Uplifting conversion across the acquisition funnel with personalization using contextual bandits on AWS

AWS Blog
Read the full article
Amazon Payments used a multi-objective contextual multi-armed bandit on Amazon SageMaker AI to personalize product acquisition funnels, achieving a high single-digit percentage lift in conversion for one customer group in a seven-week A/B test. The approach continuously balances exploration and exploitation to optimize content selection, demonstrating the growing role of bandits in managing generative AI content variations.

More in Business & Enterprise

Amazon’s New Push to Get Buy-In for Data Center Build-Out

Covered by 7 sources

Report: Anthropic targets pre-Thanksgiving IPO launch, despite warning of AI’s ‘existential risks’

Covered by 2 sources

Google rolls out new Gemini AI model but restricts access over safety concerns

Covered by 11 sources