Enhanced detection of accounting fraud using a CNN-LSTM-Attention model optimized by Sparrow search

The detection of corporate accounting fraud is a critical challenge in the financial industry, where traditional models such as neural networks, logistic regression, and support vector machines often fall short in achieving high accuracy due to the complex and evolving nature of fraudulent activitie...

Full description

Saved in:
Bibliographic Details
Main Authors: Peifeng Wu, Yaqiang Chen
Format: Article
Language:English
Published: PeerJ Inc. 2024-11-01
Series:PeerJ Computer Science
Subjects:
Online Access:https://peerj.com/articles/cs-2532.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850065172974010368
author Peifeng Wu
Yaqiang Chen
author_facet Peifeng Wu
Yaqiang Chen
author_sort Peifeng Wu
collection DOAJ
description The detection of corporate accounting fraud is a critical challenge in the financial industry, where traditional models such as neural networks, logistic regression, and support vector machines often fall short in achieving high accuracy due to the complex and evolving nature of fraudulent activities. This paper proposes an enhanced approach to fraud detection by integrating convolutional neural networks (CNN) and long short-term memory (LSTM) networks, complemented by an attention mechanism to prioritize relevant features. To further improve the model’s performance, the sparrow search algorithm (SSA) is employed for parameter optimization, ensuring the best configuration of the CNN-LSTM-Attention framework. Experimental results demonstrate that the proposed model outperforms conventional methods across various evaluation metrics, offering superior accuracy and robustness in recognizing fraudulent patterns in corporate accounting data.
format Article
id doaj-art-e8c760ce34834d5780d1c7e232c3b79c
institution DOAJ
issn 2376-5992
language English
publishDate 2024-11-01
publisher PeerJ Inc.
record_format Article
series PeerJ Computer Science
spelling doaj-art-e8c760ce34834d5780d1c7e232c3b79c2025-08-20T02:49:05ZengPeerJ Inc.PeerJ Computer Science2376-59922024-11-0110e253210.7717/peerj-cs.2532Enhanced detection of accounting fraud using a CNN-LSTM-Attention model optimized by Sparrow searchPeifeng Wu0Yaqiang Chen1School of Statistics, Jilin University of Finance and Economics, Changchun, Jilin, ChinaSchool of Statistics, Jilin University of Finance and Economics, Changchun, Jilin, ChinaThe detection of corporate accounting fraud is a critical challenge in the financial industry, where traditional models such as neural networks, logistic regression, and support vector machines often fall short in achieving high accuracy due to the complex and evolving nature of fraudulent activities. This paper proposes an enhanced approach to fraud detection by integrating convolutional neural networks (CNN) and long short-term memory (LSTM) networks, complemented by an attention mechanism to prioritize relevant features. To further improve the model’s performance, the sparrow search algorithm (SSA) is employed for parameter optimization, ensuring the best configuration of the CNN-LSTM-Attention framework. Experimental results demonstrate that the proposed model outperforms conventional methods across various evaluation metrics, offering superior accuracy and robustness in recognizing fraudulent patterns in corporate accounting data.https://peerj.com/articles/cs-2532.pdfAccounting fraudPredictionNeural networksAttentionSparrow search
spellingShingle Peifeng Wu
Yaqiang Chen
Enhanced detection of accounting fraud using a CNN-LSTM-Attention model optimized by Sparrow search
PeerJ Computer Science
Accounting fraud
Prediction
Neural networks
Attention
Sparrow search
title Enhanced detection of accounting fraud using a CNN-LSTM-Attention model optimized by Sparrow search
title_full Enhanced detection of accounting fraud using a CNN-LSTM-Attention model optimized by Sparrow search
title_fullStr Enhanced detection of accounting fraud using a CNN-LSTM-Attention model optimized by Sparrow search
title_full_unstemmed Enhanced detection of accounting fraud using a CNN-LSTM-Attention model optimized by Sparrow search
title_short Enhanced detection of accounting fraud using a CNN-LSTM-Attention model optimized by Sparrow search
title_sort enhanced detection of accounting fraud using a cnn lstm attention model optimized by sparrow search
topic Accounting fraud
Prediction
Neural networks
Attention
Sparrow search
url https://peerj.com/articles/cs-2532.pdf
work_keys_str_mv AT peifengwu enhanceddetectionofaccountingfraudusingacnnlstmattentionmodeloptimizedbysparrowsearch
AT yaqiangchen enhanceddetectionofaccountingfraudusingacnnlstmattentionmodeloptimizedbysparrowsearch