Amazon Personalize Documentation

Once you have provided your data via Amazon S3 or via real-time integrations, Amazon Personalize can load and inspect the data, enable you to select the right algorithms, train a model, provide metrics, and generate personalized recommendations. As your data set grows over time from new metadata and the consumption of real-time user event data, your models can be retrained to provide relevant and personalized recommendations. 

Compute recommendations for large numbers of users or items, store them, and feed them to batch-oriented workflows such as email systems. 

Generate recommendations even for new users and find new item recommendations for your users.

Improve relevance of recommendations by generating them within a context. 

Improve the discoverability of your catalog by surfacing similar items to your users.

Unlock the information trapped in product descriptions, reviews, movie synopses or other unstructured text to help you generate highly relevant recommendations for users. Provide unstructured text as part of your catalog and Amazon Personalize extracts key information to use when generating recommendations.

Consider what’s relevant to your users and what is important for your business when generating recommendations. You can define an objective to influence recommendations. This can be used to help you maximize for metrics you define as important to your business.

Amazon Personalize can be integrated into websites, mobile apps, or content management and email marketing systems, via an inference API call. The service lets you generate user recommendations, similar item recommendations and personalized re-ranking of items. You can call the Amazon Personalize APIs and the service will output item recommendations or a re-ranked item list, which you can use in your application.

GetRecommendations API - returns a list of relevant items when you provide a userID. The API can also be used to return a list of similar itemIDs given an input itemID. 

GetPersonalizedRanking – You can use an API to re-rank a list of itemIDs given a userID and a list of itemIDs to be re-ranked. 

Amazon Personalize Content Generator uses generative AI to make recommendations more compelling with text generated by foundation models. It improves personalization by accompanying each recommendation with a tailored snippet that describes the thematic similarity between recommended items. Incorporate it in website carousels and email campaigns to replace generic titles like “More like X”, fostering a deeper connection with your end users.

Builders can use a custom chain on LangChain to seamlessly integrate Amazon Personalize with generative AI solutions. With pre-configured LangChain code, you can invoke Amazon Personalize, retrieve recommendations for a campaign or a recommender, and feed it into your generative AI applications within the LangChain ecosystem. Explore a range of use cases including personalized marketing copy, recommending products or content in chatbots, or generating concise summaries for personalized content.

Amazon Personalize improves your generative AI workflow by enabling return item metadata as part of the inference output. Select up to 10 fields, such as genre, rating, and product description, and use our LangChain integration capability to seamlessly feed these enriched recommendations into the foundation models. This richer context helps models generate highly personalized content to boost your engagement with end users.

For additional information about service controls, security features and functionalities, including, as applicable, information about storing, retrieving, modifying, restricting, and deleting data, please see https://docs.aws.amazon.com/index.html. This additional information does not form part of the Documentation for purposes of the AWS Customer Agreement available at http://aws.amazon.com/agreement, or other agreement between you and AWS governing your use of AWS’s services.