Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

  1. Home
  3. Research Domains
  5. Commerce, Management, Tourism And Services
  7. Accounting, Auditing And Accountability
  9. Accounting Theory And Standards
  11. Enhanced Detection Of Accounting Fraud Using A Cnn-lstm-attention Model Optimized By Sparrow Search

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

Peifeng Wu1, Yaqiang Chen1

  • 1School of Statistics, Jilin University of Finance and Economics, Changchun, Jilin, China.

Peerj. Computer Science
|December 9, 2024

Related Experiment Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

468
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.6K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K

View abstract on PubMed

Summary
This summary is machine-generated.

This study introduces an advanced AI model for detecting corporate accounting fraud, significantly improving accuracy over traditional methods. The enhanced model combines deep learning techniques with optimization algorithms for more robust financial fraud detection.

Area of Science:

  • Financial Technology
  • Artificial Intelligence
  • Data Science

Background:

  • Corporate accounting fraud detection remains a significant challenge in finance.
  • Traditional models struggle with the complexity and dynamic nature of financial fraud.
  • Existing methods often lack the necessary accuracy and robustness for effective fraud identification.

Purpose of the Study:

  • To develop an enhanced AI-driven framework for improved corporate accounting fraud detection.
  • To integrate Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) with an attention mechanism.
  • To optimize the proposed model using the Sparrow Search Algorithm (SSA) for superior performance.

Main Methods:

  • Proposed a hybrid deep learning model integrating CNN and LSTM networks.
Keywords:
Accounting fraudAttentionNeural networksPrediction

Related Experiment Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

468
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.6K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K
  • Incorporated an attention mechanism to focus on salient features in accounting data.
  • Utilized the Sparrow Search Algorithm (SSA) for hyperparameter tuning and model optimization.
  • Evaluated the model's performance against conventional fraud detection techniques.

    • Main Results:

    • The proposed CNN-LSTM-Attention model with SSA optimization demonstrated superior performance.
    • Achieved higher accuracy and robustness in identifying corporate accounting fraud patterns.
    • Outperformed traditional methods like neural networks, logistic regression, and support vector machines.
    • Validated effectiveness across various key performance metrics for fraud detection.

    Conclusions:

    • The integrated CNN-LSTM-Attention framework, optimized by SSA, offers a powerful solution for corporate accounting fraud detection.
    • This advanced approach significantly enhances the ability to detect complex and evolving fraudulent activities.
    • The findings suggest a promising direction for future research in AI-powered financial security and fraud prevention.
    Sparrow search