Recommendation Logics

Default model ensemble aiming to work well in most common use cases. It is an ensemble of collaborative filtering and content-based recommendation, backed by popularity-based models when there's not enough data in the given context. The ensemble is being continuously optimized by AI so it automatically adapts to incoming data.

Universal model ensemble suitable for putting recommendations on the homepage / welcome-screen scenarios.

Universal model ensemble suitable for user-based recommendations reflecting the personal tastes of the current user.

Universal model ensemble suitable for either recommending items which are similar to the given item (in case of Items-to-Item recommendation), or recommending users who are similar to the given user (in case of Users-to-User recommendation).

Universal model suitable for recommending globally popular items, taking into account all interaction types. More important actions (purchases, cart-additions) have higher weight for computing the popularity than less important actions (detail-views).

Universal model ensemble suitable for recommending globally popular segments.

Model returning the list of recently viewed items for a particular user.

Model recommending similar items based on visual similarity (using deep-learning neural networks to process the images provided through the image properties). While the image similarity can take part in other Logics as well, in recombee:visually-similar, it is explicitly used as the primary model. Image processing may take some time. Therefore, changes in image item properties do not take effect in real-time. The functionality is still in beta mode.

Model recommending similar items based on item properties (numerical values, sets, and texts). While property values can take part in other Logics, in recombee:similar-properties, they are explicitly used as the primary data source for recommending similar items or uses. Various machine-learning methods, including NLP deep-learning networks that process unstructured text descriptions, are used to compute the similarities.

Model ensemble suitable for recommending items in periodic e-mailing campaigns. It contains fine-tuned rotation settings so that the set of recommended items for a particular user changes with each e-mail sent.

By default, rotation only takes into account recommendations (e-mails) at most 14 days old. Should a longer time period be needed for your use case, kindly contact support@recombee.com.

Model suitable for recommending items ordered by a ReQL expression given as a booster

Recommends items that are contextually related to the Item Segment and should be of interest to the user. Items may belong to the Segment or be outside it if they are strongly relevant.

Consider using recombee:personal-from-segment if you want recommendations strictly limited to items within the Segment.

Examples:

• News: For the "Climate Change" Segment, recommend articles about renewable energy (inside the Segment) or related topics like electric vehicles (outside the Segment).
• Music: For the "Jazz" Segment, recommend jazz-related songs, including classic tracks (inside the Segment) or modern experimental pieces (outside the Segment).
• E-commerce: For the "Digital Cameras" Segment, recommend products like digital cameras (inside the Segment) or accessories like tripods, lenses, or lighting kits (outside the Segment).
• Video Streaming: For the "Science Fiction" Segment, recommend sci-fi movies (inside the Segment) or related dystopian thrillers (outside the Segment).

Recommends items from the Item Segment, tailored to the user's preferences.

Consider using recombee:related-to-segment if you don't need all the recommended items to belong to the Segment.

Examples:

• News: For the "Environmental News" Segment, recommend articles on climate policy or renewable energy that align with the user’s reading history.
• Music: For the "Jazz" Segment, recommend jazz songs matching the user’s listening habits.
• E-commerce: For the "Digital Cameras" Segment, recommend digital cameras the user is most likely to be interested in, based on their browsing and purchase history.
• Video Streaming: For the "Science Fiction" Segment, recommend sci-fi movies that match the user’s preferences.

Recommends the most popular items within the Item Segment, based on overall engagement. Use this Logic to highlight trending or widely appealing items.

Examples:

• News: Most-read articles from the "World Politics" Segment.
• Music: Most-streamed tracks from the "Rock" Segment.
• E-commerce: Best-selling smartphones in the "Smartphones" Segment.
• Video Streaming: Most-watched action movies in the "Action Movies" Segment.

This Composite Logic provides a comprehensive recommendation in a single response consisting of:

• Top Segment for the User: It identifies and returns the most relevant Item Segment (e.g., the top category) for the user from the specified Segmentation.
• Top Items from the Segment: Along with the Segment, it also returns a list of the top items within that Segment.

