Abstract: Example implementations may relate to systems and methods for re-ranking item recommendations. For example, a computer-implemented method may include receiving recommended items for items in a cart of an online checkout. The computer-implemented method can also include iteratively generating clusters of a pair of recommended item of the recommended items and a fulfillment center of the recommended item, and a pair of an item of the items in the cart and a fulfillment center of the item in the cart. The computer-implemented can further include generating embeddings for the clusters, and determining a cluster combination of cluster combinations with an optimal cost. The computer-implemented can additionally include re-ranking recommended items of the cluster combination with the optimal cost, and transmitting for displaying, on a device of a user, at least a subset of the recommended items of the cluster combination with the optimal cost, as re-ranked. Other embodiments are described.

Abstract: Some embodiments provide systems to provide metadata abstraction for a comparison interface. An example system includes a non-transitory machine-readable medium storing instructions that, when executed by a processing resource, may cause the resource to: compile textual metadata associated with an item, determine a ranked list of use cases for the item based in part on using one or more prompts to a language model, at least one of the one or more prompts includes the textual metadata, receive, via a client interface provided to a client device, a selection of the item and a comparison item; and select a highlighted use case to display with the item in a comparison interface of the client interface, wherein the highlighted use case is selected based on the ranked list associated with the item and a ranked list of use cases associated with the comparison item in the use case database.

Abstract: A method includes receiving candidate recommended items based on an item included in routine reorders of a user. For each candidate recommended item, dimension features for each dimension are embedded as embedding vectors. The dimensions include a user preference, a department affinity, a model suitability, and an item conversion potential dimension. The embedding vectors are combined into a feature vector input to a deep neural network (DNN) model to generate a ranking score representing a likelihood that the user engages with the candidate recommended item. Dimension-specific scores are obtained from intermediate layers of the DNN model including a user preference, a department affinity, a model suitability, and an item conversion potential score, which are output by a multilayer perceptron (MLP) network applied to respective embedding vectors. A final score is derived by incorporating the ranking score with respective weighted contributions. The candidate recommended items are ranked by the final scores.

Abstract: Example implementations relate to order prediction and automated cart creation. In an example, basket features, item features, and order features associated with a profile are inputted into a predictive model and daily order predictions are outputted by the predictive model. The daily order predictions are inputted into a grouping algorithm to output an order predictability. Profiles are segmented into respective order predictability cohorts of a plurality of order predictability cohorts based on respective order predictabilities. A cart may be automatically created for at least one daily order prediction associated with at least one profile when a respective order predictability cohort belongs to a predetermined order predictability cohort.

Abstract: A system including one or more processors and one or more non-transitory computer-readable storage devices storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations: generating, using a first machine learning model, a first output comprising a repurchase prediction for a user; generating, using a second machine learning model and using respective data of the repurchase prediction of the first machine learning model for the user, a second output comprising a time slot prediction for the user; initiating one or more reservation functions based at least in part on the first output and the second output; and transmitting an option to the user to access a GUI of a digital shopping cart system to reserve a reservation function of the one or more reservation functions. Other embodiments are described.

Abstract: System and method for time-aware deep learning are provided. A training data set including continuous-time data and a deep learning architecture are received. A trained deep learning model is generated using a temporal kernel approach. The temporal kernel approach includes constructing a temporal kernel based on the continuous-time data and composing the temporal kernel with a selected hidden layer of the deep learning architecture to generate a hidden output. The trained deep learning model is output for use in one or more machine learning tasks.

Abstract: A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform: outputting, by a machine-learning model, a probability that a user will re-order two or more items at a present time; determining the two or more items to recommend to the user based on the probability exceeding a predetermined threshold that the user will re-order the two or more items at the present time; sending instructions to display the two or more items to the user, wherein the user interface comprises a single-click option to add to an electronic cart the two or more items; and after receiving the single-click option from the user interface, adding the two or more items to the electronic cart. Other embodiments are disclosed.

Abstract: A computer-implemented method including automatically generating predictions of a respective number of items that a user is likely to reorder in each of groups of the items that a user has ordered historically. The method also can include ranking the groups based on the predictions of the respective number of the items the user is likely to reorder in each of the groups. The method additionally can include transmitting for display to the user a user interface including the groups of the items. Other embodiments are described.

Abstract: A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, perform certain acts. The acts can include obtaining training data. The acts also can include training candidate recommendation models and an adversarial exposure model using the training data. The acts additionally can include generating recommendations based on a selected recommendation model of the candidate recommendation models. Other embodiments are described.

Abstract: A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform: mapping each item of multiple items in a mixed-intent basket to a respective product type code (PT code); generating a respective list of complementary product type codes from each respective PT code; generating, using a complementary item algorithm, a respective candidate set of complementary items; detecting a platform-level configuration of a platform used by an electronic device of a user; loading, using diversity rotation, the respective quantity of complementary items onto a website carousel; and displaying the website carousel, as loaded, on the electronic device of the user, wherein the website carousel is sized to fit the platform-level configuration. Other embodiments are disclosed.

