2018/10/22 by Malay Haldar, Mustafa Abdool, Prashant Ramanathan +9 · 3 voices
Business, Management and Accounting · Computer Science · Mathematics · Social Sciences · #Archaeology #Artificial intelligence #Artificial neural network #Computer science #Data science #Decision tree #Deep learning #Deep neural networks #Frontier #History #Human Mobility and Location-Based Analysis #Learning to rank #Machine learning #Mathematics #Perspective (graphical) #Product (mathematics) #Ranking (information retrieval) #Recommender Systems and Techniques #Sharing Economy and Platforms #cs.AI #cs.IR #cs.LG #stat.ML
paper · pdf · doi:10.1145/3292500.3330658
8 pages
arxiv published 2018/10/22 · arxiv created 2018/10/24 · openalex publication_date 2019/07/25 · arxiv updated 2020/02/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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!