平衡尝试与复购：面向按需配送的混合序列Transformer-GBDT排序器
Balancing Trial and Reorder: A Hybrid Sequential Transformer-GBDT Ranker for On-Demand Delivery
浏览论文内容
中文总结 AI 辅助
针对按需配送中尝试新店与复购排序的权衡，提出混合序列Transformer-GBDT的UVR排序器，统一多模型，提升尝试率且不损害核心指标。
中文摘要 AI 辅助
在配送平台上，个性化店铺排序极大地影响用户发现和订购的内容。与纯数字领域不同，候选店铺是本地化的，并受实时可用性和配送运营的约束。一个核心的建模张力在于：在为新店铺提供尝试机会与保持具有复购意图会话的排序质量之间取得平衡。我们提出了通用场所排序器（UVR），这是部署在Wolt的生产系统，它将用于序列用户建模的双向Transformer编码器与集成上下文、用户和店铺特征的GBDT排序器配对。UVR在一个国家的所有店铺和领域上进行训练，同时在推理时强制执行本地配送约束，它用一个统一系统取代了先前四个独立的排序模型（三个用于餐厅，一个用于零售）。标签平滑和偏向尝试的样本加权引导模型偏向新店铺，使离线尝试MRR比生产环境提升+12%至+30%，而在六个国家中的五个国家中，复购MRR有所下降。这些下降使得我们的核心在线指标Global CVR（混合了尝试和复购会话）在统计上保持不变。我们通过三个连续的A/B测试验证了UVR，前两个测试覆盖Wolt最大的运营市场，第三个测试覆盖所有运营国家和两个领域。UVR V1相比之前的生产排序器，商户尝试率提升+5.5%，Global CVR提升+0.16%；V2在此基础上进一步将商户尝试率提升+0.45%；V3是我们对餐厅和零售排序器的跨领域统一，进一步将零售商户尝试率提升+1.31%，共同贡献了显著的增量总订单价值和大幅简化的服务栈。
英文摘要
On a delivery platform, personalized store ranking greatly influences what users find and order. Unlike digital-only domains, candidate stores are local and bound by real-time availability and delivery operations. One central modeling tension is between surfacing new stores for trial and preserving ranking quality for sessions with reorder intent. We present Universal Venue Ranker (UVR), a production system deployed at Wolt that pairs a bidirectional transformer encoder for sequential user modeling with a GBDT ranker integrating contextual, user, and store features. Trained across all stores and domains of a country while enforcing local delivery constraints at inference, UVR replaces four previously separate ranking models (three for restaurants, one for retail) with a single unified system. Label smoothing and trial-biased sample weighting steer the model toward new stores, lifting offline trial MRR by +12% to +30% over production while regressing reorder MRR in five of six countries. These regressions leave Global CVR, our core online metric, which blends trial and reorder sessions, statistically unchanged. We validate UVR in three consecutive A/B tests, the first two across Wolt's largest operating markets and the third spanning all operating countries and both domains. UVR V1 delivers +5.5% Merchant Trial Rate and +0.16% Global CVR over the previous production ranker; V2 adds a further +0.45% Merchant Trial Rate on top; and V3, our cross-domain unification of the restaurant and retail rankers, adds a further +1.31% Retail Merchant Trial Rate, together accounting for substantial incremental gross order value and a materially simplified serving stack.
发表机构
- Wolt (DoorDash, Inc.)（Wolt（DoorDash公司））
机构由 AI 辅助整理，请以论文原文为准。
