How Yahoo enhances search retargeting using Amazon Bedrock
Quick Answer
Yahoo enhances its Search Retargeting capabilities by integrating Amazon Bedrock and generative AI, significantly improving keyword expansion efficiency.
Quick Take
The new system, utilizing Anthropic's Claude 3.5 Sonnet v2, achieved a fivefold increase in median broad expansion ratio, generating hundreds to thousands of relevant keywords compared to the legacy LSH method.
Key Points
- Yahoo's DSP now leverages generative AI for advanced audience targeting.
- Legacy keyword expansion faced limitations like outdated vocabulary and zero expansion.
- Amazon Bedrock enabled experimentation with multiple .
- Claude 3.5 Sonnet v2 outperformed legacy methods, improving expansion ratios significantly.
- The new system ensures semantic relevance in keyword retrieval.
DeepSignal Analysis
What happened
Yahoo has integrated Amazon Bedrock into its Search Retargeting (SRT) capabilities, utilizing generative AI to enhance keyword expansion. This new approach, powered by Anthropic's Claude 3.5 Sonnet v2, has reportedly achieved a fivefold increase in median broad expansion ratios, generating significantly more relevant keywords compared to the previous Word2Vec and locality-sensitive hashing method.
Key evidence
- Yahoo's previous SRT architecture relied on Word2Vec and locality-sensitive hashing, which had limitations such as outdated vocabulary and zero expansion in some cases.
- The integration of Amazon Bedrock allowed Yahoo to experiment with multiple large language models, ultimately selecting Anthropic's Claude 3.5 Sonnet v2 for its superior keyword expansion capabilities.
- The new generative AI-based keyword expansion system has led to a reported increase of up to 600 times in keyword expansion rates and up to five times growth in addressable audience reach.
Why it matters
The enhancement of Yahoo's SRT capabilities through Amazon Bedrock signifies a shift towards more effective audience targeting in digital advertising. By leveraging generative AI, Yahoo can provide advertisers with a broader and more precise set of keywords, aligning campaigns more closely with user intent. This improvement is crucial for increasing engagement and conversion rates, which are vital metrics in the competitive landscape of digital advertising.
Source Excerpt
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 ac
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from AWS Machine Learning
See more →
Build an explainable next-best-product recommendation system for banking on AWS
AWS presents a deep learning-based Next-Best-Product recommendation system for banks, utilizing Amazon SageMaker and PyTorch to enhance customer product predictions. This architecture leverages a multi-tower neural network for improved accuracy and explainability, addressing the complexities of customer data in financial services.
