BAFF：用于缓解RTB A/B测试中训练数据干扰的出价感知过滤器族
BAFF: Bid-Aware Filter Family for Mitigating Training Data Interference in RTB A/B Tests
浏览论文内容
中文总结 AI 辅助
针对RTB A/B测试中共享日志导致的训练数据干扰问题，提出出价感知过滤器族（BAFF），通过(k,l)参数化硬过滤器独立控制广告排序和出价定价差异的容忍度，并设计三阶段在线测量协议，实验表明其优于日志共享和日志拆分。
中文摘要 AI 辅助
在实时竞价（RTB）的在线A/B测试中，对照组和处理组模型通常在一个共享的服务日志上进行训练，该日志包含由对应模型生成的数据。这种共享日志训练通过两个渠道使每个模型的训练数据产生偏差：对应模型可能从广告候选池中选择了不同的广告（广告排序不一致），并且可能出价不同（出价定价不一致），从而可能扭曲A/B测试结果。日志拆分消除了偏差，但牺牲了训练数据；日志共享保留了所有数据，但未解决偏差问题。我们形式化了出价感知过滤器族（BAFF），这是一类由(k,l)参数化的硬过滤器，可独立控制对每个渠道的容忍度，在这两个极端之间提供了一个结构化的搜索空间。我们进一步提出了一种三阶段在线测量协议，该协议能够通过数据共享策略与生产中无干扰参考模型的偏差来评估这些策略。在离线模拟中，(k,l)扫描呈现出的操作点与无干扰参考模型的偏差小于日志共享和日志拆分。在需求方平台（DSP）上的实时RTB部署中，基于过滤器的变体比两个基线更紧密地保留了参考模型的业务指标（例如，CPC、CTR）。最佳操作点取决于设置，这凸显了搜索空间本身的实际价值。
英文摘要
In online A/B tests for real-time bidding (RTB), control and treatment models are typically trained on a shared serving log that includes data generated by the counterpart model. This shared-log training biases each model's training data through two channels: the counterpart model may have selected a different ad from the ad-candidate pool (ad-ranking disagreement) and may have bid a different price (bid-pricing disagreement), potentially distorting the A/B test outcome. Log-splitting eliminates the bias but sacrifices training data; log-sharing retains all data but leaves the bias unaddressed. We formalize the Bid-Aware Filter Family (BAFF), a class of (k,l)-parameterized hard filters that controls tolerance to each channel independently, providing a structured search space between these two extremes. We further propose a three-stage online measurement protocol that enables evaluating data-sharing strategies by their deviation from an interference-free reference model in production. In offline simulation, a (k,l) sweep surfaces operating points with smaller deviation from the interference-free reference model than both log-sharing and log-splitting. In a live RTB deployment on a demand-side platform (DSP), filter-based variants preserve the reference model's business metrics (e.g., CPC, CTR) more closely than both baselines. The best operating point is setting-dependent, underscoring the practical value of the search space itself.
发表机构
- Dable Inc.（Dable公司）
机构由 AI 辅助整理，请以论文原文为准。
