AI 中文总结
该研究针对实时广告交易平台请求过度分发的问题，提出感知竞争的请求调度框架，经在线实验验证可降低DSP请求量并提升净收入。
AI 中文摘要
实时竞价（RTB）广告交易平台通常会将几乎所有传入请求转发给需求方平台（DSP），尽管只有一小部分请求会收到竞价。这种过度分发会削弱拍卖结果：DSP在计算和预算约束下会限制参与，降低有限竞价能力的有效利用。我们提出了一种感知竞争的请求调度框架，该框架利用分布竞价预测和概率转发来决定是否将每个请求发送给每个DSP。系统通过轻量级策略优化随时间调整每个DSP的阈值，以跟踪非平稳的市场状况。我们在一个每日处理超过200亿请求的生产平台上通过四个连续的在线实验评估了该框架。在初始DSP适应期后的最近14天窗口中，完整的多DSP部署在该策略下将DSP请求量降低了34.2%，同时净收入增加了4.6%（p<0.001）。进一步分析凸显了流量细分段之间的强异质性，并表明聚合指标可能具有误导性。细分段和每个DSP的分析表明，该策略凸显了DSP之间的比较优势，在不增加总请求量的情况下提高了货币化结果。
英文摘要
Real-time bidding (RTB) ad exchanges typically forward nearly all incoming requests to demand-side platforms (DSPs), even though only a small fraction receive bids. This over-distribution weakens auction outcomes: DSPs throttle participation under compute and budget constraints, reducing the effective use of limited bidding capacity. We present a competition-aware request dispatch framework that uses distributional bid prediction and probabilistic forwarding to decide whether each request should be sent to each DSP. The system adapts per-DSP thresholds over time through lightweight policy optimization to track non-stationary market conditions. We evaluate the framework through four sequential online experiments on a production platform serving over 20 billion daily requests. A full multi-DSP deployment reduces DSP request volume under the policy by 34.2% while increasing net revenue by 4.6% (p<0.001) in a recent 14-day window after an initial DSP adaptation period. Further analysis highlights strong heterogeneity across traffic segments and reveals that aggregate metrics can be misleading. Segment-level and per-DSP analyses suggest that the policy surfaces comparative advantages among DSPs, improving monetized outcomes without increasing overall request volume.
CommentsAccepted for presentation at AdKDD 2026, the premier workshop on artificial intelligence for advertising, held in conjunction with the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2026)
