Hipcamp wanted to increase user booking rate, a proxy of revenue and both guest and host satisfaction, by improving the quality of its marketplace search results.

With a mature engineering team already following best practices in search and discovery optimization, Hipcamp already had optimized its results to an industry-standard search quality score. No more obvious low-hanging fruit remained and additional best-practices work failed to move metrics forward. In addition, Hipcamp had product constraints around distance, boosting, and blending, and required support for its in-house marketplace managers to manipulate listings. They needed a unified and adaptive solution to serve many stakeholders.

That data complexity created a barrier preventing Hipcamp from evolving from a heuristic-and-test approach to a more systematic one of experimentation and continuous optimization. A solution would need to be an order-of-magnitude investment in a combination of user metrics collection, data processing, modeling, and real-time serving.

Structurally, Hipcamp is a complex p2p marketplace with non-fungible, unique, and variable inventory. It serves users internationally across iOS, Android, and web and combines a mix of data services like Segment and in-house solutions to measure user engagement.