A Data-Driven Pricing Strategy for Automobile Insurance Policies

Abstract

An automobile insurance policy premium depends on three factors, the risk associated with the drivers and cars on the policy, the operational costs to manage the policy and the profit margin. The premium is then some function of these. Operational costs are dependent on the company efficiency. The achieved profit margin is dependent on the competition experienced. Risk, however, is a customer dependent factor and hence premiums should take into account potential risk of a new policy. Traditionally, risk tables are used to compute the risk of a new customer but we instead use historical data to predict the average claim amount that would be made on a new policy in the coming year if it was approved. We use this value, as a measure of risk, to better determine the premium that is charged. We illustrate the approach with a single customer feature, the age of the driver, but the approach can be used to take into account several customer and/or car features.