1,520 Hits in 4.7 sec

A Semi-Supervised Graph Attentive Network for Financial Fraud Detection

Daixin Wang, Yuan Qi, Jianbin Lin, Peng Cui, Quanhui Jia, Zhen Wang, Yanming Fang, Quan Yu, Jun Zhou, Shuang Yang
2019 2019 IEEE International Conference on Data Mining (ICDM)  
To address the problem, we expand the labeled data through their social relations to get the unlabeled data and propose a semi-supervised attentive graph neural network, namedSemiGNN to utilize the multi-view  ...  With the rapid growth of financial services, fraud detection has been a very important problem to guarantee a healthy environment for both users and providers.  ...  Then we propose a semi-supervised graph neural network to simultaneously model the multiview information within network to do fraud detection.  ... 
doi:10.1109/icdm.2019.00070 dblp:conf/icdm/WangQL0JWFYZY19 fatcat:6nmk42i4rrbcljhw66vggr47qq

A state of the art survey of data mining-based fraud detection and credit scoring

Xun Zhou, Sicong Cheng, Meng Zhu, Chengkun Guo, Sida Zhou, Peng Xu, Zhenghua Xue, Weishi Zhang, Nader Asnafi
2018 MATEC Web of Conferences  
The goal of this paper is to provide a dense review of up-to-date techniques for fraud detection and credit scoring, a general analysis on the results achieved and upcoming challenges for further researches  ...  In this survey we focus on a state of the art survey of recently developed data mining techniques for fraud detection and credit scoring.  ...  and semi-supervised learning methods we presented here is graph-based semi-supervised learning.  ... 
doi:10.1051/matecconf/201818903002 fatcat:iri4vifvjzfpbgvof6qgqlfyvu

Financial Crime Fraud Detection Using Graph Computing: Application Considerations Outlook [article]

E. Kurshan, H. Shen, H.Yu
2021 arXiv   pre-print
Graph neural networks and emerging adaptive solutions provide compelling opportunities for the future of fraud and financial crime detection.  ...  In this new landscape, traditional fraud detection approaches such as rule-based engines have largely become ineffective.  ...  [45] . 3) Supervised and Unsupervised Sub-Graph Analysis: Subgraph analysis and mining analyzes the local graph patterns through supervised as well as semi-or unsupervised learning [46] , [47] .  ... 
arXiv:2103.01854v1 fatcat:3f624eyqyzf2tfcjyifyztbwey

Social Fraud Detection Review: Methods, Challenges and Analysis [article]

Saeedreza Shehnepoor, Roberto Togneri, Wei Liu, Mohammed Bennamoun
2021 arXiv   pre-print
The supervised approaches for fraud detection are introduced and categorized into two sub-categories; classical, and deep learning.  ...  With this framework, a comprehensive overview of approaches is presented including supervised, semi-supervised, and unsupervised learning.  ...  Recently, graph-based techniques have shown a significant improvement as a semi-supervised approach to fraud detection.  ... 
arXiv:2111.05645v1 fatcat:qp3zuv74lbaq3hw2ajxm6lfkim

Graph Computing for Financial Crime and Fraud Detection: Trends, Challenges and Outlook [article]

E.Kurshan, H. Shen
2021 arXiv   pre-print
Graph-based techniques provide unique solution opportunities for financial crime detection.  ...  As a result, traditional fraud detection approaches such as rule-based systems have largely become ineffective.  ...  Supervised and Sub-Graph Analysis Sub-graph analysis and mining analyzes the local graph patterns through supervised as well as semi-or unsupervised learning [70] , [71] .  ... 
arXiv:2103.03227v1 fatcat:5ztiqqbtxvfuhmh5qe6vd354tm

Improving Fraud Detection via Hierarchical Attention-based Graph Neural Network [article]

Yajing Liu, Zhengya Sun, Wensheng Zhang
2022 arXiv   pre-print
In this paper, we propose a Hierarchical Attention-based Graph Neural Network (HA-GNN) for fraud detection, which incorporates weighted adjacency matrices across different relations against camouflage.  ...  Graph neural networks (GNN) have emerged as a powerful tool for fraud detection tasks, where fraudulent nodes are identified by aggregating neighbor information via different relations.  ...  This paper employs the attention mechanism for fraud detection with camouflage. Graph Fraud Detection Graph algorithms have long been considered as important tools in fraud detection.  ... 
arXiv:2202.06096v2 fatcat:i7df46zer5dipgovmqxgc4azri

A Review on Graph Neural Network Methods in Financial Applications

Jianian Wang, Sheng Zhang, Yanghua Xiao, Rui Song
2022 Journal of Data Science  
We first categorize the commonly-used financial graphs and summarize the feature processing step for each node.  ...  Among the graph modeling technologies, graph neural network (GNN) models are able to handle the complex graph structure and achieve great performance and thus could be used to solve financial tasks.  ...  Gcnext: Graph convolutional network with expanded balance theory for fraudulent user detection.  ... 
doi:10.6339/22-jds1047 fatcat:lpkkobcferal3p7l5wanydm7ay

On some studies of Fraud Detection Pipeline and related issues from the scope of Ensemble Learning and Graph-based Learning [article]

