Augmenting Guest Search Results with Recommendations at Airbnb

Users on Airbnb often perform exhaustive searches with varying conditions to find suitable accommodations. However, overly narrow search criteria can lead to insufficient results, causing frustration and abandonment of search journeys. To address these challenges, we developed flexible pivot recommendations that dynamically augment search results by suggesting alternative dates, relaxing amenity requirements, or adjusting price constraints. These recommendations align with users' broader travel intent, resulting in a measurable improvement in booking rates on the platform. Our solution introduces two key innovations: (1) a modular and extensible architecture to generate the flexible pivot recommendations that integrates seamlessly with Airbnb's existing search ranking system, enabling rapid iteration and minimizing maintenance overhead; and (2) an efficient approach leveraging transfer learning and a Mixture of Experts (MoE) architecture to rank recommendations alongside organic search results. This approach handles diverse scenarios, from single to multiple recommendations, while addressing cold-start challenges and supporting ongoing enhancements. Our solution's scalability and generalizability make it applicable to industries such as online travel agencies and e-commerce platforms, where users benefit from more diverse, intent-aligned recommendations.

• Publication year

  2025

• Venue

  International Conference on Information and Knowledge Management

• Publication date

  2025-11-10

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1145/3746252.3761526
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Transforming Location Retrieval at Airbnb: A Journey from Heuristics to Reinforcement Learning

  2024cited by this paper
• Multi-objective Learning to Rank by Model Distillation

  2024cited by this paper
• Understanding User Behavior in Carousel Recommendation Systems for Click Modeling and Learning to Rank

  2023cited by this paper
• Optimizing Airbnb Search Journey with Multi-task Learning

  2023cited by this paper
• From Ranked Lists to Carousels: A Carousel Click Model

  2022cited by this paper
• Learning To Rank Diversely At Airbnb

  2022cited by this paper
• Page-level Optimization of e-Commerce Item Recommendations

  2021cited by this paper
• Toward User Engagement Optimization in 2D Presentation

  2021cited by this paper
• Improving Deep Learning for Airbnb Search

  2020cited by this paper
• Learning from Imbalanced Data Sets with Weighted Cross-Entropy Function

  2019cited by this paper
• Boosting Search Performance Using Query Variations

  2018cited by this paper
• Applying Deep Learning to Airbnb Search

  2018cited by this paper
• Deep Learning Based Recommender System

  2017cited by this paper
• Unbiased Learning-to-Rank with Biased Feedback

  2016cited by this paper
• Query Suggestion and Data Fusion in Contextual Disambiguation

  2015cited by this paper
• Peeking Inside the Black Box: Visualizing Statistical Learning With Plots of Individual Conditional Expectation

  2013cited by this paper
• A Survey on Transfer Learning

  2010cited by this paper
• From RankNet to LambdaRank to LambdaMART: An Overview

  2010cited by this paper
• Adaptive Mixtures of Local Experts

  1991cited by this paper

• No citing papers are available for this paper.