Dynamic Re-Ranking (DRR) Advanced is available in Beta for Elevate customers. DRR is a powerful AI feature that optimizes search results for increased relevance. This update addresses long-standing customer requests, including:

• Hourly Refresh: DRR scores are now refreshed hourly, ensuring results reflect the latest user behavior and events (previously updated daily).
• Multi-Facet Support: DRR now supports re-ranking for more than one browsing facet, allowing for more precise control over filtered searches (e.g., category and brand).
• Empty Query Re-Ranking: Unfiltered empty queries will now display the most relevant results based on overall popularity, while filtered queries will prioritize results specific to the applied filters.

By participating in the public beta, Elevate customers can leverage these enhancements to achieve significant improvements in conversion rates. 

Real-Time Data Transformation is designed to simplify data preparation for Algolia. This feature provides pre-built transformation functions for common use cases, options to manage custom transformation functions, and a preview pane to review transformation code. These tools help users prepare their data more efficiently, reducing implementation time and enhancing data quality. This leads to easier access to Algolia's advanced search and discovery features, allowing users to handle data preparation tasks independently and ensuring data is well-structured for optimal performance. Click here for more information. 

This Private Beta allows you to activate Personalization for any recommendation model with one click and view it in the dashboard. This ensures results are tailored to each user’s preferences by integrating personalization signals, improving the user experience.

No-Code Banners in the Visual Rules Editor enables users to create and manage banners directly through a user-friendly UI, eliminating the need for JSON coding. Banners can be displayed at the top of search and category results for customers using InstantSearch. The feature includes a Banner Consequence in the Visual Editor, support for No-Code Banners in InstantSearch, and updated documentation. 

Algolia introduces Generative Shopping Guides, now available in private beta, to revolutionize e-commerce content creation. Leveraging Retrieval Augmented Generation (RAG), this tool allows e-commerce sites to generate long-form educational articles based on product catalogs stored in Algolia’s Search index. These guides simplify the buying process by delivering targeted, informative content that helps consumers make informed purchasing decisions. Developers can easily configure and integrate Shopping Guides using the Algolia Dashboard and SDK, enhancing customer engagement and driving conversions. Join our private beta to explore the future of generative e-commerce content.

This release streamlines data ingestion by offering a more intuitive onboarding experience and simplified domain validation with multiple new verification methods. Product & Article helpers are available to enhance data extraction using the Schema.org JSON-LD formats, eliminating the need for manual configuration. A no-code "Configuration" page allows users to set up and schedule crawlers visually, reducing reliance on coding. Accessible directly from the Algolia dashboard, this update significantly improves ease of access and management. Click here to learn more.

The Insights API now supports authenticated user tokens and offers enhanced revenue analytics for Adobe Commerce (Magento) customers. This update, powered by the new PHP API client (v4), introduces the ability to track event subtypes and revenue data, including Magento-specific discounts. Additionally, this release enhances PII protection and improves cookie consent handling. Click here to learn more.

Recommend has a new setting in the Frequently Bought Together (FBT) model! Previously, the FBT model inferred connections between products based on collaborative filtering, recommending items even if they hadn't been purchased together before. While sophisticated, this approach may not suit all use cases. To address this, we are introducing the "Strict" variant in public beta, which only recommends items that have been strictly bought together. This new option allows users to choose between the existing "Relaxed" model, which increases catalog discovery through inferred relationships, and the new "Strict" model, ensuring recommendations are based solely on past purchases. This update provides greater clarity and flexibility, enhancing the precision of product recommendations for different business needs. This feature is now available to all customers.

The new “Recommended for You” model is now in private beta. It enables the creation of personalized product carousels by leveraging individual affinity profiles. This feature delivers more relevant content to your users, boosting user engagement and conversion.