research-article

Fraud Detection under Multi-Sourced Extremely Noisy Annotations

Authors:

Chen GongAuthors Info & Claims

CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge Management

Pages 2497 - 2506

https://doi.org/10.1145/3459637.3482433

Published: 30 October 2021 Publication History

Abstract

Fraud detection in e-commerce, which is critical to protecting the capital safety of users and financial corporations, aims at determining whether an online transaction or other activity is fraudulent or not. This problem has been previously addressed by various fully supervised learning methods. However, the true labels for training a supervised fraud detection model are difficult to collect in many real-world cases. To circumvent this issue, a series of automatic annotation techniques are employed instead in generating multiple noisy annotations for each unknown activity. In order to utilize these low-quality, multi-sourced annotations in achieving reliable detection results, we propose an iterative two-staged fraud detection framework with multi-sourced extremely noisy annotations. In label aggregation stage, multi-sourced labels are integrated by voting with adaptive weights; and in label correction stage, the correctness of the aggregated labels are properly estimated with the help of a handful of exactly labeled data and the results are used to train a robust fraud detector. These two stages benefit from each other, and the iterative executions lead to steadily improved detection results. Therefore, our method is termed "Label Aggregation and Correction" (LAC). Experimentally, we collect millions of transaction records from Alipay in two different fraud detection scenarios, i.e., credit card theft and promotion abuse fraud. When compared with state-of-the-art counterparts, our method can achieve at least 0.019 and 0.117 improvements in terms of average AUC on the two collected datasets, which clearly demonstrate the effectiveness.

References

[1]

John Akhilomen. 2013. Data mining application for cyber credit-card fraud detection system. In Industrial Conference on Data Mining. Springer, 218--228.

Digital Library

[2]

Shadi Albarqouni, Christoph Baur, Felix Achilles, Vasileios Belagiannis, Stefanie Demirci, and Nassir Navab. 2016. Aggnet: deep learning from crowds for mitosis detection in breast cancer histology images. IEEE T-MI, Vol. 35, 5 (2016), 1313--1321.

[3]

John O Awoyemi, Adebayo O Adetunmbi, and Samuel A Oluwadare. 2017. Credit card fraud detection using machine learning techniques: A comparative analysis. In ICCNI. IEEE, 1--9.

[4]

Shai Ben-David, David Loker, Nathan Srebro, and Karthik Sridharan. 2012. Minimizing the misclassification error rate using a surrogate convex loss. In ICML.

Digital Library

[5]

Antonin Berthon, Bo Han, Gang Niu, Tongliang Liu, and Masashi Sugiyama. 2020. Confidence Scores Make Instance-dependent Label-noise Learning Possible. ArXiv Preprint ArXiv:2001.03772 (2020).

[6]

Siddhartha Bhattacharyya, Sanjeev Jha, Kurian Tharakunnel, and J Christopher Westland. 2011. Data mining for credit card fraud: A comparative study. Decision Support Systems, Vol. 50, 3 (2011), 602--613.

Digital Library

[7]

Christopher M Bishop. 2006. Pattern recognition and machine learning .springer.

Digital Library

[8]

Bernardo Branco, Pedro Abreu, Ana Sofia Gomes, Mariana SC Almeida, Jo ao Tiago Ascens ao, and Pedro Bizarro. 2020. Interleaved Sequence RNNs for Fraud Detection. In SIGKDD. 3101--3109.

[9]

Fabrizio Carcillo, Yann-Ael Le Borgne, Olivier Caelen, and Gianluca Bontempi. 2017. An assessment of streaming active learning strategies for real-life credit card fraud detection. In IEEE DSAA. IEEE, 631--639.

[10]

Fabrizio Carcillo, Yann-Aël Le Borgne, Olivier Caelen, and Gianluca Bontempi. 2018. Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization. International Journal of Data Science and Analytics, Vol. 5, 4 (2018), 285--300.

