Combine customer and contextual data to generate high-quality recommendations
Using machine learning, Amazon Personalize can correlate “known” customer data (such as email addresses, purchase history, and user interactions) with “contextual” data (such as location, time of day, weather, email client information, and device type of the user) to produce highly relevant and personalized recommendations for each customer.
Automated machine learning
Amazon Personalize includes AutoML capabilities that take care of the machine learning for you. Once you provide your data into Amazon S3, Amazon Personalize can automatically load and inspect the data, select the right algorithms, train a model, provide accuracy metrics, and generate personalized predictions.
Based on the same technology used at Amazon.com
Amazon Personalize includes algorithms that are based on over twenty years of personalization experience and developed expertise used in running the Amazon.com retail business. Amazon Personalize will automatically select the best algorithm base on your specific data sets, to train and deploy custom machine learning models.
Continuous learning to improve performance
Learn from every user interaction and continually improve your user engagement; Amazon Personalize automatically tracks the performance of key business metrics and retrains models based on the latest, up-to-date user and item data. The closed feedback loop enables Amazon Personalize to continuously calibrate to individual preferences and deliver dynamic, personalized experiences.
Bring your own algorithms
Advanced developers can add their own algorithms to Amazon Personalize using Amazon Sagemaker and a few simple API calls. The service handles data ingestion, storage, training, and inference in a simple and intuitive way, while allowing advanced developers, build their own algorithms/models for use in Amazon Personalize.
Easily integrate with your existing tools
Amazon Personalize can be easily integrated into websites, mobile apps, or content management and email marketing systems, via a simple inference API call. The service provides Recommendations, Search, and Notifications, so you can build more effective personalization into your applications. You simply call the Amazon Personalize APIs in your application and the service will output recommendations, search result, and notifications in a JSON format, which you can use in your application.
Recommendations API returns a list of relevant items given an userID and itemIDs. One example could be a content recommendation widget on a video streaming website that suggests a list of videos based on the user’s past views.
Search API re-ranks a list of search results based on the user’s preference. For example, an ecommerce retailer can use what they know about their customers’ previous behavior and past purchases to show the most relevant results, instead of showing the list of products that directly match the keyword.
Promotions/Notifications API returns a list of userIDs that a promotion on a particular itemID is applicable to. For example, an online travel site triggers a push notification with a custom offer when a user starts searching for flights to a specific destination. By serving up relevant promotions and offers to a targeted audience, you can help increase conversion and sales.
Refer to developer guide for instructions on using Amazon Personalize.
Instantly get access to the AWS Free Tier.
Get started building with Amazon Personalize in the AWS Console.