An optimal weighted machine learning model for detecting financial fraud

Minghuan Shou; Xueqi Bao; Jie Yu

doi:10.1080/13504851.2021.1989367

An optimal weighted machine learning model for detecting financial fraud

Minghuan Shou, Xueqi Bao, Jie Yu

Research output: Journal Publication › Article › peer-review

7 Citations (Scopus)

Abstract

The purpose of this study is to predict enterprises’ financial fraud. After collecting financial data and employing feature selection methods, totally eight features are selected. We select two best-performance machine learning models according to five indicators including accuracy, recall, specificity, AUC and the misclassification cost. Besides, an optimal weighted machine learning model, based on the two best-performance models, is proposed and the results confirm its good performance in forecasting enterprises’ financial fraud.

Original language	English
Pages (from-to)	410-415
Number of pages	6
Journal	Applied Economics Letters
Volume	30
Issue number	4
Early online date	6 Oct 2021
DOIs	https://doi.org/10.1080/13504851.2021.1989367
Publication status	Published - 2023

Keywords

Financial fraud
feature selection
machine learning
weighted model

ASJC Scopus subject areas

Economics and Econometrics

Access to Document

10.1080/13504851.2021.1989367

Cite this

Shou, M., Bao, X., & Yu, J. (2023). An optimal weighted machine learning model for detecting financial fraud. Applied Economics Letters, 30(4), 410-415. https://doi.org/10.1080/13504851.2021.1989367

@article{e4d9b8bba5874a74a3a8b277bce48706,

title = "An optimal weighted machine learning model for detecting financial fraud",

abstract = "The purpose of this study is to predict enterprises{\textquoteright} financial fraud. After collecting financial data and employing feature selection methods, totally eight features are selected. We select two best-performance machine learning models according to five indicators including accuracy, recall, specificity, AUC and the misclassification cost. Besides, an optimal weighted machine learning model, based on the two best-performance models, is proposed and the results confirm its good performance in forecasting enterprises{\textquoteright} financial fraud.",

keywords = "Financial fraud, feature selection, machine learning, weighted model",

author = "Minghuan Shou and Xueqi Bao and Jie Yu",

note = "Publisher Copyright: {\textcopyright} 2021 Informa UK Limited, trading as Taylor & Francis Group.",

year = "2023",

doi = "10.1080/13504851.2021.1989367",

language = "English",

volume = "30",

pages = "410--415",

journal = "Applied Economics Letters",

issn = "1350-4851",

publisher = "Routledge",

number = "4",

}

TY - JOUR

T1 - An optimal weighted machine learning model for detecting financial fraud

AU - Shou, Minghuan

AU - Bao, Xueqi

AU - Yu, Jie

PY - 2023

Y1 - 2023

N2 - The purpose of this study is to predict enterprises’ financial fraud. After collecting financial data and employing feature selection methods, totally eight features are selected. We select two best-performance machine learning models according to five indicators including accuracy, recall, specificity, AUC and the misclassification cost. Besides, an optimal weighted machine learning model, based on the two best-performance models, is proposed and the results confirm its good performance in forecasting enterprises’ financial fraud.

AB - The purpose of this study is to predict enterprises’ financial fraud. After collecting financial data and employing feature selection methods, totally eight features are selected. We select two best-performance machine learning models according to five indicators including accuracy, recall, specificity, AUC and the misclassification cost. Besides, an optimal weighted machine learning model, based on the two best-performance models, is proposed and the results confirm its good performance in forecasting enterprises’ financial fraud.

KW - Financial fraud

KW - feature selection

KW - machine learning

KW - weighted model

UR - http://www.scopus.com/inward/record.url?scp=85116493944&partnerID=8YFLogxK

U2 - 10.1080/13504851.2021.1989367

DO - 10.1080/13504851.2021.1989367

M3 - Article

AN - SCOPUS:85116493944

SN - 1350-4851

VL - 30

SP - 410

EP - 415

JO - Applied Economics Letters

JF - Applied Economics Letters

IS - 4

ER -

An optimal weighted machine learning model for detecting financial fraud

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this