Applying Deep Learning To Airbnb Search
This work addresses search ranking optimization for Airbnb's platform, but it is incremental as it focuses on practical application rather than novel methods.
The paper tackles the plateauing performance of Airbnb's search ranking system, which initially used gradient boosted decision trees, by applying neural networks to achieve improvements, though specific numerical gains are not provided.
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!