This Logic is ideal for recommending a section and its content together, making it particularly useful for personalized homepage sections.

If you want to display multiple distinct sections in a personalized order on your homepage, you can achieve this by making multiple Composite Recommendation requests within a single Batch call.

For more specific use cases, such as "Videos From The Top Genre For You" or "Products from the Top Category For You," there are specialized Logics available.

This Composite Logic delivers two results within a single response consisting of:

• Item the User Interacted With: The Logic selects and returns an item that the user has interacted with, based on the interaction types specified by the interactionTypes parameter (e.g., Watched, Purchased, Liked).
• Top Related Items: Simultaneously, it returns a list of top items related to that specific interacted item.

This Logic is ideal for general "Because You..." scenarios, where recommendations are tailored based on the user's previous interactions. For more specific use cases, such as "Because You Bought" or "Because You Watched", there are specialized Logics available.

This Logic is designed for infinite swiping feed experiences (such as reels or short-form video feeds), where users continuously browse content and can express feedback through likes or dislikes.

It optimizes recommendations in real time based on a configurable combination of user engagement (likes, number of viewed items, purchases), and time spent consuming content.

Smart personalized fulltext search which takes into account both the search query and the personal preferences of the user.

Non-personalized fulltext search, based purely on how well the search query is matched.

Semantic search utilizes a large language model (LLM) to improve search accuracy by understanding the intent and context behind user queries.

Instead of relying solely on keyword matches, the system comprehends the semantic meaning of queries and retrieves results that align with the user's intentions. This advanced Logic delivers more accurate, context-aware search results, even when the query terms differ from the content in the database.

This Logic can be enabled upon request for Recombee Premium customers.

Model ensemble suitable for recommending products on homepage/welcome page in E-Commerce and online retail systems.

See the Scenario Recipe guide for more information.

Model ensemble suitable for recommending similar products (alternatives) to a source (currently viewed) product.

See the Scenario Recipe guide for more information.

Model ensemble suitable for recommending compatible/complementary products. In user-based case, the products are compatible with those that the user has already put to the shopping cart. In item-based case, they are compatible with the source (currently viewed) item.

See the Scenario Recipe guides for the product detail and cart use cases.

Model suitable for recommending globally most purchased items.

See the Scenario Recipe guide for more information.

Recommends users with similar purchasing behavior as the source user.

This Composite Logic provides personalized product recommendations within a single response, tailored to the user's shopping preferences:

• Top Category for the User: It identifies and returns the most relevant product category for the user, based on their interaction history such as views, purchases, or cart additions.
• Top Products from the Category: Along with the top category, it also returns a list of the top products within that category.

This logic is ideal for scenarios where you want to recommend both a product category and its associated products, making it particularly useful for personalized sections on e-commerce homepages.

If you want to display multiple rows for distinct top categories in a personalized order, you can achieve this by making multiple Composite Recommendation requests within a single Batch call.

It is expected that the Item Segmentation selected in the configuration represents the product categories relevant to your e-commerce platform.

See the Scenario Recipe guide for more information.

This Composite Logic delivers personalized product recommendations in a single response:

• Top Segment for the User: It identifies and returns the most relevant Segment for the user. Depending on the selected Item Segmentation, this Segment could be a Brand, Tag, or other attributes.
• Top Products from the Segment: Along with the top Segment, it also returns a list of the top products associated with that Segment.

This Logic is ideal for recommending both a Segment, such as a brand, and its associated products. For example, it can be used to recommend "Top Products from Your Favorite Brand …" This makes it particularly useful for personalized sections on e-commerce homepages.

If you want to display multiple rows for distinct top Segments (e.g., different brands or tags), you can achieve this by making multiple Composite Recommendation requests within a single Batch call.

It is expected that the Item Segmentation selected in the configuration represents Segments like brands, tags, or other key attributes relevant to your e-commerce platform.

This Composite Logic provides personalized product recommendations based on the user's past purchases, all within a single response:

• Product the User Purchased: It identifies and returns a product that the user has previously purchased.
• Top Complementary Products: Along with the purchased product, it returns a list of complementary products, such as accessories or related items that pair well with the original purchase.

