Definition

What is a training dataset in insurance pricing?

A training dataset in insurance is a table with one row per risk, the facts known at quoting as feature columns, the exposure carried, and what happened afterwards (claim count and loss) as the target the model learns to predict.

Also: training set · training frame · labelled dataset · experience frame · modelling dataset

Updated 27 October 2026 · Written and reviewed by the Soldek team

Actuaries have built this table for a century under other names: the experience frame behind a rate review. Machine learning did not change its shape, only how much can be learned from it. The columns are the application answers and policy facts (features), a unit of exposure such as policy-years or trip-weeks, and the outcome: number of claims, total paid and reserved, and the premium charged for comparison. An as-of date lets the model be validated on a later period than it was trained on, which is the only validation that means anything in insurance.

The quality of a training dataset is decided before any modelling: whether the features were captured as typed fields, whether exposure can be computed from dated policy changes, whether claims join to policies by key, and whether statuses mean one thing. A frame built from documents is expensive and noisy; a frame queried from a structured book is a day's work.

On Soldek

On Soldek the frame is a join across the exported tables: policies (exposure, premium) to quotes (answers per field, cover, channel) to claims (count, paid, reserve), with the product's field definitions giving each column its type. The full export from Settings → Your data contains all of them; the Client API serves products and submissions as JSON for a scheduled pipeline.

Your data

Questions

How large does an insurance training dataset need to be?
For a frequency model, a few thousand policy-years with a few hundred claims already separates risk meaningfully; severity needs more claims and is usually modelled with fewer features. Structure matters more than size: a small clean frame beats a large reconstructed one.
Should the training dataset include the premium?
Yes, as a column, not as a feature. It lets you compute loss ratios per segment and compare the model's relativities with the tariff that priced the book, which is normally the point of the exercise.

See it running.

Book a demo and we show you the complete platform live, from product builder to bordereau.