Walmart Apollo, LLC

Shirpaa Manoharan

Kannan Achan

Evren Korpeoglu

Kaushiki Nag

Sushant Kumar

Venkata Syam Prakash Rapaka

Rajagopal Manda

Abhimanyu Mitra

Afroza Ali

Rahul Ramkumar

Vidya Sagar Kalidindi

Surya Yalla

Vimitha Manohar

Veena Santhoshi Rajasekar

The disclosed subject matter relates to a system and method for personalizing customer experience at a retailer's physical location in order to increase sales and customer satisfaction. The personalization is based upon classification of customer's online interaction with the retailer. Upon detecting the customer's presence at the retailer's physical location, data of the customer's online interactions is retrieved and classified based on the type of online interactions and temporal characteristics. Push content is transmitted to the customer, the push content being based upon at least the classification and data associated with retailer's physical location.

Methods and apparatus for providing context aware personalized in-store customer experience

A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when run on the one or more processors, cause the one or more processors to perform functions including: reconfiguring a webpage as an undirected graph; identifying a cyclic dependency in the undirected graph; iterating processing one or more inferences over the cyclic dependency for each pair of the nodes of the set of the nodes; breaking one or more of edges of the undirected graph; determining, based at least in part on compatibility functions of the one or more edges remaining after breaking the one or more of the edges, a probability of the webpage having exceeded a predetermined threshold to cause a user to take an action; and sending instructions to display the webpage. Other embodiments are described.

Whole page personalization with cyclic dependencies

Systems and methods for customizing an interface are disclosed. Interaction data is received for at least one interaction with a network environment and an intent of the at least one interaction is identified based on the interaction data. A layout is selected for a user interface based on the identified intent. The layout includes at least one zone. The at least one zone of the layout is populated with one or more modules and the each of the one or more modules is populated with content based on the identified intent

Systems and methods for layout customization

This application relates to apparatus and methods for providing recommended items to advertise. In some examples, a computing device determines a plurality of first values for a corresponding plurality of first items based on the user's engagement with each of the first items. The computing device may then determine a subset of the plurality of first items based on the first values. The computing device may receive a search request and determine a plurality of second values for a plurality of second items based on the search request. The computing device may determine a plurality of third values for the subset of items based on the plurality of second values for the plurality of second items and the user's engagement with each of the subset of items. The computing device may determine the recommended items based on the plurality of second values and the plurality of third values.

Methods and apparatus for generating item recommendations based on real-time inference of machine learning models

A system and method for content selection and presentation is disclosed. A system receives a plurality of content elements configured for presentation in at least one content container and selects one of the plurality of content elements for presentation in the at least one content container. The one of the plurality of content elements is selected by a trained selection model configured to use Thompson sampling. An interface including the selected one of the plurality of content elements is generated.

Robust reinforcement learning in personalized content prediction

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: modeling a webpage as a random field, wherein the random field comprises an undirected graph comprising nodes and edges; identifying a cyclic dependency in the undirected graph, wherein the cyclic dependency involves at least three of the nodes; breaking one or more of the edges of the undirected graph that connects the at least three of the nodes in the cyclic dependency; determining a probability of the webpage having exceeded a predetermined threshold based on compatibility functions of the edges, as updated; and sending instructions to display the webpage based at least in part on the probability of the webpage having exceeded the predetermined threshold. Other embodiments are described.

This application relates to apparatus and methods for automatically determining and providing, for a given anchor item, a ranking of items. The ranking may include sponsored items. In some examples, a computing device receives a request for items for an anchor item. The computing device determines a relevancy of a plurality of recommended items and sponsored items. The computing device also determines a cost value for the sponsored items. The computing device determines ranking values for the plurality of recommended items and sponsored items based on the relevancy values and the cost values, and ranks the items based on the ranking values. In some examples, the computing device updates the final item ranking based on the application of one or more rules. The computing device transmits the final item ranking to a web server. The web server displays advertisements for the items in ranked order.

Methods and apparatus for electronically determining item advertisement recommendations

This application relates to apparatus and methods for providing a unified serving platform that allows for the reusability of machine learning models across a plurality of websites to determine personalized content. For example, a computing device trains a machine learning model with session data identifying browsing events and transaction data identifying purchasing events for a plurality of users. The computing device receives and stores session data and transaction data associated with a first website for the customer. The computing device may then receive a request for content to display to the customer on a second website. The computing device generates label data based on the session data and transaction data associated with the first website, and executes the trained machine learning model with the label data. Based on execution of the trained machine learning model, the computing device generates content to display on the second website, and transmits the content.

Methods and apparatus for providing a unified serving platform across multiple tenants and touchpoints

A method can include modeling a webpage as a random field. The random field can include an undirected graph including two or more nodes and one or more edges. A goodness function can be associated with one or more webpage elements. Each edge of the one or more edges can include a compatibility function based at least in part on the one or more goodness functions of two different nodes of the two or more nodes. The method also can include determining a probability of the webpage having exceeded a predetermined threshold based at least in part on one or more of the compatibility functions of the one or more edges. Other embodiments are disclosed.

Systems and methods for whole page personalization

Systems and methods including one or more processors and one or more non-transitory computer readable storage devices storing computing instructions configured to run on the one or more processing modules and perform acts of: gathering historical data, which can comprise interactions of a user with a first graphical user interface at a first time; storing the historical data which can comprise the interactions of the user with the first graphical user interface as at least one historical feature vector; gathering in-session data, which can comprise interactions of the user with a second graphical user interface at a second time later than the first time; storing the in-session data which can comprise the interactions of the user with the second graphical user interface as at least one in-session feature vector; determining an intent of the user using the at least one historical feature vector and the at least one in-session feature vector; and transmitting instructions to display a third graphical user interface for the user based upon the intent of the user. Other embodiments are disclosed herein.

Systems and methods for altering a GUI in response to in-session inferences

In some embodiments, a method can comprise receiving a search query from a search by a user during a browse session, receiving one or more items from an item database in response to the search query, and receiving one or more previous search queries from a search database, the one or more previous search queries related to the search query. In many embodiments, the method can further comprise determining a purchase probability associated with a first item of the one or more items based at least in part on a first item score for the first item, ranking the one or more items based at least in part on the purchase probability associated with the first item of the one or more items, and facilitating display of the ranking of the one or more items. Other embodiments of related methods and systems are also provided.

Growing community of inventors

Santa Clara, CA, United States of America

Shirpaa Manoharan