A Data-Driven Pricing Strategy for Automobile Insurance Policies

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.

I. Introduction

Traditionally insurance companies have determined automobile policy premiums using rate tables computed by Actuaries [1]. Today, however, the vast amount of data collected in electronic form can now be used to determine more suitable premiums for a given policy since such data can be used to better predict risk [2]. Furthermore, by using data from present and past customers, the predictions are better suited for the particular environment in which the insurance company operates. This form of personalized policies benefit the customer (who pays an amount more in line with their risk) as well as the insurance company (which can now better ensure that it can safely cover claims costs from risky policies). The typical approach is straightforward. For a given new customer, one can use historical data of past and present customers with similar characteristics (features) to better estimate the risk level of the new customer and then use this to determine a premium for their policy. We use this approach to determine claim rates based on driver age and then develop an age-based pricing strategy that provides premiums based on risk according to age.