通过点击后行为轨迹提升延迟转化率预测准确率
Follow the TRACE: Exploiting Post-Click Trajectories for Online Delayed Conversion Rate Prediction
- 用反馈轨迹替代硬标签，动态评估转化可能性
- 在真实数据集上相对最佳基线提升1.8%的AUC
- 适合需要高精度延迟转化预测的广告推荐系统
延迟反馈是在线转化率（CVR）预测的核心挑战，导致标签准确性与数据新鲜度之间的权衡。现有方法通过延迟建模或样本重加权来应对，却忽视了点击后行为在观察期内的演化过程。为此，我们将其形式化为反馈轨迹，并提出TRACE。该方法不强制对未揭示样本赋予硬标签，而是评估累积反馈状态与转化/非转化的匹配程度，动态优化后验概率，无需等待最终结果。为缓解早期轨迹稀疏性问题，我们进一步设计了可靠性门控回溯补全模块，利用全生命周期数据为未揭示样本提供自适应后验引导。大量实验验证了TRACE在主流基线上的优越性，并确认回溯补全模块可作为模型无关增强器适配现有系统。代码已开源：https://github.com/LunaZhangxy/TRACE。
原文摘要 · Abstract (English)
Delayed feedback poses a core challenge for online CVR prediction, forcing a trade-off between label accuracy and data freshness. Existing methods address this through delay modeling or sample reweighting, yet neglect how post-click behaviors evolve over the observation period. To overcome this limitation, we formalize this evolution as feedback trajectory and propose TRACE. Instead of forcing hard labels on unrevealed samples, our method evaluates how well the accumulated feedback status aligns with conversion versus non-conversion, dynamically refining posteriors without waiting for final outcomes. To counteract early-stage trajectory sparsity, we further design a reliability-gated retrospective completer that leverages full-lifecycle data to provide adaptive posterior guidance for unrevealed samples. Extensive experiments validate TRACE's superiority over state-of-the-art baselines and confirm the retrospective completion module as a model-agnostic enhancer for existing systems. Our code is available at https://github.com/LunaZhangxy/TRACE.
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。