发表机构
Airbnb（爱彼迎）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出SIFT，一种基于Transformer的筛选器排序模型，从行为序列学习客人偏好，统一表示支持多任务，离线计算保证服务速度，显著提升预订与筛选器参与度，并已全面部署。
AI 中文摘要
搜索筛选器帮助客人在Airbnb这样的双边市场中浏览庞大的房源目录，推荐正确的筛选器可以显著提升预订转化率。然而，许多此类生产环境中的筛选器排序系统通过ETL流水线生成的手工设计、预聚合特征来表示客人。这使得系统维护成本高昂，且难以扩展到新的筛选器类型或情境维度（如行程长度、团体规模）。我们提出了SIFT（搜索意图到筛选器Transformer），一种基于Transformer的排序模型，直接从原始行为序列中学习客人偏好。SIFT用统一的客人表示取代了手动特征工程，该表示服务于多个预测任务，包括预订可能性、筛选器参与度以及序数容量阈值（例如2+卧室）——这是一个适用于双边市场中筛选器排序的通用框架，支持布尔型和数值范围型筛选器类型。将SIFT扩展到新筛选器只需添加新的输出头，而无需构建新的特征流水线。为保持服务快速，该客人表示以每日频率离线计算，而非在请求时计算。离线评估中，SIFT在预订和设施参与度PR-AUC上分别比生产基线提升了+51.9%和+62.8%。在线A/B测试中，SIFT使推荐筛选器的参与度提升了+20.0%，搜索者中整体筛选器使用率提升了+0.72%，新支持的卧室、浴室和床筛选器的使用率分别提升了+3.9%、+10.7%和+0.52%。为展示系统的可扩展性，我们利用相同的共享表示快速集成了一种新颖的酒店意图筛选器，使未取消酒店预订量提升了+3.8%，整体市场预订量提升了+0.76%。SIFT现已全面部署于生产环境，为数百万客人提供可扩展的个性化服务。
英文摘要
Search filters help guests navigate vast catalogs in two-sided marketplaces like Airbnb, and recommending the right filters can meaningfully lift booking conversion. Many such production filter-ranking systems, however, represent the guest through hand-engineered, pre-aggregated features generated by ETL pipelines. This makes it expensive to maintain and difficult to extend for new filter types or contextual dimensions (trip length, group size). We present SIFT (Search Intent-to-Filter Transformer), a ranking model built on transformers that learns guest preferences directly from raw behavioral sequences. SIFT replaces manual feature engineering with a unified guest representation that feeds multiple prediction tasks, including booking likelihood, filter engagement, and ordinal capacity thresholds (e.g., 2+ bedrooms) -- a general framework for filter ranking in two-sided marketplaces that accommodates both boolean and numeric-range filter types. Extending SIFT to new filters requires only adding a new head, not a new feature pipeline. To keep serving fast, this guest representation is computed offline on a daily cadence rather than at request time. Offline, SIFT improves booking and amenity-engagement PR-AUC by +51.9% and +62.8% respectively over the production baseline. In online A/B testing, SIFT increased engagement with recommended filters by +20.0%, overall filter usage among searchers by +0.72%, and usage of the newly-supported bedroom, bathroom, and bed filters by +3.9%, +10.7%, and +0.52% respectively. Demonstrating the system's extensibility, we rapidly integrated a novel hotel-intent filter using the same shared representation, driving a +3.8% lift in uncancelled hotel bookings and a +0.76% lift in overall marketplace bookings. SIFT is now fully deployed in production, serving scalable personalization to millions of guests.
Comments9 pages, 5 figures, 6 tables. Accepted at GRAIL 2026: Workshop on Generative, Retrieval-augmented, and Agentic Intelligence for Personalization, co-located with CIKM 2026, Rome, Italy
