From Explaining to Enabling: Actionable Transparency in Algorithmic Insurance Pricing

The paper proposes a framework for making machine‑learning based insurance premiums explainable in a way that is valid, actionable, and reliable. It introduces axioms for each property and develops a method that uses Conformal Prediction to filter out uncertain recommendations, ensuring that suggested changes to controllable characteristics are likely to lower premiums. Experiments on real Florida flood‑insurance claims and synthetic driver‑telematics data show that constrained recommendations are more reliable and predict larger risk reductions than unconstrained ones.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.