Applying Deep Learning To Airbnb Search

TL;DR

This paper describes Airbnb's experience in applying deep learning to improve search ranking, highlighting practical challenges and useful insights gained during implementation.

Contribution

It provides a real-world case study of integrating neural networks into an existing search system to overcome performance plateaus.

Findings

Neural networks can enhance search ranking performance.

Practical challenges in deploying deep learning in production.

Insights into effective neural network application strategies.

Abstract

The application to search ranking is one of the biggest machine learning success stories at Airbnb. Much of the initial gains were driven by a gradient boosted decision tree model. The gains, however, plateaued over time. This paper discusses the work done in applying neural networks in an attempt to break out of that plateau. We present our perspective not with the intention of pushing the frontier of new modeling techniques. Instead, ours is a story of the elements we found useful in applying neural networks to a real life product. Deep learning was steep learning for us. To other teams embarking on similar journeys, we hope an account of our struggles and triumphs will provide some useful pointers. Bon voyage!