Abstract: A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform generating a training dataset comprising training quadruplets; generating a respective text feature vector for each of the four respective items for the each of the training quadruplets using a vector encoder; transforming the respective text feature vector for each of the four respective items; training the shared trainable parameters of the feature representation transformation model; receiving, from a user device a selection of an anchor item from the item catalog; determining, for the anchor item, one or more similar items or one or more complementary items; and sending instructions to display the one or more of the one or more similar items or the one or more of the one or more complementary items on the user device. Other embodiments are disclosed.

Abstract: A category recommender system includes a computing device configured to obtain customer information characterizing a customer's interactions on an ecommerce marketplace. The computing device is further configured to determine discovery category rankings for each category of items available on the ecommerce marketplace for the customer based on the customer information, determine repeat category rankings for each category of items available on the ecommerce marketplace for the customer based on the customer information, and determine item rankings for each item in the ecommerce marketplace based on the customer information. The computing device is further configured to merge the discovery category rankings, the repeat category rankings and the item recommendation rankings into final recommendations based on one or more predetermined merging criteria and provide the final recommendations to the customer.

Abstract: This application relates to apparatus and methods for automatically generating item information, such as item descriptions, and providing the item information to customers. For example, the embodiments may generate and provide personalized item descriptions to customers during conversational interactions in speech-based systems. In some examples, the embodiments determine entities (e.g., attributes) from item information, and apply trained machine learning processes to the extracted entities to generate textual data, such as item descriptions. For example, a computing device may apply a trained natural language processing, such as a trained transformer-based machine learning technique, to the extracted entities to generate the item descriptions. In some examples, the computing device applies post processing techniques to the generated textual data. The generated textual data may include descriptive phrases that are user friendly to customers in an e-commerce system.

Abstract: A seasonal recommender system includes a computing device configured to obtain periodic sales data characterizing a number of purchases made of each item of a plurality of items in a specified period and to obtain periodic buyers data characterizing a number of unique customers of each item in the plurality of items in the specified period. The computing device is further configured to determine a final item seasonality embedding for each item based on the periodic sales data and the periodic buyers data and to determine a final user seasonality embedding for each user based on the periodic purchase data. The computing device is further configured to determine a final user-item score for each item based on the final item seasonality embedding and the final user seasonality embedding and to send a recommendation to a user based on the final user-item score.

Abstract: This application relates to apparatus and methods for providing recommended items to advertise. In some examples, a computing device determines a first set of items for recommendation based on historical user data associated with a user, and a second set of items for recommendation based on real-time user session data for the user. The computing device may then determine a subset of the first set of items based on associated scores and a predetermined threshold number of first items that can be presented for optimal user interaction. The computing device may generate a set of item recommendations by combining the subset of the first set of items and at least one of the second set of items to present to the user as advertisements.

Abstract: This application relates to apparatus and methods for automatically determining and providing personalized digital recommendations including sponsored items. In some examples, a computing device receives a recommendation request. In response, the computing device determines an initial set of items for recommendation based on a relevance of associated items to the user and potential revenue from user interactions with the associated items. The computing device then generates final item recommendations by replacing at least one item of the initial set of items with a closest sponsored item that is selected based on a similarity of the closest sponsored item to the corresponding item. The final item recommendations are then presented to the user.

Abstract: This application relates to apparatus and methods for automatically determining item relevancy based on textual information. In some examples, a computing device receives a search query, and a plurality of items corresponding to the search query. The computing device may identify one or more features of the search query. The computing device may generate relevancy values for each of the items based on the features of the search query, and features of each of the plurality of items. For example, the computing device may generate, for each of the items, a plurality of relevance values, each relevance value generated based on a feature of the search query and corresponding features of the item. The computing device may transmit the generated relevancy values for the plurality of items. In some examples, the computing device may rank the plurality of items based on the generated relevancy values.

Abstract: In some examples, a system may be configured to generate one or more query attributes for a search query received from a computing device of a user. Additionally, the system may be configured to, based at least in part on historical data of the user including data characterizing one or more items associated with the user, generate relevant item data. In various examples, the relevant item data characterizing a set of relevant items. Moreover, the system may be configured to, based on the relevant item data, the historical data of the user and the one or more query attributes, implement a set of operations that generate a set of personalized search results associated with the search query.

Abstract: A system and method of generating user personalized search results is disclosed. A search query including one or more words is received and a set of relevance-based search results is generated in response to the search query. One or more query attributes are generated for the search query. Historic data for a user associated with the search query is received and a set of personalized search results is generated from the set of relevance-based search results based on the query attributes and the historic data for the user. The historic data includes one or more items associated with the user.

Abstract: This application relates to apparatus and methods for automatically determining and providing carousels specifically curated for a user. In some examples, a computing device obtains user transaction data identifying in-store and/or online transactions, and user engagement data identifying user interactions with items and carousels from user's prior sessions. The computing device determines a sequential order for presentation of carousels with a set of item recommendations. For example, the computing device scores each potential carousel based on prior user interactions and transactions with items and carousels. The carousels are then ranked and subsequently presented to the user based on their corresponding scores.

