Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
March 4, 2026Discover Artificial IntelligenceOpen Access

Detection of false financial statements in enterprises based on dual-layer knowledge graph and graph-driven approach

View Full Paper
Ask AI
Bookmark
Share

Authors

XMXiaohua Ma

Discussion

Loading...

Member takes

Overview

This research proposes a novel detection model for financial fraud in enterprises, highlighting its effectiveness and accuracy.

Key Points

  • The aim is to improve the detection of false financial statements in enterprises using advanced graph techniques.
  • Organized and preprocessed financial statement data to identify indicators of falsification.
  • Developed a fraud detection model using a dual-layer knowledge graph.
  • Implemented a graph-driven detection model leveraging graph neural networks and attention mechanisms.
  • Achieved peak accuracy of 93.4% in accuracy tests across various feature scales.
  • Identified hidden fraudulent relationships with an accuracy of 86.2%.
  • Outperformed comparable models with a 0.905 identification accuracy in the enterprise-audit firm relationship graph.

Cite This Study

Xiaohua Ma (2026) studied this question.

synapsesocial.com/papers/69a7cd4fd48f933b5eed98a2https://doi.org/10.1007/s44163-026-00977-y
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Financial fraud detection model based on dual-layer knowledge graph2026
  2. 2An Intelligent Financial Fraud Detection Model Using Knowledge Graph-Integrated Deep Neural Network2024 · 4 citations
  3. 3Graph Data Science for improved Financial Fraud Detection2026
  4. 4Unmasking Financial Fraud in the Digital Era: A Hybrid CNN-LSTM-Attention and GNN Model for Intelligent Statement Analysis2026
  5. 5Modeling interdependencies in fraud detection: a graph embedding-based approach2026