[11]

Nuno Carneiro, Goncalo Figueira, and Miguel Costa. 2017. A data mining based system for credit-card fraud detection in e-tail. Decision Support Systems, Vol. 95 (2017), 91--101.

Digital Library

[12]

Tianqi Chen and Carlos Guestrin. 2016. Xgboost: A scalable tree boosting system. In SIGKDD. 785--794.

Digital Library

[13]

Jiacheng Cheng, Tongliang Liu, Kotagiri Ramamohanarao, and Dacheng Tao. 2020. Learning with bounded instance-and label-dependent label noise. In ICML.

[14]

Alexander Philip Dawid and Allan M Skene. 1979. Maximum likelihood estimation of observer error-rates using the EM algorithm. Journal of the Royal Statistical Society: Series C (Applied Statistics), Vol. 28, 1 (1979), 20--28.

[15]

Daniel de Roux, Boris Perez, Andrés Moreno, Maria del Pilar Villamil, and César Figueroa. 2018. Tax fraud detection for under-reporting declarations using an unsupervised machine learning approach. In SIGKDD. 215--222.

Digital Library

[16]

Jun Du and Zhihua Cai. 2015. Modelling class noise with symmetric and asymmetric distributions. In AAAI.

Digital Library

[17]

Beno^it Frénay, Ata Kabán, et al. 2014. A comprehensive introduction to label noise. In Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning.

[18]

Jerome H Friedman. 2001. Greedy function approximation: a gradient boosting machine. Annals of Statistics (2001), 1189--1232.

[19]

Prasad Gabbur, Sharath Pankanti, Quanfu Fan, and Hoang Trinh. 2011. A pattern discovery approach to retail fraud detection. In SIGKDD. 307--315.

Digital Library

[20]

Jyoti R Gaikwad, Amruta B Deshmane, Harshada V Somavanshi, Snehal V Patil, and Rinku A Badgujar. 2014. Credit Card Fraud Detection using Decision Tree Induction Algorithm. IJITEE, Vol. 4, 6 (2014).

[21]

Matt W Gardner and SR Dorling. 1998. Artificial neural networks (the multilayer perceptron)-a review of applications in the atmospheric sciences. Atmospheric environment, Vol. 32, 14--15 (1998), 2627--2636.

[22]

Aritra Ghosh, Himanshu Kumar, and PS Sastry. 2017. Robust loss functions under label noise for deep neural networks. In AAAI. 1919--1925.

Digital Library

[23]

Aritra Ghosh, Naresh Manwani, and PS Sastry. 2015. Making risk minimization tolerant to label noise. Neurocomputing, Vol. 160 (2015), 93--107.

Digital Library

[24]

Jacob Goldberger and Ehud Ben-Reuven. 2016. Training deep neural-networks using a noise adaptation layer. (2016).

[25]

Chen Gong, Hong Shi, Tongliang Liu, Chuang Zhang, Jian Yang, and Dacheng Tao. 2019. Loss decomposition and centroid estimation for positive and unlabeled learning. IEEE T-PAMI, Vol. 43, 3 (2019), 918--932.

[26]

Chen Gong, Jian Yang, Jane J You, and Masashi Sugiyama. 2020. Centroid estimation with guaranteed efficiency: A general framework for weakly supervised learning. IEEE T-PAMI (2020).

[27]

David J Hand. 2009. Measuring classifier performance: a coherent alternative to the area under the ROC curve. ML, Vol. 77, 1 (2009), 103--123.

Digital Library

[28]

Takafumi Kanamori, Shohei Hido, and Masashi Sugiyama. 2009. A least-squares approach to direct importance estimation. JMLR, Vol. 10 (2009), 1391--1445.

Digital Library

[29]

Takafumi Kanamori, Taiji Suzuki, and Masashi Sugiyama. 2010. Theoretical analysis of density ratio estimation. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, Vol. 93, 4 (2010), 787--798.

[30]

Ashish Khetan, Zachary C Lipton, and Anima Anandkumar. 2018. Learning from noisy singly-labeled data. In ICLR.