Abstract: A method including receiving a basket including basket items selected by a user from an item catalog. The method also can include grouping the basket items of the basket into categories based on a respective item category of each of the basket items. The method additionally can include randomly sampling a respective anchor item from each of the categories. The method further can include generating a respective list of complementary items for the respective anchor item for the each of the categories based on a respective score for each of the complementary items generated using two sets of trained item embeddings for items in the item catalog and using trained user embeddings for the user. The two sets of trained item embeddings and the trained user embeddings can be trained using a triple embeddings model with triplets.

Abstract: This application relates to apparatus and methods for generating preference profiles that may be used to rank search results. In some examples, a computing device obtains browsing session data and determines items that were engaged, such as items that were viewed or clicked. The computing device obtains item property data, such as product descriptions, for the items, and applies a dependency parser to the item property data to identify portions that include certain words, such as nouns or adjectives, which are then identified as attributes. The computing device generates attribute data identifying portions of the item property data as item attributes. In some examples, the computing device applies one or more machine learning algorithms to the session data and/or search query to identify item attributes. The computing device may generate a profile that includes the item attributes, and may rank search results based on the attribute data, among other uses.

Abstract: A method being implemented via execution of computing instructions configured to run at one or more processors and stored at one or more non-transitory computer-readable media. The method can include training two sets of item embeddings for items in an item catalog and a set of user embeddings for users, using a triple embeddings model, with triplets. The triplets each include a respective first user of the users, a respective first item from the item catalog, and a respective second item from the item catalog, in which the respective first user selected the respective first item and the respective second item in a respective same basket. The method also can include randomly sampling an anchor item from a category of items selected by a user. The method additionally can include generating a list of complementary items using a query vector associated with the user and the anchor item.

Abstract: Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform: inputting one or more pairs of digital images into a neural network; determining, using the neural network, a respective contrastive loss for each respective pair of digital images of the one or more pairs of digital images; receiving one or more new digital images; and determining, using the neural network, the one or more new digital images and the respective contrastive loss, at least one image to which the one or more new digital images is similar. Other embodiments are disclosed herein.

Abstract: A method including building a recommendation triggering model. The method can include receiving, via a user device of a user through a network, an add-to-cart command associated with an anchor item for the user. The method further can include determining, in real-time after receiving the add-to-cart command, a recommendation for one or more complementary items of the anchor item for the user. The method also can include determining, in real-time after determining the recommendation, a recommendation confidence for the recommendation. The method additionally can include after determining the recommendation confidence, when the recommendation confidence is positive, transmitting, in real-time through the network, the one or more complementary items to be presented to the user via the user device. The method likewise can include after determining the recommendation confidence, when the recommendation confidence is not positive, refraining from transmitting the one or more complementary items to the user.

Abstract: A method including training two sets of item embeddings for items in an item catalog and a set of user embeddings for users, using a triple embeddings model, with triplets. The triplets each can include a respective first user of the users, a respective first item from the item catalog, and a respective second item from the item catalog, in which the respective first user selected the respective first item and the respective second item in a respective same basket. The method also can include generating an approximate nearest neighbor index for the two sets of item embeddings. The method additionally can include receiving a basket including basket items selected by a user from the item catalog. The method further can include grouping the basket items of the basket into categories based on a respective item category of each of the basket items. The method additionally can include randomly sampling a respective anchor item from each of the categories.

Abstract: A method including building a recommendation triggering model. The method can include receiving, via a user device of a user through a network, an add-to-cart command associated with an anchor item in a session by the user. The method further can include determining, in real-time after receiving the add-to-cart command, a recommendation for one or more complementary items based at least in part on: (a) the anchor item; and (b) a user profile of the user. The method also can include determining, in real-time after determining the recommendation, a recommendation confidence for the recommendation based at least in part on one or more of: (a) the user profile; (b) the anchor item; (c) the one or more complementary items; or (d) one or more feedbacks from the user associated with one or more prior recommendations in the session.

Abstract: Many embodiments can include a system. In some embodiments, the system can comprise one or more processors and one or more non-transitory storage devices storing computing instructions are disclosed.

Abstract: A method including receiving a basket including basket items selected by a user from an item catalog. The method also can include grouping the basket items of the basket into categories based on a respective item category of each of the basket items. The method additionally can include randomly sampling a respective anchor item from each of the categories. The method further can include generating a respective list of complementary items for the respective anchor item for the each of the categories based on a respective score for each of the complementary items generated using two sets of trained item embeddings for items in the item catalog and using trained user embeddings for the user. The two sets of trained item embeddings and the trained user embeddings can be trained using a triple embeddings model with triplets.

Abstract: A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform receiving from an item catalog database a respective item description and respective attribute values for each item of a set of items; generating text embeddings using a text embedding model to represent the respective item description and the respective attribute values; generating a graph of the set of items from the item catalog database connected by a set of edges; training the text embedding model and a machine learning model using a neural loss function based on the graph; and automatically determining, based on the machine learning model, as trained, a gender label for each first item in which the gender classification is unlabeled and in which a respective quantity of respective attribute values for the each first item is at least a predetermined threshold. Other embodiments are disclosed.