AI, Predictive Modeling, and Data Trends in Underwriting

Artificial intelligence (AI) is revolutionizing the underwriting process, offering unprecedented opportunities for efficiency and accuracy in the insurance industry. In this interview with AAIS Partner, Cogitate, we explored how AI is promising a new era in data interpretation and utilization. Jacqueline Schaendorf, CPCU, Co-Founder of Cogitate and President and CEO of Insurance House, discussed the potential of predictive modeling in underwriting and claims processes, significant data challenges faced by carriers, and innovative solutions offered by Cogitate.

AI Game Changers for Underwriters

With extensive industry experience and a keen eye on the evolution of technology platforms, particularly in AI and underwriting, Schaendorf identified numerous use cases for carriers, especially in underwriting and claims. She also sees significant potential in data access and utilization. Currently, data is often presented in static reports or dynamic formats, but AI has the power to transform how data is interpreted and interacted with.

Advancing Predictive Modeling in Underwriting and Claims Processes

In addressing the future of predictive modeling, Schaendorf explained how Cogitate focuses on its application in underwriting. "We're looking at the profile of our risks, specifically the risk attributes that come in with each different type of client," she said. While there are similarities in some variables, many are distinct, and Cogitate's goal is to use these data attributes to build models that predict outcomes. For instance, Cogitate aims to determine the propensity for a loss ratio based on specific risk attributes.

On the claims side, the objective is to value claims accurately, especially complex ones. "It's easy to handle the least complex claims, such as glass and towing in auto, but when it [comes] to a case that's going to go to litigation, how do you set the reserves on that and what does that look like over the life of that claim?" Schaendorf proposed. "I see the ability to use that data and predictive modeling to get a little more accurate and a little better at it."

Biggest Data Challenges Carriers Face and How to Overcome Them

According to Schaendorf, the biggest challenge carriers face when it comes to data is its structure and accessibility. While some data, like written premiums, policy numbers, and loss ratios, are well-structured, other types are not. This lack of structure poses significant difficulties in obtaining better, more accurate, and more useful data. To address this, Schaendorf believes it is crucial to foster a strong partnership between data professionals and top leadership within a company. "One group has one set of skills, and the other group has the business knowledge," she explained. Although establishing these standards is time-consuming and may not seem immediately rewarding, they ultimately facilitate faster and more accurate data access.

About Cogitate

Cogitate was formed in 2012 by Schaendorf and her co-founder, Arvind Kaushal, as a digital platform operating on a software-as-a-service model. It is designed to streamline rating, quoting, binding, and issuance across all lines of business, including both commercial and personal lines. This modern-facing platform boasts numerous third-party data integrations, enhancing its functionality. "The proudest thing I can say about Cogitate is it's an enabler," Schaendorf shared. Cogitate has seen rapid growth and implementation success with their clients, processing a significant volume of quotes, binders, and premiums through the platform across various lines, such as commercial transportation, personal property, flood, commercial property, and professional liability. "It's really facilitating growth for our partners, and that's what we're most proud of with the company."

Learn more at cogitate.us.

To view the full interview with Jacqueline Schaendorf, CPCU, click on the video above.

Public link

Please use the above public link if you want to share this noodl on another website.