Finding the large flood losses on the day they are lodged
A first-notice triage score for a property insurer’s claims team, fitted on 2019 to 2023 flood claims and tested on 96,255 claims from the 2024 and 2025 hurricane seasons.
Executive summary
Scoring new flood claims at first notice finds 92% of large losses at the caseload where a coverage-and-zone rule finds 76%.
Situation
After a major flood, a property insurer’s claims team receives a surge of new claims; the minority that become large losses carry most of the money and wait in the same queue.
Approach
A first-notice score from policy and lodgement fields, fitted on 2019 to 2023 US flood claims and tested on 96,255 claims from 2024 and 2025, against a coverage-and-zone desk rule.
Result
AUC 0.868 without inspection, 0.883 once water depth is recorded. At the rule’s caseload the score finds 92% of large losses against 76%.
The problem
After a flood, an insurer’s claims team faces thousands of property claims at once, and the largest losses are mixed in with minor ones. In the 2022 east-coast floods, insurers used flood-depth imagery and policy data to send assessors to the worst-hit homes first. Most claims, though, are still triaged on what the customer says at lodgement.
I measured how well a score from the policy and the first notice of loss finds the large losses on the day they are lodged, against sorting by the amount the customer estimates.
- Team
- Claims operations, large-loss and catastrophe desk, reserving actuaries, panel adjusters
- Scale
- Home and small commercial property books with tens of thousands of claims in a catastrophe year
- Systems
- Guidewire ClaimCenter, Duck Creek Claims or Sapiens, with policy data from the policy admin system
- Measure
- Large losses found in the first review tranche; caseload on the large-loss desk
What I built
A first-notice score for each new property claim, computed from the policy and the notice itself: flood zone, building cover and replacement cost, contents cover, occupancy, construction year, foundation and basement type, floors, elevation, cause of damage, whether the loss belongs to a named event, location and the days between loss and notice. A second version adds water depth inside the building once the customer or a desk adjuster records it.
Claims are ranked on arrival. The top band goes to the large-loss desk with an early reserve prompt; the middle band to standard handling; the low band to fast-track settlement with photo evidence.
Results
The score was fitted on claims from losses in 2019 to 2023 and tested on 96,255 paid claims from 2024 and 2025, a period that includes Hurricanes Helene and Milton and was never used to fit anything. It ranks a random large loss above a random smaller claim 87% of the time (AUC 0.868); adding water depth lifts that to 0.883.
Against the coverage-and-zone rule
A rule sending every claim with building cover of US$250,000 or more in an A or V zone to the large-loss desk flags 56% of claims and finds 76% of large losses. The score, sending the same number of claims, finds 92%. The desk keeps the same caseload and misses about a third as many large losses.
| Large-loss desk rule | Claims sent to the desk | Large losses found | Desk caseload that is large |
|---|---|---|---|
| Building cover US$250k+ in an A or V flood zone | 56% | 76% | 49% |
| Score, same caseload | 56% | 92% | 59% |
| Score, top fifth only | 20% | 44% | 80% |
| Score, top tenth only | 10% | 22% | 81% |
What the signals show
Water depth is the single strongest fact once it is known. Claims with 25 to 48 inches inside the building become large losses more than half the time; claims recorded at 49 inches and above show a lower rate, a pattern I would check against the insurer’s own claims before relying on it.
Speed of notice matters too. Claims lodged within three days of the loss became large losses 32% of the time; those lodged more than 30 days later, 9%. Severe damage gets reported fast.
| Rated flood zone | Paid claims | Large-loss rate | Median paid |
|---|---|---|---|
| A (high risk) | 191,032 | 30% | US$46k |
| X / B / C (moderate-low) | 49,242 | 16% | US$26k |
| V (coastal high) | 8,457 | 28% | US$29k |
Holding up in a surge
2024 was the heaviest year in the data, with US$8.8 billion paid. Inside each event the score still ranks claims well, which is what a catastrophe desk needs when every claim in the queue shares the same storm.
Data and method
- Data
- OpenFEMA FIMA NFIP Redacted Claims (v3), US National Flood Insurance Program, public domain: 249,139 claims with a payment, losses in 2019 to 2025
- Target
- Building plus contents paid of US$100,000 or more
- Split
- Fitted on 152,884 claims from 2019 to 2023 losses; tested on 96,255 claims from 2024 and 2025 losses
- Features
- Policy and first-notice fields only; water depth in a second version; no payment, damage or adjuster fields
- Method
- Gradient boosting with native categorical handling; benchmark against a coverage-and-zone rule
- Measures
- AUC, average precision, large losses found at fixed review shares, results inside each named event
Limitations
- This is US flood insurance data. Australian insurers price and settle flood differently, and the score is refitted on the insurer’s own claims before use; the fields it needs sit in any property claims system.
- Only claims with a payment are included, so nil claims and withdrawals do not appear. In live use the score runs on every new claim.
- 2024 is dominated by one event. Results inside each event are shown so a single storm does not carry the headline.
- Location is coarse in the public data. An insurer’s own geocoded address and flood-height data would add signal.
How I would take it live
- Pull three years of property claims from ClaimCenter or Duck Creek with first-notice fields and final paid amounts
- Refit the score, set the large-loss desk tranche with the claims lead, and run it in shadow on new claims for a month
- Show the score and reason codes on the claim screen; route the top tranche to the large-loss desk with an early reserve prompt
- Recalibrate after each major event and review missed large losses with the desk