Airbnb 用 Chronon 将推荐嵌入陈旧度从两天降至秒级
原标题：Airbnb Cuts Recommendation Staleness from 2 Days to Seconds with Chronon
AI 摘要
Airbnb 扩展了其开源特征平台 Chronon，新增 Push Mode 和近实时（NRT）Model Transform，使基于序列的推荐嵌入能在用户活动后数秒内更新，将嵌入陈旧度从近两天降至不到一分钟（典型 10-30 秒）。离线 NDCG 提升 1.67%，在线 A/B 测试中未取消预订量提升约 0.33%。该方案复用已有的 JourneyFormer Transformer 序列编码器，在线排序路径基本不变，两项能力已贡献至 Chronon 公开仓库。
正文节选
Airbnb has extended its open source Chronon feature platform with Push Mode and Near Real Time (NRT) Model Transform to update sequence based recommendation embeddings within seconds of guest activity. The change reduced embedding staleness from nearly two days to less than a minute, with typical updates arriving within 10 to 30 seconds. Airbnb also reported a 1.67% improvement in offline NDCG and an approximately 0.33% increase in uncancelled bookings in online A/B testing. The work builds on A