online marketing teams

Abstract: AI-generated summaries increasingly mediate how people interpret information across platforms, including product reviews on e-commerce sites. Using Amazon's AI summaries as a case study, we conducted a preregistered, randomized experiment (N = 278) comparing how AI summaries and user reviews shaped product perceptions, and how their influence varied with valence and presentation order. We found that both AI summaries and user reviews influenced participants' opinions, with negative summaries having a larger effect than positive ones. Presentation order was the most important factor: the first source anchored judgment and only user reviews could displace an existing anchor. Although participants reported preferring user reviews, they often underestimated the influence of AI summaries on their judgments. Our findings show how the placement of AI summaries shapes user perception and highlight opportunities to design interfaces that support more deliberate judgments about when to rely on summaries and when to examine the underlying content directly.

Abstract: 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.