Delayed Feedback Modeling for Post-Click Gross Merchandise Volume Prediction: Benchmark, Insights and Approaches

TL;DR

This paper introduces TRACE, a new benchmark for online delayed feedback modeling in GMV prediction, and proposes READER, a novel model that improves accuracy by handling repurchase behaviors and dynamic label calibration.

Contribution

The paper presents TRACE, a comprehensive GMV prediction benchmark, and proposes READER, a novel dual-branch model that effectively captures delayed feedback and repurchase patterns.

Findings

READER achieves 2.19% higher accuracy than baselines.

Delayed feedback modeling is crucial for online GMV prediction.

Separate modeling for repurchase and single-purchase samples improves performance.

Abstract

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 .