An up-and-coming online insurer has been expanding their user base rapidly in their first two years of operations, but they have a churn problem. Customers are not providing the value they’re estimated to have, and the cost of maintaining existing policyholders has become a serious drag on revenues. The company’s internal models consistently rank a specific region higher than the rest based on historic internal data, but predictions haven’t panned out accordingly, leading to misallocated budgets and unnecessary spending.
Our customer used Explorium’s Enrichment Catalog to expand its context for each customer and their likelihood to spend more. They used Explorium to retrain their existing machine learning models and were able to build new features to better predict customer lifetime value (CLV) and churn, including:
Using Explorium, the company was able to redefine their CLV calculation by providing greater context around each customer’s value and improve their ranking model to prioritize those policyholders that actually offer the greatest CLV. The company was able to boost their revenues per customer by 13%. Moreover, our customer was able to reduce their churn by nearly 10%, cutting down the number of clients lost every month. In an industry where acquiring new customers is significantly costlier than keeping existing ones, the company managed to cut down on their marketing costs in a big way.
