Applying Deep Learning To Airbnb Search
Machine Learning
2020-02-13 v2 Artificial Intelligence
Information Retrieval
Machine Learning
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!
Cite
@article{arxiv.1810.09591,
title = {Applying Deep Learning To Airbnb Search},
author = {Malay Haldar and Mustafa Abdool and Prashant Ramanathan and Tao Xu and Shulin Yang and Huizhong Duan and Qing Zhang and Nick Barrow-Williams and Bradley C. Turnbull and Brendan M. Collins and Thomas Legrand},
journal= {arXiv preprint arXiv:1810.09591},
year = {2020}
}
Comments
8 pages