Use case · Insurance

Cancellation early warning for insurers: spot at-risk policies before the notice arrives

Cancellation early warning is a prediction of which insurance policies are likely to be cancelled in the coming weeks. UNID AI Predict delivers a weekly ranking per adviser, weighted by premium at risk, with the reasons from the data and the next best products.

Last updated:

The problem

By the time the cancellation notice arrives it is usually too late. At the same time, sales cannot call every customer. What is needed is a short list with reasons: whom first, and with which offer.

What you get

  • A weekly worklist per adviser, sorted by risk × annual premium
  • For each policy, the facts that drive the score
  • The top three next products per customer (next best product)
  • A backtest you recalculate yourself

Animated sample view: a worklist shows the policies with the highest cancellation risk in the next 90 days, sorted by premium at risk. Clicking a policy shows the reasons from the data and the next best products. A backtest shows how the insurer checks the prediction themselves.

Sample data, fictional

What data is needed

Seven tables are enough to start. Names and addresses are not needed; customers can be pseudonymised.

TableContent (examples)
CustomersCustomer ID, age band, region, customer since
PoliciesPolicy ID, line, start, premium, changes
CancellationsPolicy ID, date, reason (if recorded)
Premium invoicesAmount, due date, payment, reminders
ClaimsNotification, status, settlement, decline
AdvisersAdviser ID, responsibility, changes
ProductsProduct catalogue and lines

How the prediction is checked

  1. Hidden cut-off date

    You provide data up to a cut-off date and keep the cancellations after it.

  2. Baseline

    Your existing model or a simple rule (e.g. “premium increase above X%”).

  3. Metrics

    Hit rate and lift in the top 1, 5 and 10% of the list.

  4. Value calculation

    With your own save rate and contact costs, not our assumptions.

We do not promise an improvement in percent up front. You measure it in the backtest on your data.

Data protection and governance

  • No health data needed
  • Marketing consent respected
  • Never used for pricing or underwriting decisions
  • A person decides on every contact
  • Log, model card, fairness report by age band and region
  • Works council involvement planned

Deployment

Predict runs as a container on the insurer’s infrastructure, with a local language model and no outside connection if required. Alternatively on a dedicated server with a processing agreement.

What it does not do

  • The prediction says who is at risk, not how to keep them. That remains the job of sales.
  • Without cancellation history covering at least one period as long as the prediction window, no statement is possible.
  • Against a well-tuned existing model the margin can be small.

FAQ

Frequently asked questions

What is cancellation early warning?

Cancellation early warning predicts which policies are likely to be cancelled in a given period, so sales can act in time. It produces a ranking, not a decision.

What data does churn prediction need?

At least customers, policies, cancellations, premium invoices, claims, advisers and products, each with keys and timestamps. Names and addresses are not needed.

Does customer data have to leave the building?

No. Predict can run fully on your infrastructure. Pseudonymised data is enough for the backtest.

How much better is this than our existing model?

We do not promise that up front. You measure it yourself in a backtest with a hidden cut-off date, against your existing model.

Is this a high-risk system under the EU AI Act?

That depends on the purpose. The AI Act lists risk assessment and pricing in life and health insurance as high-risk. A retention ranking is a different case but needs the insurer’s own assessment. We support it with documentation.

What is next best product?

A recommendation of which product most likely fits a customer next, derived from what similar customers in similar situations took out.

Which lines of business are suitable?

Mainly lines with annual cancellation rights and enough history, such as motor, household, home and legal protection.

See it working on your own material.

In a 30-minute call we show the products live and work out which use case makes sense for you first. No obligation, in German or English, in Vienna or online.

UNID AI · Leonard-Bernstein-Straße 10 · 1220 Vienna · +43 660 476 30 89