This Logic is ideal for scenarios like "Because You Purchased …," where recommendations are tailored to the user's purchasing history and focus on products that complement what the user has already bought.

Model ensemble suitable for recommending partially watched movies or episodes, or the next episode from a watched series.

See the Scenario Recipe guide for more information.

Model ensemble suitable for recommending personalized rows on the homepage or browse pages.

Rows with specific content (e.g. award-winning movies) can be set up by applying filters.

See the Scenario Recipe guide for more information.

Model ensemble suitable for recommending favorite segments (genres, actors, ...) for a specific user.

A particular segmentation must exist beforehand.

See the Scenario Recipe guide for more information.

Model ensemble suitable for recommending globally popular items.

See the Scenario Recipe guide for more information.

Model ensemble suitable for recommendations of hand-picked editorial content.

See the Scenario Recipe guide for more information.

Model ensemble suitable for recommending similar assets on the asset detail page.

See the Scenario Recipe guide for more information.

Model ensemble suitable for end-of-playback recommendations embedded in a video player.

See the Scenario Recipe guide for more information.

Model ensemble suitable for reverse-chronological listing episodes of a particular series.

Smart personalized full-text search suitable for searching movies, series, and episodes.

See the Scenario Recipe guide for more information.

Smart personalized full-text search suitable for searching segments (genres, actors, ...).

A particular segmentation must exist beforehand.

Model ensemble suitable for sending personalized emails with personalized content for the user. It contains fine-tuned rotation settings so that the set of recommended assets for a particular user changes with each e-mail sent.

See the Scenario Recipe guide for more information.

This Composite Logic delivers a comprehensive recommendation in a single response consisting of:

• Top Genre for the User: It identifies and returns the most relevant genre or category for the user, based on their viewing history and preferences.
• Top Videos from the Genre: Along with the top genre, it also returns a list of the top videos within that genre or category.

This Logic is ideal for recommending both a genre and its associated videos together, making it particularly useful for personalized sections on the homepages of video streaming platforms.

If you wish to display multiple rows for distinct top genres in a personalized order, you can achieve this by making multiple Composite Recommendation requests within a single Batch call.

It is expected that the Item Segmentation selected in the configuration represents the genres or categories of the videos.

See the Scenario Recipe guide for more information.

This Composite Logic delivers a comprehensive recommendation in a single response consisting of:

• Top Segment for the User: It identifies and returns the most relevant Segment for the user. Depending on the selected Item Segmentation, this could be a Director, Theme, Tag, Actor, etc.
• Top Videos from the Segment: Along with the top Segment, it also returns a list of the top videos associated with that Segment.

Based on the selected Item Segmentation, this Logic can be used for rows such as “Your Favorite Director … And Their Movies” or “Videos About Your Favorite Topic …”.

If you wish to display multiple rows for distinct top Segments in a personalized order, you can achieve this by making multiple Composite Recommendation requests within a single Batch call.

This Composite Logic delivers personalized recommendations based on a user's previous watching activity, all within a single response consisting of:

• Video the User Watched: It selects and returns a video that the user has recently watched.
• Top Related Videos: Along with the watched video, it also returns a list of top videos related to that specific video, offering content the user is likely to be interested in.

This Logic is ideal for scenarios like “Because You Watched …,” where recommendations are tailored to the user’s recent watching history.

The watched video is determined based on View Portion interactions, and you can refine this by specifying the maxDaysAgo and minWatchedPercentage parameters to define which View Portions are considered. If no such View Portion exists, an empty recommendation is returned.

If you want to display multiple sets of related videos based on different watched content, you can achieve this by making multiple Composite Recommendation requests within a single Batch call.

See the Scenario Recipe guide for more information.

Model ensemble optimized for high-visibility placements.

It ensures users stay connected to the most significant news stories while maintaining a personalized experience based on their past behavior.

It caters to frequent visitors by consistently offering fresh, relevant content.

