What does this research mean for the field?

A detection method based on a dual-layer knowledge graph combining cross-layer path mining and rule vector discrimination achieves high accuracy and interpretability in identifying corporate financial fraud. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To develop and evaluate an intelligent, interpretable corporate financial fraud detection framework based on a two-layer knowledge graph architecture.

September 14, 2026Discover Artificial IntelligenceOpen Access

Financial fraud detection model based on dual-layer knowledge graph

View Full Paper

Ask AI

Bookmark

Authors

YJYing Jiang

Discussion

Member takes

Overview

Experimental study reveals accurate financial fraud detection in corporate enterprise data, indicating robust potential for automated auditing systems.

Key Points

To develop and evaluate an intelligent, interpretable corporate financial fraud detection framework based on a two-layer knowledge graph architecture.
Constructed a dual-layer knowledge graph integrating cross-layer path mining and rule vector discrimination to enable closed-loop fraud detection.
Evaluated the model across a sample of 700 enterprises and an industry-specific manufacturing scenario using 100 rule-mining iterations.
Achieved an accuracy of 94.2%, precision of 92.7%, recall of 93.5%, F1 score of 93.1%, AUC of 0.95, and MCC of 0.88 across 700 enterprises.
Attained a peak accuracy of 97.0%, an AUC of 0.975, and a rule trigger rate of 87% in the manufacturing dataset, retaining roughly 390 high-quality rules with average support exceeding 0.069.

Cite This Study

Ying Jiang (2026) studied this question.

synapsesocial.com/papers/6aa7b2e10926e14a848b17db https://doi.org/10.1007/s44163-026-02097-z

View Full Paper

Ask AI

Bookmark

September 14, 2026Discover Artificial IntelligenceOpen Access

Financial fraud detection model based on dual-layer knowledge graph

View Full Paper

Ask AI

Bookmark

Authors

YJYing Jiang

Discussion

Member takes

Overview

Experimental study reveals accurate financial fraud detection in corporate enterprise data, indicating robust potential for automated auditing systems.

Key Points

To develop and evaluate an intelligent, interpretable corporate financial fraud detection framework based on a two-layer knowledge graph architecture.
Constructed a dual-layer knowledge graph integrating cross-layer path mining and rule vector discrimination to enable closed-loop fraud detection.
Evaluated the model across a sample of 700 enterprises and an industry-specific manufacturing scenario using 100 rule-mining iterations.
Achieved an accuracy of 94.2%, precision of 92.7%, recall of 93.5%, F1 score of 93.1%, AUC of 0.95, and MCC of 0.88 across 700 enterprises.
Attained a peak accuracy of 97.0%, an AUC of 0.975, and a rule trigger rate of 87% in the manufacturing dataset, retaining roughly 390 high-quality rules with average support exceeding 0.069.

Cite This Study

Ying Jiang (2026) studied this question.

synapsesocial.com/papers/6aa7b2e10926e14a848b17db https://doi.org/10.1007/s44163-026-02097-z

Also Consider

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

View Full Paper

Ask AI

Bookmark