Improving territory mapping for P&C insurers with machine learning

Most personal auto and home insurance carriers use geographic risk as a primary rating variable for calculating policy premium rates. This ensures that customers living in the same neighborhood pay similar insurance premiums, as they are likely to experience the same geographical risks to their automobiles and property.

A combination of actuarial concepts and analytics techniques can be used to review old territory definitions for rating and underwriting. In this technique, new rating territories are defined using unsupervised machine learning algorithms, such as cluster analysis techniques, after applying principal of locality to increase the credibility of data – a concept discussed later in this paper. The goal is that the new distinct territories will display a lower variance within their boundaries. This would help the company ensure that they offer better-tailored premiums to their customers, more aligned with their geographic risk profiles.

Read our whitepaper to learn more about how EXL helps insurance clients extract meaningful insights from their data, helping them achieve efficiency across their entire customer value chain using a suite of domain-led advanced analytics methodologies.