See the Scenario Recipe guide for more information.

Model ensemble providing individualized content suggestions, carefully selecting the best choices from the catalog to match each user's specific interests.

It is particularly suitable for the For You scenarios, where personalized recommendations are essential.

Model ensemble recommending personalized articles most likely to engage users after they finish reading the current article.

It considers the content of the current article and analyzes both recent and long-term user behavior to encourage continued reading and extend visit duration.

Suitable for Continue Reading or You Might Also Like scenarios.

See the Scenario Recipe guide for more information.

Model ensemble recommending news articles that are currently trending, providing users with content that is gaining widespread interest and should not be missed.

Suitable for the Trending Articles scenario.

Model ensemble recommending articles that are highly popular within a specified time period.

It is ideal for Popular Articles scenario, allowing users to see what others find interesting.

Model ensemble showcasing the most recently published articles, ensuring users stay updated with the latest content.

Suitable for the Latest News scenario.

See the Scenario Recipe guide for more information.

Model ensemble recommending articles that are related to the current article, providing users with a seamless continuation of their reading experience on a given topic.

Suitable for the Related Articles scenario.

Model ensemble recommending categories relevant to the user based on their previously read articles.

Suitable, for example, for personalized re-ordering of sections on the homepage.

Assumes the scenario is configured with an Item Segmentation representing article categories.

Model ensemble suitable for recommendations of hand-picked editorial content.

See the Scenario Recipe guide for more information.

The news:emailing Logic is designed to provide a personalized selection of articles for email newsletters.

This Logic combines:

• Personalized recommendations based on the user's reading history and preferences.
• Key unread articles to ensure the user stays informed about the most important news they haven’t seen yet.

To maintain content freshness, it is advisable to apply a Filter that limits the selection to recently published articles, depending on the email frequency. For example, for a daily digest, you can filter for articles published within the last 24 hours.

See the Scenario Recipe guide for more information.

This Composite Logic provides a comprehensive recommendation in a single response consisting of:

• Top Segment for the User: It identifies and returns the most relevant Item Segment (e.g., the top category) for the user from the specified Segmentation.
• Top Items from the Segment: Along with the Segment, it also returns a list of the top items within that Segment.

This Logic is ideal for recommending a section and its content together, making it particularly useful for personalized homepage sections.

If you want to display multiple distinct sections in a personalized order on your homepage, you can achieve this by making multiple Composite Recommendation requests within a single Batch call.

For more specific use cases, such as "Videos From The Top Genre For You" or "Products from the Top Category For You," there are specialized Logics available.

See the Scenario Recipe guide for more information.

This Composite Logic delivers personalized news article recommendations in a single response:

• Top Segment for the User: It identifies and returns the most relevant Segment for the user. Depending on the selected Item Segmentation, this Segment could be based on attributes such as authors or tags.
• Top Articles from the Segment: Along with the top Segment, it returns a list of the top articles associated with that Segment.

This Logic is ideal for recommending both a Segment (e.g., a favorite author or popular tag) and its associated articles. For example, it can be used for scenarios like "Top Articles from Your Favorite Author".

If you wish to display multiple distinct Segments in a personalized order, you can achieve this by making multiple Composite Recommendation requests within a single Batch call.

This Composite Logic delivers personalized news article recommendations based on the user's previous reading activity, all within a single response:

• Article the User Read: It selects and returns an article that the user has previously read.
• Top Related Articles: Along with the read article, it returns a list of top related articles focused on the same or similar topics, offering follow-up content or deeper insights into the subject the user has already shown interest in.

This Logic is ideal for scenarios like “Because You Read …,” where recommendations are tailored to the user’s reading history. It can recommend follow-up articles, related pieces, or additional articles on similar subjects.

Model ensemble suitable for recommending products on homepage/welcome page of a Classified advertising site.

Model ensemble suitable for recommending picked ads right for the given user. Can be used on different places, such as in-category recommendation when augmented with appropriate ReQL filter.

Model ensemble suitable for recommending ads that are similar to the one which is currently viewed.