Researchers have developed UMAR, a novel multi-agent framework designed to improve audit risk assessment by explicitly modeling uncertainty and evidence conflict. UMAR utilizes three specialized agents—MD&A Text Agent, Financial Ratio Agent, and CAM Agent—to generate independent risk scores with calibrated uncertainty. These scores are then aggregated using Dempster-Shafer theory, which quantifies inter-agent disagreement. Evaluations on 3,200 firm-year observations from SEC 10-K filings demonstrated UMAR's superior performance over baseline models, achieving an AUROC of 0.782 and a PR-AUC of 0.341, while also providing actionable insights through conflict patterns. AI
IMPACT This framework could improve the accuracy and interpretability of financial risk assessments by leveraging multi-agent systems and uncertainty quantification.
RANK_REASON The cluster describes a new academic paper detailing a novel framework and its evaluation. [lever_c_demoted from research: ic=1 ai=1.0]
- CAM Agent
- Financial Ratio Agent
- FinBERT
- Form 10-K
- logistic regression model
- MD&A Text Agent
- UMAR
- XGBoost
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
