected]
2Department of Mathematics, University of Patras, Greece
[email protected]
Abstract. This paper uses machine learning techniques in detecting firms that issue fraudulent financial statements (FFS) and deals with the identification of factors associated to FFS. To this end, a number of experiments have been conducted using representative learning algorithms, which were trained using a data set of 164 fraud and non-fraud Greek firms. A random committee of cost-sensitive decision tree classifiers is the best choice according to our experiments.
LNAI 7297, p. 57 ff.
[email protected]
© Springer-Verlag Berlin Heidelberg 2012