一种面向替代度假租赁房源推荐候选生成的多源集成方法
A Multi-Source Ensemble Approach to Candidate Generation for Alternative Vacation Rental Property Recommendations
查看机构详情
- Expedia Group（亿客行集团）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对度假租赁替代房源推荐，提出融合协同过滤与图神经网络的混合候选生成方法，在超200万房源数据上Recall@300提升14.8%，并验证了候选质量对下游排序的正向影响。
中文摘要 AI 辅助
替代房源推荐在度假租赁市场中起着关键作用，帮助用户在查看特定房源时发现相关选项。然而，生成高质量的候选替代房源面临独特挑战：库存异构、地理约束、可用性快速变化以及长尾房源分布。我们对度假租赁替代房源的候选生成（CG）方法进行了全面研究，比较了协同过滤、浅层嵌入和图神经网络（GNN）方法。我们在一个大型度假租赁平台（超过200万个活跃房源）上的实验表明，将基于物品的协同过滤与基于GNN的检索相结合的混合架构，在Recall@300上比最强基线提升了14.8%，这得益于两种来源的互补优势：协同过滤在具有丰富交互历史的房源上擅长早期召回，而GNN能发现多样化、非显而易见的替代房源，并更有效地处理冷启动场景。作为组成部分的结果，仅使用GNN嵌入就大幅优于浅层Hotel2Vec嵌入（各K值下相对召回率提升48-68%），这促使将其纳入集成。关键的是，我们考察了CG阶段的增益如何传导到下游排序阶段，发现更强的候选池能带来更高的下游排序质量，尽管由于候选生成与排序器训练之间的耦合，清晰归因这一效应较为复杂。这种召回-转化差距是从业者在两阶段推荐系统中部署新检索方法时的重要考量。
英文摘要
Alternative property recommendations play a critical role in vacation rental marketplaces, helping users discover relevant options when viewing a specific listing. However, generating high-quality candidate alternatives presents unique challenges: heterogeneous inventory, geographic constraints, rapid availability changes, and long-tail property distributions. We present a comprehensive study of candidate generation (CG) approaches for vacation rental alternatives, comparing collaborative filtering, shallow embeddings, and graph neural network (GNN) methods. Our experiments on a large-scale vacation rental platform (over 2M active properties) show that a hybrid architecture combining item-based collaborative filtering with GNN-based retrieval improves Recall@300 by 14.8% over the strongest baseline, by leveraging the complementary strengths of the two sources: collaborative filtering excels at early recall for properties with rich interaction history, while GNNs discover diverse, non-obvious alternatives and handle cold-start scenarios more effectively. As a component result, GNN-based embeddings alone substantially outperform shallow Hotel2Vec embeddings (48-68% relative recall improvement across K), motivating their inclusion in the ensemble. Crucially, we examine how CG-stage gains carry through to the downstream ranking stage, and find that a stronger candidate pool yields higher downstream ranking quality, though attributing this effect cleanly is complicated by the coupling between candidate generation and ranker training. This recall-conversion gap is an important consideration for practitioners deploying new retrieval methods in two-stage recommendation systems.
