Parallel Experimentation and Competitive Interference on Online Advertising Platforms
揭示了竞争广告主同时进行在线实验会导致广告效果估计出现偏差，并提出一个框架来考虑并纠正这种偏差。
This paper shows the existence of bias in the estimation of ad effectiveness created by concurrent online experimentation by competing advertisers and proposes a framework to account and correct for it.