FTI Consulting Client Example: Building a More Profitable Customer

FTI Consulting was engaged by a multinational insurance group with the objective of enabling the client to use existing customer data to better understand customer behaviors across product lines; building a more profitable customer base; and improving its return on data.

Related article: Realistic Steps for Improving Your Return on Insurance Data

While this company had a plethora of data on its customers, it was not able to create a single view of a specific customer. For example, producers or customer service employees were unaware that a household carrying an automobile insurance policy with the company also carried its home insurance or might at one time have considered purchasing pet insurance. As a result of this inability to have a single view of the customer, the company lacked a clear understanding of the potential profitability of each customer.

Working with the client, FTI extracted historical customer data from the company’s data warehouse and transformed, standardized and cleansed the data before loading the data in an AaaS (Analytics as a Service) platform. This effort was required since the customer data—including demographics, products, premiums and customer care information—was both structured (in spreadsheets) and unstructured (in notes and emails).

Two years of historical revenue and cost data that could be associated with each household—including profit and loss numbers, reported claims, losses, premiums, and claims handling costs—were then loaded in a database for analysis via the AaaS platform. FTI used various data modeling techniques to create, for the first time, a single view of each household. The process included calculating overall profitability per household by breaking down the costs and revenues per customer over the prior two-year period.

With this robust portrait of the customer in hand, FTI was able to analyze customer behaviors to create behavioral profiles of key customer segments. Using machine-learning algorithms, FTI clustered households into one of six distinct segments.

Ultimately, the analytics process was transferred to the client, enabling the company to calculate retention rates per household for each segment and develop retention strategies targeted to the needs and behaviors of each one, considering profitability, product holdings and life stage. The client also used the analysis to cross-sell and upsell products more effectively to households in each segment.

To improve conversion rates, FTI developed a model that predicted the likelihood that a customer requesting a product quote would end up purchasing a policy. This information was documented before the request was routed to a sales professional.

The program improved the client’s quote-to-win ratio by 40 percent and increased its annual gross written premiums by 10 percent. As important, the program was sustainable and thus capable of producing ongoing financial benefits.