Insurers are under enormous pressure to innovate and be nimble today, especially as the industry works to address global changes to risk profiles, behavioral patterns, and both micro and macroeconomic uncertainties surrounding the novel coronavirus. Buyers have become more price-sensitive than ever, viewing insurance providers as interchangeable. New technology-driven players have come on the scene, winning market share from long-established players. And real-time data from IoT devices like smart homes, car sensors, health devices, and drones have become mainstream, offering vast insights to those able to tap into them.
Whereas once insurers focused data science efforts mainly on risk management, data science is foundational across all areas of the business today. One Fortune 500 insurer has centralized data science work on Domino, slashing model delivery and validation cycles by months so the firm can provide a differentiated customer experience and better prevent fraud.
For nearly 30 years, this Fortune 500 insurer has used advanced analytics to better understand customer needs and data science initiatives have grown organically across the company’s core product lines and functions, and the number of data scientists has swelled into the hundreds.
One area of focus in particular has been fraud detection. Risk leaders understand that there’s a fine line financial services organizations must walk when it comes to detecting (and stopping) fraud. Get it right, and customers are grateful that their financial institution prevented a fraudulent transaction, account breach, or false claim. Get it wrong, and customer frustration sets in as transactions and claims are put on hold.
But as data scientists worked to build new fraud detection models and integrate new data sources that would enable the business get this balance right, they faced many hurdles that slowed their progress:
The company conducted a two-week pilot of data science technologies from Domino Data Lab, Dataiku, DataScience.com (acquired by Oracle), and IBM. Pilot participants, who represented the company’s Banking, Property and Casualty, Innovation, and Risk divisions among others, unanimously selected Domino for its unique ability to support the end-to-end data science management lifecycle, accelerating model development, validation, and deployment.
The organization took a phased approach toward implementing Domino, onboarding approximately 30 users per week. Today, the platform serves more than 400 users across Data Science and IT, including: