Credit Card Fraud Detection through Parenclitic Network Analysis
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 dia...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2018/5764370 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832548027199389696 |
|---|---|
| author | Massimiliano Zanin Miguel Romance Santiago Moral Regino Criado |
| author_facet | Massimiliano Zanin Miguel Romance Santiago Moral Regino Criado |
| author_sort | Massimiliano Zanin |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-f8da82b6b6534640854a446eda259e65 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2018-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-f8da82b6b6534640854a446eda259e652025-02-03T06:42:29ZengWileyComplexity1076-27871099-05262018-01-01201810.1155/2018/57643705764370Credit Card Fraud Detection through Parenclitic Network AnalysisMassimiliano Zanin0Miguel Romance1Santiago Moral2Regino Criado3Department of Computer Science, Faculty of Science and Technology, Universidade Nova de Lisboa, Lisboa, PortugalData, Networks and Cybersecurity Research Institute, Univ. Rey Juan Carlos, 28028 Madrid, SpainData, Networks and Cybersecurity Research Institute, Univ. Rey Juan Carlos, 28028 Madrid, SpainData, Networks and Cybersecurity Research Institute, Univ. Rey Juan Carlos, 28028 Madrid, SpainThe 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.http://dx.doi.org/10.1155/2018/5764370 |
| spellingShingle | Massimiliano Zanin Miguel Romance Santiago Moral Regino Criado Credit Card Fraud Detection through Parenclitic Network Analysis Complexity |
| title | Credit Card Fraud Detection through Parenclitic Network Analysis |
| title_full | Credit Card Fraud Detection through Parenclitic Network Analysis |
| title_fullStr | Credit Card Fraud Detection through Parenclitic Network Analysis |
| title_full_unstemmed | Credit Card Fraud Detection through Parenclitic Network Analysis |
| title_short | Credit Card Fraud Detection through Parenclitic Network Analysis |
| title_sort | credit card fraud detection through parenclitic network analysis |
| url | http://dx.doi.org/10.1155/2018/5764370 |
| work_keys_str_mv | AT massimilianozanin creditcardfrauddetectionthroughparencliticnetworkanalysis AT miguelromance creditcardfrauddetectionthroughparencliticnetworkanalysis AT santiagomoral creditcardfrauddetectionthroughparencliticnetworkanalysis AT reginocriado creditcardfrauddetectionthroughparencliticnetworkanalysis |