Worldwide, insurers face increasing consumer expectations for convenience, speed, and service. Many are turning to data science and real-time analytics to power innovative services and capabilities.
Take ConTe.it, for example. Headquartered in Rome, ConTe.it is the Italian brand for the Admiral Group, a direct insurance company specializing in auto and motorcycle insurance. With more than five million customers worldwide, the Admiral Group and its brands have made their mark in innovation, convenience, and customer satisfaction in the highly competitive insurance industry.
Francesco Maggina, ConTe.it’s Head of Data Science, expects within the next five years to make machine learning part of the company’s DNA and transform everything from how they price products for customers to how quickly they process claims. To this end, he and data science leaders from the company’s brands in Spain (under the Admiral Seguros brand) and France (under the L’olivier brand) have adopted the Domino data science platform to accelerate the development and deployment of algorithmic models that will help them better understand and serve their customers. Already, a new recommendation engine built and deployed on Domino enables ConTe.it to more quickly direct customers to the products they need. It has increased customer satisfaction and is on track to generate an incremental €2 million in profit, with more than €500,000 in additional revenue already captured through these targeted customer recommendations.
For Francesco Maggina, one of his team’s biggest priorities is delivering real-time services for customers — whether providing real-time pricing and policies, or processing claims and providing customer payments within minutes of them submitting the request. “I expect that in three years we will be able to pay 70 percent of our claims within minutes,” said Maggina.
It will require a broad range of complex algorithmic models working in concert. For example, in the case of claims processing, models provide a real-time assessment of payments based on accident photos, predicted repair costs, policy information, and more. But to create innovative products and services like this, the company’s data science team needed a platform that would facilitate research, development, deployment, and monitoring of new models.
Data scientists previously used personal workstations to build models, which created a host of challenges that impeded innovation. These included:
“Our first challenge at the European level was to select our data science platform that would help us improve data scientist productivity and performance so we could bring new services into production more quickly,” explained Maggina.
Together with his counterparts at Admiral Seguros and L’olivier and IT staff, Maggina launched the effort to identify a data science platform that could foster collaboration and accelerate data science efforts.
“We started with a list of 50 data science platforms and other solutions, and an extensive list of requirements covering DevOps, ModelOps, platform administration, privacy, security, training, support, and documentation. We narrowed the field down to three finalists—Domino, Amazon SageMaker, and Databricks—and then conducted in-person evaluations. In the end, we found that Domino was the best platform due to its security, ability to go live with models quickly, and comprehensive features.”
ConTe.it, Admiral Seguros, and L’olivier today all use the Domino data science platform to facilitate research, development, and deployment of machine learning models. The companies also plan to use Domino’s model monitoring capabilities to provide a single view of the health of all models. ConTe.it has deployed more than seven models on Domino since its adoption in 2018, and many others are under development.
With Domino, the teams can: