ModelRefs / Fraud Detection — Canonical Workflow
Fraud Detection — Canonical Workflow
Fraud Detection: provisional AI workflow implementation reference with candidate models, providers, tools, and architecture.
Overview
Prioritize anomalous transactions for human investigation with traceable risk indicators, false-positive review, and case escalation. Finance deployment requires organization- and jurisdiction-specific access, retention, segregation-of-duties, approval, reconciliation, and audit controls. Candidate outputs should preserve source-data traceability and route missing, conflicting, or policy-sensitive cases to qualified finance reviewers. These pages describe provisional decision support; accountable people retain accounting, payment, audit, financial-reporting, and compliance authority.
Implementation profile
| Category | reasoning-models |
|---|---|
| Implementation maturity | enterprise |
| Primary use cases | reasoning |
| Deployment options | managed-api, hybrid |
| Architectures | serverless-api, managed-container, hybrid-private-cloud |
What this evidence does not establish
- No fraud definition, population, labeling policy, loss model, investigation capacity, action policy, or appeal process is registered.
- No measured precision, recall, calibration, subgroup error, detection delay, analyst burden, complaint, or harm outcome is attached.
Candidate models with published references
- BGE-M3
- GPT-5
- GPT-5 Mini
- Claude Sonnet 4.5
- Claude Opus 4
- Gemini 3 Pro
- Llama 4 Scout
- DeepSeek R1
- Mistral Large 2
- Command R+
- o3
- o4 Mini
Coverage means the model is a candidate worth evaluating for this workflow, not a ranking or a recommendation. Models whose reference pages are still in review are omitted.
Benchmarks relevant to this workflow
- GPQA Diamond — Graduate-level Google-Proof Q&A in physics, chemistry, and biology.
- MMLU-Pro — Harder MMLU successor with 10-option questions and reduced contamination.
- MMLU — Massive Multitask Language Understanding — 57 academic and professional subjects.
These are the benchmarks whose task shape bears on this workflow. Each one only describes its own protocol and date, so confirm the harness matches your workload before treating a score as evidence.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Fraud Detection — Canonical Workflow.