Abstract: Systems and methods including one or more processors and one or more non-transitory computer readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform: receiving a user request via a graphical user interface, the user request corresponding to a user search query for a product; determining whether a first processing machine of the system is operating in a first processing mode or a second processing mode; when the first processing machine is determined to be operating in the first processing mode, analyzing the user request via the first processing machine and using a process, to identify a candidate recommendation system to utilize by: determining a randomized strategy for one or more candidate recommendation systems based on a ratio of a number of the one or more candidate recommender systems, the randomized strategy to be stored in a collected history data; determining model parameters based on the collected history data; and

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: receiving in-session user activity entered into on an initial graphical user interface (GUI) from a user electronic device of a user; pre-processing the in-session user activity to determine one or more intents of the in-session user activity; comparing the one or more intents of the in-session user activity with one or more complementary intents; and coordinating displaying a complimentary GUI on the user device of the user based on the one or more complementary intents. Other embodiments are disclosed herein.

Abstract: A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform functions comprising: receiving one or more vectors representing one or more types of features for a pair of items; generating, using a similarity item model of a machine learning architecture, a prediction for a similar item, wherein the similarity item model combines a pair of separately trained machine learning models; combining a first output of the gradient boosted model and a second output of the neural network model to generate a similarity score for the pair of items; and transmitting the similar item to a first position on a carousel display of a website that concurrently displays the anchor item on the website. Other embodiments are disclosed.

Abstract: This application is directed to systems and methods for cross-category item recommendation or ranking. In some embodiments, a disclosed method includes receiving interaction data indicative of an interaction with an information item associated with an anchor item in a first category; in accordance with a determination that the first category is associated with a plurality of themes of a second category, applying at least one type selection model to determine a set of item types associated with the plurality of themes of the second category; generating an ordered list of recommended items of the second category based on the set of item types; and in response to the interaction data, enabling display of the ordered list of recommended items of the second category on a display of a client device. In some embodiments, a large language model is applied to determine the plurality of themes of the second category.

Abstract: Example implementations relate to generating keywords. An item data structure including textual information is received. A first context associated with the textual information is determined and a plurality of keywords is generated using a first trained model that receives the textual information and the first context. A plurality of matching item data structures including respective textual information corresponding to a plurality of matching items associated with the item is received. A set of reference keywords is generated using a second trained model that receives the respective textual information and one or more of second contexts. A relevancy score is determined between at least one keyword and the first context using the first trained model, and an interface that includes the at least one keyword is generated.

Abstract: Systems and methods of attribute extraction and labelling are disclosed. An input dataset is received and a plurality of preliminary attribute labels are generated for at least a first attribute of a first element in the input dataset. Each preliminary attribute label in the plurality of preliminary attribute labels is generated by one of a plurality of large language models (LLM). A final attribute label for the first attribute is generated based on a weighted combination of the plurality of preliminary attribute labels for the first attribute and a data structure representative of the first element is updated to include the final attribute label for the first attribute.

Abstract: In various embodiments, systems and methods for generating interfaces including similar elements are disclosed. An interface request identifying an anchor element is received and a set of similar elements for the anchor element identifier is generated by implementing an inference recommendation model generated by a Siamese wide and deep training framework. The inference recommendation model is configured to receive at least one recall set of candidate elements and generate a similarity score for each candidate element in the set of candidate elements and the anchor element. An interface including at least one similar element selected from the set of similar elements is generated and transmitted to a user device associated with the interface request.

Abstract: Systems and methods for providing item recommendations based on item images or uploaded images are disclosed. In some embodiments, a disclosed method includes: receiving, from a computing device, a recommendation request for recommending items to a customer; determining an anchor image based on the recommendation request; generating at least one query based on the anchor image; generating, using a language model, textual recommendation data based on the at least one query; generating, using at least one machine learning model, at least one ranked list of recommended items based on the textual recommendation data; and transmitting to the computing device the at least one ranked list of recommended items to be displayed to the customer.

Abstract: Systems and methods for generating an interface including recommended elements selected using generated element type relation labels are disclosed. An interface generation request including at least one element type is received and a set of recommended elements is generated based on element type relations between the at least one element type and additional element types associated with a network interface. The element type relations are generated by at least one large language model and at least one optimal relation generation prompt. An interface including the set of recommended elements is generated.

Abstract: System and methods for generating cohesive product recommendations are disclosed. In some embodiments, a disclosed method includes: storing, in a database, historical customer data associated with a customer, receiving an indication of a customer's selection of a first product, parsing and extracting first product description data from catalog description data, generating summary data of the first product description data, the summary data being a subset of the first product description data, and generating a plurality of recommended products based on the summary data, the historical customer data, and at least one business rule.