Tuan Tran
2022 arXiv   pre-print
graph-based semi-supervised learning to detect fraudulent transactions.  ...  Fraud Detection Pipeline is a potential backbone of the system and is easy to be extended or upgraded, ii) when to update models in our system (and keep the accuracy stable) in order to reduce the cost  ...  An Mai for his supervision and interesting discussions on several research topics. A great thank you also goes to Loc Tran who helps me complete this thesis.  ... 
arXiv:2205.04626v1 fatcat:g4b4xkuoobh37b4wunh3tbhn3e

Fraud Detection in Online Product Review Systems via Heterogeneous Graph Transformer

Songkai Tang, Luhua Jin, Fan Cheng
2021 IEEE Access  
Traditional fraud detection algorithm mainly utilizes rule-based methods, which is insufficient for the rich user interactions and graph-structured data.  ...  Alternatively, we propose a new model named Fraud Aware Heterogeneous Graph Transformer(FAHGT), to address camouflages and inconsistency problems in a unified manner.  ...  The detector f is trained based on the labeled node information in a semi-supervised manner. For example, the node could be an account in a transaction system or a user in a social network.  ... 
doi:10.1109/access.2021.3084924 fatcat:wzzwnmdptnfm5hvarripls7heu

Deep learning and explainable artificial intelligence techniques applied for detecting money laundering – a critical review

Dattatray V. Kute, Biswajeet Pradhan, Nagesh Shukla, Abdullah Alamri
2021 IEEE Access  
Money laundering has been a global issue for decades, which is one of the major threat for economy and society.  ...  Key findings of the review are, researchers have preferred variants of Convolutional Neural Networks, and AutoEncoder; graph deep learning together with natural language processing is emerging as an important  ...  Using escalated alerts and SMRs as a label data, a semi-supervised learning model predicts the suspiciousness of a given node and potential bad actors in the transaction network based on the direct or  ... 
doi:10.1109/access.2021.3086230 fatcat:n4wwkfoiaff5rjpelnddtcruwu

Intelligent Fraud Detection in Financial Statements using Machine Learning and Data Mining: A Systematic Literature Review

Matin N. Ashtiani, Bijan Raahemi
2021 IEEE Access  
heuristic methods for anomaly (fraud) detection.  ...  We present the key issues, gaps, and limitations in the area of fraud detection in financial statements and suggest areas for future research.  ...  Taking a combination of supervised and unsupervised techniques, previously unseen types of suspicious behaviors could be detected in a manner called semi-supervised learning methods [40] .  ... 
doi:10.1109/access.2021.3096799 fatcat:6nzhyjlcm5dm5gwbn2njfr5voq

Quick survey of graph-based fraud detection methods [article]

Paul Irofti, Andrei Patrascu, Andra Baltoiu
2021 arXiv   pre-print
We present a survey on anomaly detection techniques used for fraud detection that exploit both the graph structure underlying the data and the contextual information contained in the attributes.  ...  In these networks, fraudulent behaviour may appear as a distinctive graph edge, such as spam message, a node or a larger subgraph structure, such as when a group of clients engage in money laundering schemes  ...  A different formulation, that is suited for online, semi-supervised applications, has been tested on the task of detecting malware files [24] .  ... 
arXiv:1910.11299v3 fatcat:zyupd4ezxrgw3f7g5utzihy6qi

Financial Cybercrime: A Comprehensive Survey of Deep Learning Approaches to Tackle the Evolving Financial Crime Landscape

Jack Nicholls, Aditya Kuppa, Nhien-An Le-Khac
2021 IEEE Access  
Qi, “Infdetect: A large scale graph-based fraud detection system actions from a network perspective: An overview,” Journal of Network for e-commerce insurance,  ...  Available: egat: A temporal edge enhanced graph attention network for tax evasion detection,” Proceedings - 2020 IEEE International  ... 
doi:10.1109/access.2021.3134076 fatcat:lm2upcaoabbnbie6r4sfzhjh4y

Machine Learning for Financial Risk Management: A Survey

Akib Mashrur, Wei Luo, Nayyar A. Zaidi, Antonio Robles-Kelly
2020 IEEE Access  
Recently, semi-supervised graph-based networks have been implemented to address the problem of few labelled examples in fraud detection datasets [186] .  ...  Graph neural networks have been applied in financial fraud detection tasks [65] , [66] . IV.  ... 
doi:10.1109/access.2020.3036322 fatcat:44z5jx3b2ff5xc6pcw3pwniyua

Anomaly Detection in Finance: Editors' Introduction

Archana Anandakrishnan, Senthil Kumar, Alexander R. Statnikov, Tanveer A. Faruquie, Di Xu
2017 Knowledge Discovery and Data Mining  
Several new ideas are emerging to tackle this challenge, including semi-supervised learning methods, deep learning based approaches and network/graph based solutions.  ...  The authors Cao et al. (2017) present a system to detect fraud by capturing common fraudulent behavior in networks.  ... 
dblp:conf/kdd/AnandakrishnanK17 fatcat:2qdx5u2exnfwvc5a73phvjsjfm
« Previous Showing results 1 — 15 out of 1,520 results