AWS를 활용한 상품 추천 서비스 구축::김태현:: AWS Summit Seoul 2018

The document discusses recommendations for building a product recommendation service using AWS. It covers key concepts in recommendation systems like collaborative filtering, content-based filtering, and association rules. It also describes the architecture for a recommendation system including using Amazon S3 for data lakes, AWS Glue for data cataloging, Amazon SageMaker for machine learning, and services like DynamoDB, ElastiCache and Lambda for the recommendation APIs and caching. Performance is evaluated using metrics like CTR, CVR, and RMSE.