OfferUp uses Amazon Titan Multimodal Embeddings to boost buyer & seller experience

Опубликовано 19 марта 2024, 23:11

OfferUp is one of the largest mobile marketplaces for local buyers and sellers in the U.S. However, a key challenge was that users often provided limited text descriptions for their listings, resulting in poor search discoverability.

Hear Andres Velez, Principal Data Scientist at OfferUp, explain how they leveraged the Amazon Titan Multimodal Embeddings model on Amazon Bedrock. The solution combines sparse text descriptions with image data from product listings to generate rich, accurate embeddings to represent each listing. Even listings with minimal initial text can now be properly surfaced to buyers using the enhanced multimodal embeddings from Amazon Bedrock.

The key benefit is improved product discoverability on OfferUp's marketplace, and shortened time-to-sale for sellers - providing a better overall experience for both buyers and sellers.

Learn more at: go.aws/4aWOKNJ

Subscribe:
More AWS videos: go.aws/3m5yEMW
More AWS events videos: go.aws/3ZHq4BK

Do you have technical AWS questions?
Ask the community of experts on AWS re:Post: go.aws/3lPaoPb

ABOUT AWS
Amazon Web Services (AWS) is the world’s most comprehensive and broadly adopted cloud platform, offering over 200 fully featured services from data centers globally. Millions of customers — including the fastest-growing startups, largest enterprises, and leading government agencies — are using AWS to lower costs, become more agile, and innovate faster.

#generativeAI #AmazonTitan #OfferUp #AmazonBedrock #AWS #AmazonWebServices #CloudComputing