Q: Why should I use Amazon Personalize?
A: Amazon Personalization has been empirically proven to increase key user engagement and revenue metrics in diverse industries. A market study of 1.5 billion shopping sessions across e-commerce businesses revealed 11.5% incremental revenue attributed to recommendations. For example, 30% of page views on Amazon.com are driven by recommendations.
Q: What are the key use cases supported by Amazon Personalize
A: Amazon Personalize supports the following key use cases:
- Personalized recommendations
- Personalized search, i.e., re-rank search results for a user based on a user's past interactions and activity.
- Personalized promotions/notifications
Q: What are some of the common business applications for Amazon Personalize
A: Amazon Personalize can be used to personalize the end-user experience over any digital channel. Examples include product recommendations for e-commerce, news articles and content recommendation for publishing, media and social networks, hotel recommendations for travel websites, credit card recommendations for banks, and match recommendations for dating sites. These recommendations and personalized experiences can be delivered over websites, mobile apps, or email/messaging. Amazon Personalize can also be used to customize the user experience when user interaction is over a physical channel, e.g., a meal delivery company could personalize weekly meal to users in a subscription plan.
Using Amazon Personalize
Q: How do I get started with Amazon Personalize?
Developers can also add their existing algorithms via containers that conform to Amazon SageMaker specifications in a few simple steps from the Amazon Personalize console or via APIs. These developers provided algorithms can then be used in the same fashion as the native algorithms in Amazon Personalize and benefit from its managed experience.
When deployed, developers call the service from their production services to get real-time or batch recommendations, and Amazon Personalize will automatically scale to meet demand. Once Amazon Personalize begins making inferences on production traffic, it measures the lift in engagement from personalization and generates reports in the AWS Console to allow developers to evaluate the model’s success.
Q: What data do I have to provide to Amazon Personalize?
A: Developers should provide the following data to Amazon Personalize:
- User activity stream or event data - User interaction data on the website/application is captured in the form of events and sent to Amazon Personalize often via an integration that involves a single line of code. This includes key events such as click, buy, add-to-shopping cart, comment, like etc. When onboarding to the service, developers can also provide a historical log of all event/activity stream data, if available.
- Catalog data - This can be any type of catalog including books, videos, news articles or products. This involves item ids and meta-data associated with each item. This data is optional.
- User data - User profile data including user demographic data such as gender and age. This data is optional.
Amazon Personalize will train and deploy a model based on this data. Developers can then configure personalization experiences/widgets (e.g. related items or personalized search) using the Amazon Personalize console and use a simple inference API to get individualized recommendations at run-time.
Q: How do I apply/export Amazon Personalize recommendations to my business workflows or applications?
A: Amazon Personalize provide customers two inference APIs: getRecommendations and getRerankedResults. Both these APIs return a list of itemIDs where an itemID can be a product identifier, videoID etc. The customers are then expected to use these itemIDs to generate the end user experience through steps, such as fetching image and description, and then rendering a display. In some cases, customers might integrate with AWS or third party email delivery services, or notification services etc. to generate the end user experience.
Q: How is the effectiveness of a personalization measured in Amazon Personalize?
A: The effectiveness of a personalization solution can be measured by first specifying a business goal the customer wants to optimize and then measuring the impact on this goal via an A/B test. These goals typically are revenue per user, revenue per session, average time spent per session, click-thru, and retention rates.