Authors:
Tales Matos
;
José Antonio F. de Macedo
;
José Maria Monteiro
and
Francesco Lettich
Affiliation:
Federal University of Ceará, Brazil
Keyword(s):
Fraud Detection, Data Mining, Tax Evasion, Feature Selection.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Data Mining
;
Databases and Information Systems Integration
;
Enterprise Information Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
Abstract:
Fiscal evasion represents a very serious issue in many developing countries. In this context, tax fraud detection constitutes a challenging problem, since fraudsters change frequently their behaviors to circumvent existing laws and devise new kinds of frauds. Detecting such changes proves to be challenging, since traditional classifiers fail to select features that exhibit frequent changes. In this paper we provide two contributions that try to tackle effectively the tax fraud detection problem: first, we introduce a novel feature selection algorithm, based on complex network techniques, that is able to capture determinant fraud indicators -- over time, this kind of indicators turn out to be more stable than new fraud indicators. Secondly, we propose a classifier that leverages the aforementioned algorithm to accurately detect tax frauds. In order to prove the validity of our contributions we provide an experimental evaluation, where we use real-world datasets, obtained from the Stat
e Treasury Office of Cear{\'a} (SEFAZ-CE), Brazil, to show how our method is able to outperform, in terms of F1 scores achieved, state-of-the-art approaches available in the literature.
(More)