Credit card fraud detection through parenclitic network analysis

DOI10.1155/2018/5764370MaRDI QIDQ1649519zbMATH OpenOpenAlexWikidataFDO

Authors Massimiliano Zanin, Miguel Romance, Santiago Moral, Regino Criado

Publication date 6 July 2018

Published in Complexity (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/1706.01953

zbMATH Keywords

credit card transactionsdata analysisfraudshybrid data mining/complex network classification algorithmneural network-based classification algorithm

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Actuarial science and mathematical finance (91G99) Neural networks for/in biological studies, artificial life and related topics (92B20) Authentication, digital signatures and secret sharing (94A62)

Abstract: The detection of frauds in credit card transactions is a major topic in financial research, of profound economic implications. While this has hitherto been tackled through data analysis techniques, the resemblances between this and other problems, like the design of recommendation systems and of diagnostic / prognostic medical tools, suggest that a complex network approach may yield important benefits. In this contribution we present a first hybrid data mining / complex network classification algorithm, able to detect illegal instances in a real card transaction data set. It is based on a recently proposed network reconstruction algorithm that allows creating representations of the deviation of one instance from a reference group. We show how the inclusion of features extracted from the network data representation improves the score obtained by a standard, neural network-based classification algorithm; and additionally how this combined approach can outperform a commercial fraud detection system in specific operation niches. Beyond these specific results, this contribution represents a new example on how complex networks and data mining can be integrated as complementary tools, with the former providing a view to data beyond the capabilities of the latter.

Review text

Summary: The detection of frauds in credit card transactions is a major topic in financial research, of profound economic implications. While this has hitherto been tackled through data analysis techniques, the resemblances between this and other problems, like the design of recommendation systems and of diagnostic/prognostic medical tools, suggest that a complex network approach may yield important benefits. In this paper, we present a first hybrid data mining/complex network classification algorithm, able to detect illegal instances in a real card transaction data set. It is based on a recently proposed network reconstruction algorithm that allows creating representations of the deviation of one instance from a reference group. We show how the inclusion of features extracted from the network data representation improves the score obtained by a standard, neural network-based classification algorithm and additionally how this combined approach can outperform a commercial fraud detection system in specific operation niches. Beyond these specific results, this contribution represents a new example on how complex networks and data mining can be integrated as complementary tools, with the former providing a view to data beyond the capabilities of the latter.

Recommendations

• Advances in Neural Networks – ISNN 2005
• Plastic card fraud detection using peer group analysis
• Off-the-peg and bespoke classifiers for fraud detection
• Mining Personal Banking Data to Detect Fraud
• scientific article; zbMATH DE number 1927180

Cites work

• Bayesian network classifiers
• Complex networks: structure and dynamics
• Exploring complex networks
• Harmony in the small-world
• Statistical mechanics of complex networks
• Support-vector networks
• The elements of statistical learning. Data mining, inference, and prediction
• The self-organizing map

Cited in

(7)

• A blockwise network autoregressive model with application for fraud detection
• scientific article; zbMATH DE number 1927180 (Why is no real title available?)
• Advances in Neural Networks – ISNN 2005
• Advances in Neural Networks – ISNN 2005
• Competitor identification with memory in a dynamic financial transaction network
• Network analytics for insurance fraud detection: a critical case study
• Plastic card fraud detection using peer group analysis

Describes a project that uses

Uses Software

• KNIME

This page was built for publication: Credit card fraud detection through parenclitic network analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1649519)