Part of Dataset Foundry — synthetic, documented, citable datasets across domains
Insurance
Log in
The tool

Forge a Home & Property insurance dataset

Choose how many policy records you want and a seed. The same two numbers will always produce the same dataset — write the seed down and cite it in your methodology chapter.

Capped at 20,000 — the API generates synchronously (see ROADMAP.md Phase 1 for the planned async path beyond that).

Optional — leave both blank for the default (365 days from 2024-01-01). Policy start dates are spread across this range; end must be after start.

Two-stage additionally computes the claim payout for rows where a claim occurred — the claim_amount_ghs column only exists in this mode. Single-stage produces the claim-occurrence columns only (claim_occurred, claim_id, claim_category, claim_date are identical in both modes). Building age and security features (frequency) are unaffected either way; construction type and prior claims count only affect payout, so they're inert under single-stage.

Advanced: customize the model

Same directional relationships described in the methodology — strengthen, weaken, or rebalance them here without touching any code. Defaults are illustrative, not derived from real Ghanaian property-claims data.

Claim payout (severity)

Claim frequency — loadings

Property type is table-rated off the property-type base-claim-rate anchor (not adjustable here); these loadings multiply on top of it. Building age is a banded loading — only each band's multiplier is editable here, not its age range.

Name field

Off by default — most statistical work has no use for a name column. This is a separate decision from the Country field above: that only decides which name pool a name would be drawn from, not whether this dataset has names in it at all.