Personalizing Airbnb search by learning from the guest journey

Summary

Airbnb replaced hundreds of hand-crafted ranking features with a Transformer-based sequence model that captures both long-term booking history and short-term browsing behavior. To keep latency low and throughput high, sequence representations are generated via daily batch jobs and combined with real-time queries using a co-trained setwise ranker.

Takeaways

• Guest histories are split into long-term events (up to 7 years of bookings and cancellations, capped at 80 events) and short-term events (past 21 days of listing views, capped at 200 events).
• Training throughput improved fourfold by using causally masked search batching to share a single forward pass across multiple searches, sequence-length bucketizing, and sparse calculations.
• Serving latency is minimized by precomputing sequence embeddings in daily batch jobs and retrieving them in real time for a setwise ranker that scores listing candidate sets together.

Related reading

• Airbnb · Jul 28, 2026

  Eval-driven development: Lessons from evaluating GenAI at scale

  Airbnb outlines its framework for eval-driven development (EDD), treating GenAI evaluation as a continuous engineering discipline rather than an afterthought. The strategy combines programmatic checks, calibrated LLM-as-a-judge evaluators, and human review to detect subtle quality regressions. By inspecting intermediate agentic execution traces and real-world failure modes, teams ensure generative models remain reliable and aligned with product requirements.

  Rohit Girme

• Airbnb · Jul 14, 2026

  From weeks to a day: how we made LLM evaluation fast enough to iterate on

  Airbnb built a four-layer LLM infrastructure framework to reduce iteration and evaluation turnaround from weeks to a single day. By using per-sample caching for generated references and judge scores, they established a deterministic evaluation foundation that separates genuine model drift from measurement noise. This setup enables rapid, bounded model hotfixes using micro LoRA adapters and comprehensive end-to-end validation across component boundaries.

  Baharak Saberidokht

• Meta · Aug 5, 2026

  From User Sequences to Scaling Laws: A Multi-Stage Architecture for Meta’s Ads Ranking

  Scaling sequence models for real-time ad recommendations faces latency bottlenecks and scaling ceilings when hybrid configurations process both long user histories and sparse feature interactions online. Meta addresses these trade-offs with a multi-stage architecture that decouples heavy, asynchronous offline user modeling from lightweight, real-time online ranking. Deep upstream transformer models process sequences of thousands of actions to generate cached user embeddings, which downstream online models combine with candidate ad features using dense tokenization and target-aware multi-head attention. This framework produces predictable, LLM-style log-linear scaling curves between compute and normalized entropy without disproportionate increases in online serving costs. Implemented as part of Meta's Generative Ads Recommendation Model, the design achieved a cumulative 6% lift in Instagram conversions and a 3% lift in Facebook conversions.

  By Steven De Gryze, Parshva Doshi, Sean O'Byrne, Arnold Overwijk, Dinesh Ramasamy, Lee Xiong

• Airbnb · Aug 25, 2026

  Project Lighthouse — Part 3: Introducing project-lighthouse-anonymize

  Airbnb has open-sourced project-lighthouse-anonymize, a Python library powering their privacy-preserving anonymization used to measure user experience disparities. The release is accompanied by technical papers detailing Core Mondrian, an extended partition-based anonymization algorithm, alongside a framework for measuring anonymized data quality. The library enforces k-anonymity and p-sensitive k-anonymity while offering built-in data quality metrics.

  Adam Bloomston