Collective Fraud Detection Capturing Inter-Transaction Dependency

Bokai Cao, Mia Mao, Siim Viidu, Philip Yu
Proceedings of the KDD 2017: Workshop on Anomaly Detection in Finance, PMLR 71:66-75, 2018.

Abstract

In e-commerce, different payment transactions have different levels of risk. Risk is generally higher for digital goods, but it also differs based on product and its popularity, the offer type (packaged game, virtual currency to a game or subscription service), storefront and geography. Existing fraud policies and models make decisions independently for each transaction based on transaction attributes, payment velocities, user characteristics, and other relevant information. However, suspicious transactions may still evade detection and hence we propose a novel approach leveraging a graph based perspective to uncover relationships among suspicious transactions, i.e., inter-transaction dependency. Our focus is to detect suspicious transactions by capturing common fraudulent behaviors that would not be considered suspicious when being considered in isolation. In this paper, we present HitFraud that leverages heterogeneous information networks for collective fraud detection by exploring correlated and fast evolving fraudulent behaviors. First, a heterogeneous information network is designed to link entities of interest in the transaction database via different semantics. Then, graph based features are efficiently discovered from the network exploiting the concept of meta-paths, and decisions on frauds are made collectively on test instances. Experiments on real-world payment transaction data from Electronic Arts demonstrate that the prediction performance is effectively boosted by HitFraud where the computation of meta-path based features is largely optimized. Notably, recall can be improved up to 7.93% and F-score 4.62% compared to baselines.

Cite this Paper

BibTeX
@InProceedings{pmlr-v71-cao18a, title = {Collective Fraud Detection Capturing Inter-Transaction Dependency}, author = {Cao, Bokai and Mao, Mia and Viidu, Siim and Yu, Philip}, booktitle = {Proceedings of the KDD 2017: Workshop on Anomaly Detection in Finance}, pages = {66--75}, year = {2018}, editor = {Anandakrishnan, Archana and Kumar, Senthil and Statnikov, Alexander and Faruquie, Tanveer and Xu, Di}, volume = {71}, series = {Proceedings of Machine Learning Research}, month = {14 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v71/cao18a/cao18a.pdf}, url = {https://proceedings.mlr.press/v71/cao18a.html}, abstract = {In e-commerce, different payment transactions have different levels of risk. Risk is generally higher for digital goods, but it also differs based on product and its popularity, the offer type (packaged game, virtual currency to a game or subscription service), storefront and geography. Existing fraud policies and models make decisions independently for each transaction based on transaction attributes, payment velocities, user characteristics, and other relevant information. However, suspicious transactions may still evade detection and hence we propose a novel approach leveraging a graph based perspective to uncover relationships among suspicious transactions, i.e., inter-transaction dependency. Our focus is to detect suspicious transactions by capturing common fraudulent behaviors that would not be considered suspicious when being considered in isolation. In this paper, we present HitFraud that leverages heterogeneous information networks for collective fraud detection by exploring correlated and fast evolving fraudulent behaviors. First, a heterogeneous information network is designed to link entities of interest in the transaction database via different semantics. Then, graph based features are efficiently discovered from the network exploiting the concept of meta-paths, and decisions on frauds are made collectively on test instances. Experiments on real-world payment transaction data from Electronic Arts demonstrate that the prediction performance is effectively boosted by HitFraud where the computation of meta-path based features is largely optimized. Notably, recall can be improved up to 7.93% and F-score 4.62% compared to baselines.} }
Endnote
%0 Conference Paper %T Collective Fraud Detection Capturing Inter-Transaction Dependency %A Bokai Cao %A Mia Mao %A Siim Viidu %A Philip Yu %B Proceedings of the KDD 2017: Workshop on Anomaly Detection in Finance %C Proceedings of Machine Learning Research %D 2018 %E Archana Anandakrishnan %E Senthil Kumar %E Alexander Statnikov %E Tanveer Faruquie %E Di Xu %F pmlr-v71-cao18a %I PMLR %P 66--75 %U https://proceedings.mlr.press/v71/cao18a.html %V 71 %X In e-commerce, different payment transactions have different levels of risk. Risk is generally higher for digital goods, but it also differs based on product and its popularity, the offer type (packaged game, virtual currency to a game or subscription service), storefront and geography. Existing fraud policies and models make decisions independently for each transaction based on transaction attributes, payment velocities, user characteristics, and other relevant information. However, suspicious transactions may still evade detection and hence we propose a novel approach leveraging a graph based perspective to uncover relationships among suspicious transactions, i.e., inter-transaction dependency. Our focus is to detect suspicious transactions by capturing common fraudulent behaviors that would not be considered suspicious when being considered in isolation. In this paper, we present HitFraud that leverages heterogeneous information networks for collective fraud detection by exploring correlated and fast evolving fraudulent behaviors. First, a heterogeneous information network is designed to link entities of interest in the transaction database via different semantics. Then, graph based features are efficiently discovered from the network exploiting the concept of meta-paths, and decisions on frauds are made collectively on test instances. Experiments on real-world payment transaction data from Electronic Arts demonstrate that the prediction performance is effectively boosted by HitFraud where the computation of meta-path based features is largely optimized. Notably, recall can be improved up to 7.93% and F-score 4.62% compared to baselines.
APA
Cao, B., Mao, M., Viidu, S. & Yu, P.. (2018). Collective Fraud Detection Capturing Inter-Transaction Dependency. Proceedings of the KDD 2017: Workshop on Anomaly Detection in Finance, in Proceedings of Machine Learning Research 71:66-75 Available from https://proceedings.mlr.press/v71/cao18a.html.

Related Material