Predictive modeling in insurance: Key issues to consider throughout the lifecycle of a model

  • PDF
  • Pricing
  • Rating +2

Most personal lines and a number of larger commercial lines insurers have incorporated a predictive analytics capability into their organisation. For those carriers evaluating if and how they should approach implementing such capabilities, there is much to consider, as doing so will involve a significant investment balanced against the risks associated with failing to invest in such capabilities.

In order to effectively navigate the best path to building this capability, it is important to form an understanding of how predictive analytics are used in the insurance industry, what a predictive model is, and to think through the key considerations during the typical lifecycle of predictive models.

Written with chief underwriting officers and product line heads in mind, this paper serves as a guide to how these decision makers might critically think about, identify, and plan around these issues as they relate to predictive models used to optimise relative pricing.