Advancing financial risk management: A transparent framework for effective fraud detection

Wenjuan Li; Xinghua Liu; Junqi Su; Tianxiang Cui

doi:10.1016/j.frl.2025.106865

Advancing financial risk management: A transparent framework for effective fraud detection

Wenjuan Li, Xinghua Liu, Junqi Su, Tianxiang Cui^*

^*Corresponding author for this work

Department of Information Systems

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

12 Downloads (CityUHK Scholars)

Abstract

Robust financial fraud detection is crucial for protecting assets and maintaining financial system integrity. Traditional models lack flexibility, while machine learning models are often complex and difficult to interpret. We propose an XGB-GP framework that combines Extreme Gradient Boosting (XGB) and Genetic Programming (GP) to create interpretable models, enhancing fraud detection. Our framework highlights the effectiveness of the financial indicator “Total Liabilities/Operating Costs” and outperforms traditional and machine learning models in detecting fraud, as demonstrated through analysis of data from the CSMAR database of Chinese publicly listed companies.
© 2025 The Authors.

Original language	English
Article number	106865
Journal	Finance Research Letters
Volume	75
Online published	1 Feb 2025
DOIs	https://doi.org/10.1016/j.frl.2025.106865
Publication status	Published - Apr 2025

Funding

This work was supported by the Ningbo Natural Science Foundation (2023J194), University of Nottingham Ningbo China Education Foundation (LDS202303), Basic and Commonweal Programme of Zhejiang Natural Science Foundation (LY24F020006), Ningbo Government (Project ID 2021B-008-C) and The Philosophy and Social Science Planned Research Project of Zhejiang Province (24NDJC240YBM).

Research Keywords

Financial fraud detection
Financial indicators
Explainable model

Publisher's Copyright Statement

This full text is made available under CC-BY-NC 4.0. https://creativecommons.org/licenses/by-nc/4.0/

Access Output

10.1016/j.frl.2025.106865

267753537.pdfFinal Published version, 980 KBLicence: CC BY-NC

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{768e35127bd94c6791020334145e019f,

title = "Advancing financial risk management: A transparent framework for effective fraud detection",

abstract = "Robust financial fraud detection is crucial for protecting assets and maintaining financial system integrity. Traditional models lack flexibility, while machine learning models are often complex and difficult to interpret. We propose an XGB-GP framework that combines Extreme Gradient Boosting (XGB) and Genetic Programming (GP) to create interpretable models, enhancing fraud detection. Our framework highlights the effectiveness of the financial indicator “Total Liabilities/Operating Costs” and outperforms traditional and machine learning models in detecting fraud, as demonstrated through analysis of data from the CSMAR database of Chinese publicly listed companies.{\textcopyright} 2025 The Authors.",

keywords = "Financial fraud detection, Financial indicators, Explainable model",

author = "Wenjuan Li and Xinghua Liu and Junqi Su and Tianxiang Cui",

year = "2025",

month = apr,

doi = "10.1016/j.frl.2025.106865",

language = "English",

volume = "75",

journal = "Finance Research Letters",

issn = "1544-6123",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Advancing financial risk management

T2 - A transparent framework for effective fraud detection

AU - Li, Wenjuan

AU - Liu, Xinghua

AU - Su, Junqi

AU - Cui, Tianxiang

PY - 2025/4

Y1 - 2025/4

N2 - Robust financial fraud detection is crucial for protecting assets and maintaining financial system integrity. Traditional models lack flexibility, while machine learning models are often complex and difficult to interpret. We propose an XGB-GP framework that combines Extreme Gradient Boosting (XGB) and Genetic Programming (GP) to create interpretable models, enhancing fraud detection. Our framework highlights the effectiveness of the financial indicator “Total Liabilities/Operating Costs” and outperforms traditional and machine learning models in detecting fraud, as demonstrated through analysis of data from the CSMAR database of Chinese publicly listed companies.© 2025 The Authors.

AB - Robust financial fraud detection is crucial for protecting assets and maintaining financial system integrity. Traditional models lack flexibility, while machine learning models are often complex and difficult to interpret. We propose an XGB-GP framework that combines Extreme Gradient Boosting (XGB) and Genetic Programming (GP) to create interpretable models, enhancing fraud detection. Our framework highlights the effectiveness of the financial indicator “Total Liabilities/Operating Costs” and outperforms traditional and machine learning models in detecting fraud, as demonstrated through analysis of data from the CSMAR database of Chinese publicly listed companies.© 2025 The Authors.

KW - Financial fraud detection

KW - Financial indicators

KW - Explainable model

UR - http://www.scopus.com/inward/record.url?scp=85216651765&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85216651765&origin=recordpage

U2 - 10.1016/j.frl.2025.106865

DO - 10.1016/j.frl.2025.106865

M3 - RGC 21 - Publication in refereed journal

SN - 1544-6123

VL - 75

JO - Finance Research Letters

JF - Finance Research Letters

M1 - 106865

ER -

Advancing financial risk management: A transparent framework for effective fraud detection

Abstract

Funding

Research Keywords

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this