Celina Insurance’s Predictive Analytics Initiative: The Machine Learning Factor
Abstract
Predictive analytics is an investment insurers need to consider going forward, and we think insurance-based machine learning represents a key factor they need to take into consideration when evaluating vendors.
In the report, Celina Insurance’s Predictive Analytics Initiative: The Machine Learning Factor, Celent details how Celina Insurance, a US mutual insurance company, came to the decision to invest in a modern predictive analytics solution, and why machine learning has been a crucial factor driving its decision.
Machine learning is a technique that leverages algorithms that learn how to improve a model through experiences in performing data observations without human intervention. Automation is key to machine learning because the objective is to define algorithms that are able to learn without human assistance. For instance a machine learning algorithm will be able to learn which data sources would add value in a model or determine the impact of a variable on the result of a calculation.
“New techniques and emerging technologies enable business innovation or at least improvements in insurance,” says Nicolas Michellod, Senior Analyst in the Celent insurance practice and author of the report. “Celina Insurance’s curiosity and interest in what’s new on the market allowed them to identify how machine learning could add value to their business.”
After a short introduction of Celina Insurance Group, this report describes how the mutual enterprise has identified and prioritized predictive analytics business applications and communicated the potential value that can be derived from such a tool internally. The report also describes the process used by Celina Insurance to select a predictive analytics vendor and explain why and how machine learning has been a key factor influencing Celina Insurance decision.