[31]

Shikun Li, Shiming Ge, Yingying Hua, Chunhui Zhang, Hao Wen, Tengfei Liu, and Weiqiang Wang. 2020. Coupled-View Deep Classifier Learning from Multiple Noisy Annotators. In AAAI. 4667--4674.

[32]

Can Liu, Qiwei Zhong, Xiang Ao, Li Sun, Wangli Lin, Jinghua Feng, Qing He, and Jiayu Tang. 2020. Fraud Transactions Detection via Behavior Tree with Local Intention Calibration. In SIGKDD. 3035--3043.

[33]

Tongliang Liu and Dacheng Tao. 2015. Classification with noisy labels by importance reweighting. IEEE T-PAMI, Vol. 38, 3 (2015), 447--461.

Digital Library

[34]

Jorge M Lobo, Alberto Jiménez-Valverde, and Raimundo Real. 2008. AUC: a misleading measure of the performance of predictive distribution models. Global Ecology and Biogeography, Vol. 17, 2 (2008), 145--151.

[35]

Yijing Luo, Bo Han, and Chen Gong. 2020. A Bi-level Formulation for Label Noise Learning with Spectral Cluster Discovery. In IJCAI. 2605--2611.

[36]

Aditya Krishna Menon, Brendan Van Rooyen, and Nagarajan Natarajan. 2016. Learning from binary labels with instance-dependent corruption. ArXiv Preprint ArXiv:1605.00751 (2016).

[37]

Kaixiang Mo, Erheng Zhong, and Qiang Yang. 2013. Cross-task crowdsourcing. In SIGKDD. 677--685.

Digital Library

[38]

Nagarajan Natarajan, Inderjit S Dhillon, Pradeep K Ravikumar, and Ambuj Tewari. 2013. Learning with noisy labels. In NeurIPS. 1196--1204.

Digital Library

[39]

Curtis G Northcutt, Tailin Wu, and Isaac L Chuang. 2017. Learning with confident examples: Rank pruning for robust classification with noisy labels. In AAAI.

[40]

Giorgio Patrini, Alessandro Rozza, Aditya Krishna Menon, Richard Nock, and Lizhen Qu. 2017. Making deep neural networks robust to label noise: A loss correction approach. In CVPR. 1944--1952.

[41]

Alexander Ratner, Braden Hancock, Jared Dunnmon, Frederic Sala, Shreyash Pandey, and Christopher Ré. 2019. Training complex models with multi-task weak supervision. In AAAI, Vol. 33. 4763--4771.

[42]

Vikas C Raykar, Shipeng Yu, Linda H Zhao, Gerardo Hermosillo Valadez, Charles Florin, Luca Bogoni, and Linda Moy. 2010. Learning from crowds. JMLR, Vol. 11, 4 (2010).

Digital Library

[43]

Filipe Rodrigues, Francisco Pereira, and Bernardete Ribeiro. 2014. Gaussian process classification and active learning with multiple annotators. In ICML. 433--441.

Digital Library

[44]

Victor S Sheng, Foster Provost, and Panagiotis G Ipeirotis. 2008. Get another label? improving data quality and data mining using multiple, noisy labelers. In SIGKDD. 614--622.

Digital Library

[45]

https://github.com/dmlc/xgboost. 2020. XGBoost.

[46]

Andreas Veit, Neil Alldrin, Gal Chechik, Ivan Krasin, Abhinav Gupta, and Serge Belongie. 2017. Learning from noisy large-scale datasets with minimal supervision. In CVPR. 839--847.

[47]

Daixin Wang, Jianbin Lin, Peng Cui, Quanhui Jia, Zhen Wang, Yanming Fang, Quan Yu, Jun Zhou, Shuang Yang, and Yuan Qi. 2019. A Semi-supervised Graph Attentive Network for Financial Fraud Detection. In ICDM. IEEE, 598--607.

