Learning to Match

TL;DR

This paper discusses Booking.com's approach to enhancing its marketplace by using hundreds of machine learning models to help guests discover suitable accommodations, turning the platform into a decision process advisor.

Contribution

It introduces a comprehensive system of machine learning models that improve guest decision-making and platform efficiency, validated through rigorous experiments.

Findings

Hundreds of ML models are used to improve matching.

Models are validated with randomized controlled experiments.

The platform acts as a decision process advisor.

Abstract

Booking.com is a virtual two-sided marketplace where guests and accommodation providers are the two distinct stakeholders. They meet to satisfy their respective and different goals. Guests want to be able to choose accommodations from a huge and diverse inventory, fast and reliably within their requirements and constraints. Accommodation providers desire to reach a reliable and large market that maximizes their revenue. Finding the best accommodation for the guests, a problem typically addressed by the recommender systems community, and finding the best audience for the accommodation providers, are key pieces of a good platform. This work describes how Booking.com extends such approach, enabling the guests themselves to find the best accommodation by helping them to discover their needs and restrictions, what the market can actually offer, reinforcing good decisions, discouraging bad ones, etc. turning the platform into a decision process advisor, as opposed to a decision maker. Booking.com implements this idea with hundreds of Machine Learned Models, all of them validated through rigorous Randomized Controlled Experiments. We further elaborate on model types, techniques, methodological issues and challenges that we have faced.