解决点击后商品交易额预测的延迟反馈难题，提出新模型与数据集。
Delayed Feedback Modeling for Post-Click Gross Merchandise Volume Prediction: Benchmark, Insights and Approaches
- 构建在线流式处理的GMV预测基准TRACE，支持完整交易序列建模。
- 发现复购样本标签分布与单次购买差异大，需分开展示建模。
- 提出READER模型，动态激活专家并校准回归目标，提升预测精度2.19%。
在线广告排序模型的预测目标正从转化率（CVR）等概率指标转向点击后商品交易额（GMV）等数值型业务指标。与已有研究充分探讨的CVR延迟反馈问题不同，GMV预测中的延迟反馈建模仍属空白，且挑战更大——因为GMV是连续变量，一次点击可能引发多次购买，累计形成最终标签。为填补这一研究空白，我们构建了TRACE基准，包含每个用户点击产生的完整交易序列，支持在线流式延迟反馈建模。对TRACE的分析与实验揭示两大关键洞察：（1）GMV标签分布快速演变，要求在在线流式训练中建模延迟反馈；（2）复购样本的标签分布显著区别于单次购买样本，凸显分开展示建模的必要性。基于此，我们提出一种新型建模范式RepurchasE-Aware Dual-branch prEdictoR（READER），通过路由器预测复购行为，选择性激活专家参数，并动态校准回归目标以缓解因标签不完整导致的低估问题。实验表明，READER在TRACE上优于基线模型，准确率提升2.19%。我们认为本研究将开启在线延迟反馈建模在GMV预测中的新方向，所提出的TRACE基准与洞见将推动该领域的后续研究与应用。代码与数据集已开源：https://github.com/alimama-tech/OnlineGMV。
原文摘要 · Abstract (English)
The prediction objectives of online advertisement ranking models are evolving from probabilistic metrics like conversion rate (CVR) to numerical business metrics like post-click gross merchandise volume (GMV). Unlike the well-studied delayed feedback problem in CVR prediction, delayed feedback modeling for GMV prediction remains unexplored and poses greater challenges, as GMV is a continuous target, and a single click can lead to multiple purchases that cumulatively form the label. To bridge the research gap, we establish TRACE, a GMV prediction benchmark containing complete transaction sequences rising from each user click, which supports delayed feedback modeling in an online streaming manner. Our analysis and exploratory experiments on TRACE reveal two key insights: (1) the rapid evolution of the GMV label distribution necessitates modeling delayed feedback under online streaming training; (2) the label distribution of repurchase samples substantially differs from that of single-purchase samples, highlighting the need for separate modeling. Motivated by these findings, we propose RepurchasE-Aware Dual-branch prEdictoR (READER), a novel GMV modeling paradigm that selectively activates expert parameters according to repurchase predictions produced by a router. Moreover, READER dynamically calibrates the regression target to mitigate under-estimation caused by incomplete labels. Experimental results show that READER yields superior performance on TRACE over baselines, achieving a 2.19% improvement in terms of accuracy. We believe that our study will open up a new avenue for studying online delayed feedback modeling for GMV prediction, and our TRACE benchmark with the gathered insights will facilitate future research and application in this promising direction. Our code and dataset are available at https://github.com/alimama-tech/OnlineGMV .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。