How Yahoo enhances search retargeting using Amazon Bedrock
AWS Machine Learning Jessica Young
Yahoo replaced its Word2Vec and locality-sensitive hashing keyword expansion system with generative AI powered by Amazon Bedrock's Claude 3.5 Sonnet model in their Search Retargeting ad platform. The new system achieved a median fivefold increase in keyword expansion ratio and up to 600 times higher expansion rates compared to the legacy approach. This enhancement launched in Q1 2025 and enables advertisers to reach significantly larger and more precisely targeted audiences with improved campaign performance and conversion rates.
Why it matters
In this post, we demonstrate how Yahoo implemented Amazon Bedrock to enhance their Search Retargeting (SRT) capabilities in the Yahoo DSP ad tech suite. SRT is a core audience targeting solution that helps advertisers reach users based on their historical search behavior, bridging search intent with display, video, and native advertising. Beyond targeting keywords entered on Yahoo Search, SRT uses AI to identify and engage users who demonstrate intent through search activity both on Yahoo and across integrated partner systems.
