Pinterest 用 40 亿参数 Qwen3 模型替换旅程聚类系统
原标题：Pinterest Replaces Journey Clustering with 4B Qwen3 LLM, Reports Improved Engagement
AI 摘要
Pinterest 将用户旅程推断系统从多阶段聚类流水线替换为微调的 40 亿参数 Qwen3 模型，模型读取用户最多 150 条、跨 360 天的行为历史并生成排序后的旅程名称。该系统在美国和加拿大的 A/B 测试中带来邮件点击率提升 1.1%、推送打开率提升 1.3%，并取得统计显著的参与度和留存收益。工程上采用 NVIDIA Dynamo 配合 vLLM 与 L40S GPU 提升推理效率，并通过跳过近期已处理用户减少不必要的推理。
正文节选
Pinterest has moved its user-journey inference system from a multi-stage clustering pipeline to a fine-tuned 4-billion-parameter language model, reporting a 1.1% improvement in email click-through and 1.3% higher push opens. Rather than clustering keywords into interests, the model examines users' activity histories to identify longer-term goals and feeds those journeys into Pinterest's existing recommendation infrastructure. Pinterest defines a "journey" as a goal that connects interests, inten