[48]

Haibo Wang, Chuan Zhou, Jia Wu, Weizhen Dang, Xingquan Zhu, and Jilong Wang. 2018. Deep structure learning for fraud detection. In ICDM. IEEE, 567--576.

[49]

Qizhou Wang, Bo Han, Tongliang Liu, Gang Niu, Jian Yang, and Chen Gong. 2021a. Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model. In AAAI. 10183--10191.

[50]

Qizhou Wang, Jiangchao Yao, Chen Gong, Tongliang Liu, Mingming Gong, Hongxia Yang, and Bo Han. 2021b. Learning with Group Noise. In AAAI. 10192--10200.

[51]

Yang Wei, Chen Gong, Shuo Chen, Tongliang Liu, Jian Yang, and Dacheng Tao. 2019. Harnessing side information for classification under label noise. IEEE T-NNLS, Vol. 31, 9 (2019), 3178--3192.

[52]

Peter Welinder, Steve Branson, Pietro Perona, and Serge J Belongie. 2010. The multidimensional wisdom of crowds. In NeurIPS. 2424--2432.

Digital Library

[53]

Jacob Whitehill, Ting-fan Wu, Jacob Bergsma, Javier R Movellan, and Paul L Ruvolo. 2009. Whose vote should count more: Optimal integration of labels from labelers of unknown expertise. In NeurIPS. 2035--2043.

Digital Library

[54]

Xiaobo Xia, Tongliang Liu, Nannan Wang, Bo Han, Chen Gong, Gang Niu, and Masashi Sugiyama. 2019. Are Anchor Points Really Indispensable in Label-Noise Learning?. In NeurIPS. 6838--6849.

Digital Library

[55]

Yan Yan, Rómer Rosales, Glenn Fung, Ramanathan Subramanian, and Jennifer Dy. 2014. Learning from multiple annotators with varying expertise. ML, Vol. 95, 3 (2014), 291--327.

Digital Library

[56]

Chuang Zhang, Chen Gong, Tengfei Liu, Xun Lu, Weiqiang Wang, and Jian Yang. 2020. Online Positive and Unlabeled Learning. In IJCAI. 2248--2254.

[57]

Chuang Zhang, Dexin Ren, Tongliang Liu, Jian Yang, and Chen Gong. 2019. Positive and Unlabeled Learning with Label Disambiguation. In IJCAI. 4250--4256.

Digital Library

[58]

Jing Zhang and Xindong Wu. 2018. Multi-label inference for crowdsourcing. In SIGKDD. 2738--2747.

Digital Library

Cited By

Park DSerra ESpezzano F(2024)Graph-theoretical Approach to Enhance Accuracy of Financial Fraud Detection Using Synthetic Tabular Data GenerationProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3680267(5467-5470)Online publication date: 21-Oct-2024
https://dl.acm.org/doi/10.1145/3627673.3680267
Guan WCao JZhao HGu YQian S(2024)WAKE: A Weakly Supervised Business Process Anomaly Detection Framework via a Pre-Trained AutoencoderIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2023.332241136:6(2745-2758)Online publication date: Jun-2024
https://doi.org/10.1109/TKDE.2023.3322411
Wang ZXie JNie FWang RJia YLiu S(2024)T-distributed Stochastic Neighbor Network for unsupervised representation learningNeural Networks10.1016/j.neunet.2024.106520179(106520)Online publication date: Nov-2024
https://doi.org/10.1016/j.neunet.2024.106520
Show More Cited By

Index Terms

Fraud Detection under Multi-Sourced Extremely Noisy Annotations
1. Information systems
  1. Information systems applications
    1. Data mining
      1. Data cleaning

Recommendations

Noisy multi-label semi-supervised dimensionality reduction
Highlights
- A new semi-supervised and label noise-tolerant multi-label dimensionality reduction method.
Abstract
Noisy labeled data represent a rich source of information that often are easily accessible and cheap to obtain, but label noise might also have many negative consequences if not accounted for. How to fully utilize noisy labels has been ...
Research on Credit Card Fraud Detection Model Based on Distance Sum
JCAI '09: Proceedings of the 2009 International Joint Conference on Artificial Intelligence

