Dr. Karnik is the Chief Data Scientist at Aureus. In this role, he is responsible for development of algorithms and mathematical models that help large organizations with advanced analytics solutions. His PhD dissertation made a substantial contribution to the theory of Type-2 Fuzzy Logic Systems and his work is still widely referenced.
I recently attended my first InsurTech Connect conference in Las Vegas a few weeks ago. Aureus has been attending and exhibiting at this conference, so I thought I knew what to expect. What surprised me the most about ITC 2019 was the sheer volume of people and the efficiency with which it was handled. I was impressed with how well organized it was. ITC's mobile app was a great way to encourage networking. The app enabled me to speak with over 150 attendees from insurance companies, agencies, brokers, and other technology providers. From these conversations, there were three topics that seemed to be on everyone’s mind this year.
If a life insurer wants to build a predictive model, how should they go about it? In this article, we explore the factors that need to be considered before beginning actual model development. We will do this by using the example of predictive models for improving persistency. (Improving persistency for a life insurer means increasing the volume of business they retain.)