Applying Deep Learning To Airbnb Search

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!

8 pages

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• An Overview of Multi-Task Learning in Deep Neural Networks
• Don't Decay the Learning Rate, Increase the Batch Size
• On Application of Learning to Rank for E-Commerce Search
• Dropout as data augmentation

Cited by in corpus (22)

• Challenges in Deploying Machine Learning: a Survey of Case Studies
• The Role of Machine Learning in Cybersecurity
• EEGDnet: Fusing Non-Local and Local Self-Similarity for 1-D EEG Signal Denoising with 2-D Transformer
• Software Engineering for AI-Based Systems: A Survey
• Incorrect Data in the Widely Used Inside Airbnb Dataset
• Field-Programmable Gate Array Architecture for Deep Learning: Survey & Future Directions
• Listwise Learning to Rank by Exploring Unique Ratings
• Optimizing Airbnb Search Journey with Multi-task Learning
• Leveraging Organizational Resources to Adapt Models to New Data Modalities
• Improving Deep Learning For Airbnb Search
• Are Interpretations Fairly Evaluated? A Definition Driven Pipeline for Post-Hoc Interpretability
• Muddling Label Regularization: Deep Learning for Tabular Datasets
• Handling Position Bias for Unbiased Learning to Rank in Hotels Search
• A Social Search Model for Large Scale Social Networks
• Industry Insights from Comparing Deep Learning and GBDT Models for E-Commerce Learning-to-Rank
• Transforming Location Retrieval at Airbnb: A Journey from Heuristics to Reinforcement Learning
• Beyond Lexical: A Semantic Retrieval Framework for Textual SearchEngine
• SERank: Optimize Sequencewise Learning to Rank Using Squeeze-and-Excitation Network
• ModelPS: An Interactive and Collaborative Platform for Editing Pre-trained Models at Scale
• Uncertainty-Aware Learning for Improvements in Image Quality of the Canada-France-Hawaii Telescope
• Chromatic Learning for Sparse Datasets
• A scale invariant ranking function for learning-to-rank: a real-world use case