Amazon Personalize features

User personalization predicts the items that a user will interact with based on their historical interactions with your catalog items. The user personalization recipe can be trained on up to 3 billion interactions and 5 million unique items. When recommending items, user personalization improves discovery and engagement with automatic item exploration, and updates every 2 hours to consider new items (when automatic updates are enabled).

Personalized ranking helps you deliver a list of recommended items that are ranked for a specific user. This is useful if you have a collection of ordered items, such as search results, promotions, or curated lists, and you want to provide personalized ranking for each of your users. Personalized ranking supports up to 5 million items with low latency, and enables you to highlight and adapt item recommendations according to a user’s evolving interests.

Improve the discoverability of your catalog by surfacing items your users are viewing, exploring, or searching for. Similar items generates recommendations for items that are similar to an item you specify. Use similar items to help users discover new items in your catalog based on their previous behavior and item metadata. Recommending similar items can increase user engagement, click-through rate, and conversion rate for your business.

Personalize your users’ search results by leveraging the Amazon Personalize and OpenSearch integration. Using the Amazon Personalize Search Ranking plugin within OpenSearch v2.9 and above, you can boost relevant items within a specific user's search results based on their interests, context, and past interactions in real-time. You can also control the level of personalization for each search query to ensure maximum flexibility and control over your search experience. Personalizing your search results can increase user engagement, click-through rate, and conversion rate for your application.

Automatically segment your users based on their interest in product categories, brands, and other attributes. Item affinity identifies users based on their interest in individual items such as movies, songs, or products, and item attribute affinity identifies users based on the attributes they care about, such as genre or price point. Intelligent user segmentation can drive higher engagement with marketing campaigns, increase retention through targeted messaging, and improve the return on investment for your marketing spend.

Recommend items gaining popularity at the fastest pace among your users. Using trending now, you can define the frequency at which trending now identifies trending items, with options for refreshing recommendations every 30 minutes, 1 hour, 3 hours, or 1 day, based on the most recent interaction data from your users.

Maximize brand engagement and loyalty by proactively recommending actions tailored to individualized users’ needs in real-time. Next best action generates recommendations for actions that your users are likely to take based on their previous interactions with your catalogue. Use next best action to recommend high-value actions such as enrolling in loyalty programs, signing up for a newsletter, exploring a new category, and downloading an app.

Amazon Personalize provides flexibility to use real-time or batch data based on what is most appropriate for your use case. For example, real-time data may be more appropriate for product or content recommendations on a website or app. Make your recommendations relevant by responding to the changing intent of your users in real-time. Batch data may be more appropriate for large notification campaigns. For example, you can compute recommendations for very large numbers of users or items in one go, store them, and feed them to batch-oriented workflows such as email systems. Amazon Personalize also supports incremental bulk data imports to update your data and improve the quality of your recommendations. You can easily append new records to the existing data in your datasets.

Providing relevant recommendations requires you to consider the context in which they are being viewed. With contextual recommendations, you can deliver a more personalized experience for customers and improve the relevance of recommendations by generating them within a context, such as device type, time of day, and more.