# Agent context: Claims Fraud Detection

Source: https://aiplaybooks.app/industries/insurance/claims/fraud-detection
AI suitability: conditional

## Objective

Rank open claims by fraud risk so that a fixed number of investigator hours is spent on the highest-value cases, without automating any refusal decision.

## Constraints

- Never decline, delay, or reduce a claim automatically. The system ranks, a human decides.
- Train only on confirmed investigation outcomes, never on adjuster referral decisions.
- Use only features available at scoring time, and prove it by reconstructing the feature set as of the scoring timestamp.
- Size the referral threshold to real investigator capacity rather than to a target recall.
- Log every score with the feature values that produced it, for audit and appeal.
- Test for disparate impact across protected groups before deployment and on a recurring schedule.

## Inputs

- Claim records with amounts, timeline, and status history.
- Policy and prior claim history joined as of the scoring timestamp.
- Resolved entity identifiers for people, vehicles, addresses, providers, and bank accounts.
- Confirmed investigation outcomes with verdict and verdict date.
- Investigator capacity expressed as referrals per day.

## Outputs

- A calibrated risk score per open claim.
- The ranked referral queue truncated at investigator capacity.
- The top contributing factors for each referred claim, in language an investigator can act on.
- Cluster summaries for suspected organised activity, listing the shared entities.

## Success criteria

- Referral precision improves against the queue the system replaced, measured on the same capacity.
- Confirmed fraud value prevented per investigator hour increases.
- Time to settle for non-referred claims does not get worse.
- No measurable disparate impact across protected groups.
- Score drift and label delay are monitored with an alert threshold agreed before launch.

## Known pitfalls

- Training on adjuster referral decisions rather than confirmed outcomes, which teaches the model to imitate existing bias instead of detecting fraud.
- Using features that only exist after an investigation has started, which produces excellent offline metrics and a useless production model.
- Optimising recall when investigation capacity is the binding constraint, which floods the queue and lowers yield.
- Ignoring that fraud is adversarial, so a static model decays as fraudsters learn what it catches.
- Treating a low-precision anomaly queue as a referral queue and burning investigator trust in the first month.

## When not to use AI here

- Only a small number of confirmed fraud outcomes exist, as a rule of thumb fewer than a few hundred, which is not enough to train or to evaluate honestly.
- Claims data cannot yet be joined across systems, in which case data integration is the real project.
- The insurer operates where state regulators have adopted the NAIC model bulletin, which expects AI decisions to be accurate and not unfairly discriminatory, and the organisation cannot yet explain a model score.
- Existing rules have not been tuned or retired in years, because that cheaper work is, in this playbook's judgement, worth doing before any model.

## Candidate approaches

- Intake red-flag rules (primary): Deterministic checks applied at first notification of loss that flag a claim for review before payment.
- Claim risk scoring (primary): A model trained on confirmed investigation outcomes that ranks open claims by fraud risk for a fixed investigator queue.
- Outlier claim discovery (discovery): Unsupervised scoring that surfaces claims deviating from the norm for their segment, used to find new fraud patterns worth labelling.
- Organised ring detection (supporting): Graph analysis linking claims through shared people, vehicles, addresses, and providers to expose coordinated fraud rings.

## Human oversight

A trained investigator makes every accusation and every refusal. The model orders the queue, and it explains why a case was ranked highly, but it never declines a claim on its own. Any coordinated action against a suspected ring is confirmed by a specialist first.

## Sources

- [Insurance fraud: do you live in a 'crash for cash' hotspot?](https://www.which.co.uk/news/article/insurance-fraud-do-you-live-in-a-crash-for-cash-hotspot-aD76p9P9jfWm), Which?, reporting Insurance Fraud Bureau analysis, 2021, practitioner
- [Social Network Analytics for Supervised Fraud Detection in Insurance](https://doi.org/10.1111/risa.13693), Risk Analysis, 2022, research
- [An expert system for detecting automobile insurance fraud using social network analysis](https://doi.org/10.1016/j.eswa.2010.07.143), Expert Systems with Applications, 2011, research
- [NAIC Members Approve Model Bulletin on Use of AI by Insurers](https://content.naic.org/article/naic-members-approve-model-bulletin-use-ai-insurers), National Association of Insurance Commissioners, 2023, regulation