A distributed deep neural network model for credit card fraud detection

Yu-Tian Lei; Chao-Qun Ma; Yi-Shuai Ren; Xun-Qi Chen; Seema Narayan; Anh Ngoc Quang Huynh

doi:10.1016/j.frl.2023.104547

A distributed deep neural network model for credit card fraud detection

Yu-Tian Lei, Chao-Qun Ma, Yi-Shuai Ren, Xun-Qi Chen, Seema Narayan, Anh Ngoc Quang Huynh

Monash Business Sch DDLEE

Research output: Contribution to journal › Article › Research › peer-review

13 Citations (Scopus)

Abstract

This paper develops a distributed neural network model (DDNN) for detecting credit card fraud to federate credit card transaction data among different financial institutions. In addition, the convergence of the DDNN model is achieved by introducing a model optimization algorithm. The results demonstrate that (1) The use of a distributed model can avoid privacy leakage and data handling costs; (2) The DDNN model accelerates the convergence of the model through simultaneous computation of multiple clients; (3) The DDNN model detects credit card fraud better than multiple types of centralized models.

Original language	English
Article number	104547
Number of pages	7
Journal	Finance Research Letters
Volume	58
Issue number	Part C
DOIs	https://doi.org/10.1016/j.frl.2023.104547
Publication status	Published - Dec 2023

Keywords

Credit card fraud
Deep neural network model
Distributed model
Fraud detection

Access to Document

10.1016/j.frl.2023.104547

Cite this

@article{26e47d5c1edc46fd9185caae1a3ae2b4,

title = "A distributed deep neural network model for credit card fraud detection",

abstract = "This paper develops a distributed neural network model (DDNN) for detecting credit card fraud to federate credit card transaction data among different financial institutions. In addition, the convergence of the DDNN model is achieved by introducing a model optimization algorithm. The results demonstrate that (1) The use of a distributed model can avoid privacy leakage and data handling costs; (2) The DDNN model accelerates the convergence of the model through simultaneous computation of multiple clients; (3) The DDNN model detects credit card fraud better than multiple types of centralized models.",

keywords = "Credit card fraud, Deep neural network model, Distributed model, Fraud detection",

author = "Yu-Tian Lei and Chao-Qun Ma and Yi-Shuai Ren and Xun-Qi Chen and Seema Narayan and Huynh, {Anh Ngoc Quang}",

note = "Funding Information: This work is financially supported by the National Natural Science Foundation of China (No. 72104075 , 72274056 ), the National Social Science Fund of China (No. 19AZD014 , 21&ZD125 ), the Natural Science Foundation of Hunan Province (No. 2022JJ40106 ), and Hunan University Youth Talent Program. Publisher Copyright: {\textcopyright} 2023 Elsevier Inc.",

year = "2023",

month = dec,

doi = "10.1016/j.frl.2023.104547",

language = "English",

volume = "58",

journal = "Finance Research Letters",

issn = "1544-6123",

publisher = "Elsevier",

number = "Part C",

}

TY - JOUR

T1 - A distributed deep neural network model for credit card fraud detection

AU - Lei, Yu-Tian

AU - Ma, Chao-Qun

AU - Ren, Yi-Shuai

AU - Chen, Xun-Qi

AU - Narayan, Seema

AU - Huynh, Anh Ngoc Quang

N1 - Funding Information: This work is financially supported by the National Natural Science Foundation of China (No. 72104075 , 72274056 ), the National Social Science Fund of China (No. 19AZD014 , 21&ZD125 ), the Natural Science Foundation of Hunan Province (No. 2022JJ40106 ), and Hunan University Youth Talent Program. Publisher Copyright: © 2023 Elsevier Inc.

PY - 2023/12

Y1 - 2023/12

N2 - This paper develops a distributed neural network model (DDNN) for detecting credit card fraud to federate credit card transaction data among different financial institutions. In addition, the convergence of the DDNN model is achieved by introducing a model optimization algorithm. The results demonstrate that (1) The use of a distributed model can avoid privacy leakage and data handling costs; (2) The DDNN model accelerates the convergence of the model through simultaneous computation of multiple clients; (3) The DDNN model detects credit card fraud better than multiple types of centralized models.

AB - This paper develops a distributed neural network model (DDNN) for detecting credit card fraud to federate credit card transaction data among different financial institutions. In addition, the convergence of the DDNN model is achieved by introducing a model optimization algorithm. The results demonstrate that (1) The use of a distributed model can avoid privacy leakage and data handling costs; (2) The DDNN model accelerates the convergence of the model through simultaneous computation of multiple clients; (3) The DDNN model detects credit card fraud better than multiple types of centralized models.

KW - Credit card fraud

KW - Deep neural network model

KW - Distributed model

KW - Fraud detection

UR - http://www.scopus.com/inward/record.url?scp=85173743961&partnerID=8YFLogxK

U2 - 10.1016/j.frl.2023.104547

DO - 10.1016/j.frl.2023.104547

M3 - Article

AN - SCOPUS:85173743961

SN - 1544-6123

VL - 58

JO - Finance Research Letters

JF - Finance Research Letters

IS - Part C

M1 - 104547

ER -

A distributed deep neural network model for credit card fraud detection

Abstract

Keywords

Access to Document

Other files and links

Cite this