Algolia's Frequently Bought Together (FBT) feature now includes a "Strict" model variant, providing customers with a more precise and controlled recommendation strategy. This variant ensures that only items strictly purchased together are recommended, addressing specific use cases where a more conservative approach is desired.
Algolia Recommend is now integrated into Algolia’s Shopify offering, allowing merchants to add cross-selling functionalities directly within Shopify's theme customizer. This drag-and-drop functionality simplifies setup to under 10 minutes, eliminating the need for complex API integrations. Merchants can leverage Recommend carousels to showcase relevant product suggestions, boosting sales and customer engagement. Click here to learn more.
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.
Recommend UI library components, such as Frequently Bought Together and Looking Similar, are now integrated into InstantSearch. This unification reduces fragmentation in Algolia’s frontend libraries, simplifying the development process and enhancing the customer experience.
Learn more: InstantSearch Guide | API Reference | Launch Blog Post
The Algolia Recommend setup process for Salesforce Commerce Cloud's native Storefront Reference Architecture (SFRA) has been simplified. Historically, setting up Recommend required extensive coding and conceptual adjustments, which complicated the integration process. The new low-code solution allows integrators to easily incorporate pre-made templates into SFRA content slots with minimal coding required. This enhancement not only streamlines the integration process but also provides comprehensive guidance for using various Recommend models. This update makes it easier and faster to adopt Recommend on SFCC SFRA storefronts. 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.
An important update has been made to the "Looking Similar" feature in Recommend. Previously, this feature could only fetch a maximum of 500k items, which prevented the model from being trained if the catalog exceeded this limit. This posed a challenge for customers with larger indices. With this update, Algolia now accepts indices of all sizes, still fetching up to the maximum number of items. Records are browsed and ordered by Custom Ranking to prioritize the most relevant items based on your business criteria. For example, training on a catalog of 3 million book items now completes in 5 hours using the top 500k records. Next, the limit will be tested at 1 million items, enhancing flexibility and usability for larger datasets.
An option to customize the events used by the Frequently Bought Together (FBT) model has been released. Previously, customers reported that the FBT model did not recommend items that they expected to go together, partly because the model considered all conversion events, such as purchases, add-to-cart, and add-to-wishlist, which diluted the accuracy of recommendations. To address this, a new setting has been introduced in the FBT model configuration that allows users to specify which event types should be considered for training. This customization increases the relevancy of FBT recommendations and improves adoption rates. Customers can update their existing FBT configurations or set it up during the initial model setup to ensure the model is trained with the most accurate conversion data. This enhancement is part of a broader initiative to detect sufficient event data availability before training, reducing the likelihood of training failures.
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.
”Looking Similar,” a new visual recommendations model, has been launched in Recommend. This innovative feature analyzes images to find visually similar items, addressing the cold start problem by generating recommendations without needing events. Perfect for eCommerce companies aiming to create visually engaging shopping experiences. Available to all Recommend users starting today, this model marks our first step into image-based recommendations and search.