Along with increasing credit cards and growing trade volume in China, credit card fraud rises sharply. How to enhance the detection and prevention of credit card fraud becomes the focus of risk control of banks. This paper proposes a credit card fraud ...
Identifying noisy labels with a transductive semi-supervised leave-one-out filter
Highlights
- Semi-supervised classifiers are susceptible to label noise.
- Our method (LGC_...
Abstract
Obtaining data with meaningful labels is often costly and error-prone. In this situation, semi-supervised learning (SSL) approaches are interesting, as they leverage assumptions about the unlabeled data to make up for the limited ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge Management

October 2021

4966 pages

ISBN:9781450384469

DOI:10.1145/3459637

General Chairs:
Gianluca Demartini
The University of Queensland, Australia
,
Guido Zuccon
The University of Queensland, Australia
,
Program Chairs:
J. Shane Culpepper
RMIT University, Australia
,
Zi Huang
The University of Queensland, Australia
,
Hanghang Tong
University of Illinois at Urbana-Champaign, USA

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 30 October 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

NSF of China
the Ant Financial Science Funds for Security Research of Ant Financial
HKBU CSD Departmental Incentive Grant
Fundamental Research Funds for the Central Universities
the RGC Early Career Scheme

Conference

CIKM '21

Sponsor:

CIKM '21: The 30th ACM International Conference on Information and Knowledge Management

November 1 - 5, 2021

Queensland, Virtual Event, Australia

Acceptance Rates

Overall Acceptance Rate 1,861 of 8,427 submissions, 22%

Upcoming Conference

CIKM '25

Sponsor:
sigir
sigir

The 34th ACM International Conference on Information and Knowledge Management

November 10 - 14, 2025

Seoul , Republic of Korea

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
230
Total Downloads

Downloads (Last 12 months)38
Downloads (Last 6 weeks)7

Reflects downloads up to 17 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Park DSerra ESpezzano F(2024)Graph-theoretical Approach to Enhance Accuracy of Financial Fraud Detection Using Synthetic Tabular Data GenerationProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3680267(5467-5470)Online publication date: 21-Oct-2024
https://dl.acm.org/doi/10.1145/3627673.3680267
Guan WCao JZhao HGu YQian S(2024)WAKE: A Weakly Supervised Business Process Anomaly Detection Framework via a Pre-Trained AutoencoderIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2023.332241136:6(2745-2758)Online publication date: Jun-2024
https://doi.org/10.1109/TKDE.2023.3322411
Wang ZXie JNie FWang RJia YLiu S(2024)T-distributed Stochastic Neighbor Network for unsupervised representation learningNeural Networks10.1016/j.neunet.2024.106520179(106520)Online publication date: Nov-2024
https://doi.org/10.1016/j.neunet.2024.106520
Somavarapu TSingh ASingh MPandey SVerma SAgarwal K(2024)Event-Aware Multi-component (EMl) Loss for Fraud DetectionPattern Recognition10.1007/978-3-031-78398-2_7(105-119)Online publication date: 2-Dec-2024
https://doi.org/10.1007/978-3-031-78398-2_7
Chen LWang LXu JChen SWang WZhao WLi QWang LFrommholz IHopfgartner FLee MOakes MLalmas MZhang MSantos R(2023)Knowledge-inspired Subdomain Adaptation for Cross-Domain Knowledge TransferProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3614946(234-244)Online publication date: 21-Oct-2023
https://dl.acm.org/doi/10.1145/3583780.3614946
Dang QNguyen N(2022)Evaluating the Contribution of Relationship Information in Detecting Fraud Using Graph Neural NetworksInventive Communication and Computational Technologies10.1007/978-981-19-4960-9_65(865-875)Online publication date: 14-Nov-2022
https://doi.org/10.1007/978-981-19-4960-9_65

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten