Walmart Apollo, LLC

Back Micro Solutions LLC

Other

Complatform LLC

Yahoo Ad Tech LLC

Inbit, Inc.

Wal-mart Stores, Inc.

Yahoo Assets LLC

Gula Consulting Limited Liability Company

Lu Wang

Jinsheng Wang

Wei Shen

Zhao Zhao

Xuan Cao

Thanawat Kaewka

Gautham Krishna

Muchen Liu

Chenxi Liu

Vahid Jalalibarsari

Changzheng Liu

Jingsi Zhang

Jing Lu

Yuan Xie

Liu Munchen

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 operations including: reducing, using a multilayer perceptron, a dimension of feature embeddings for an item to generate a representation vector; extracting, using a recurrent neural network, sequential data from traffic features for the item; inputting the representation vector and the sequential data into a multilayer neural network, wherein the first scoring layer outputs one or more first performance metrics based on offline learning; and re-purposing the output of the second ReLU activation function of the multilayer neural network by feeding the output of the second ReLU activation function into a second scoring layer to output one or more second performance metrics based on online learning. Other embodiments are disclosed.

Deep learning-based revenue-per-click prediction model framework

One or more computing devices, systems, and/or methods are provided. In an example, an email addressed to an email address associated with an email account is received. A request to display the email is received from a client device associated with the email account. In response to receiving the request to display the email, the email and a social interaction interface are displayed via an email interface on the client device. The social interaction interface includes one or more social interaction features. The one or more social interaction features include a commenting feature, a feedback feature and/or a chat feature.

System and method for providing social interaction interface for emails

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 operations: segmenting each respective user of one or more users into a respective user state of one or more respective user states; predicting, using a machine learning LTV update model, a respective LTV for each respective user of the one or more users; determining a respective transition path from the respective user state of the respective user to a different respective user state; determining a respective online advertisement to transition a respective user of the one or more users from a respective transition state to the different respective user state; and displaying the respective online advertisement for the respective user of the one or more users. Other embodiments are disclosed herein.

Systems and methods for determining customer lifetime value

In some aspects, the techniques described herein relate to a method including: receiving, at a processor, a message sent by a sender to a user, the message including a message content item related to an item of interactive content; displaying, by the processor, the message to the user through a user interface (UI); receiving, by the processor, an input corresponding to an interaction between the user and the message content item in the UI, the input directing the processor to generate the interactive content; obtaining, by the processor, interactive content data related to the interactive content; generating, by the processor, the interactive content based on the interactive content data; and displaying, by the processor, the generated interactive content to the user through the UI.

Method and system to provide interactivity for embedded content

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 acts of storing, for each respective customer of one or more customers, respective customer information in a customer database; predicting, using a machine learning lifetime value (LTV) update model, a respective LTV for each respective customer of the one or more customers; determining an online advertisement for each respective customer of the one or more customers using the respective LTV, as predicted, for each respective customer of the one or more customers; and coordinating displaying the online advertisement for at least a portion of the one or more customers. Other embodiments are disclosed herein.

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 extracting meta features for an item to generate sparse feature embeddings for the item; reducing, using a multilayer perceptron, a dimension of the sparse feature embeddings to generate a representation vector for the meta features; extracting, using a recurrent neural network, sequential data from dense traffic features for the item over a period of time; and inputting the representation vector for the meta features and the sequential data from the dense traffic features into a multilayer neural network with a rectified linear unit (ReLU) activation function and a scoring layer to generate one or more performance metrics for the item. Other embodiments are disclosed.

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 one or more objectives and one or more constraints from a user electronic device of a user; generating a combined objective using the one or more objectives; calculating, using the combined objective, a return per click for an advertisement campaign; determining one or more bids based on (a) the return per click for the advertisement campaign and (b) a return on advertising spend for the advertisement campaign; estimating, using a first predictive algorithm and the one or more bids, an average cost per click; estimating an expected number of clicks for the advertisement campaign based on the average cost per click; determining a total amount used of the one or more constraints for the one or more bids based on the expected number of clicks for the advertisement campaign; and when the total amount used of the one or more constraints for the one or more bids exceeds at least one of the one or more constraints, lowering the one or more bids. Other embodiments are disclosed herein.

Systems and methods for training of multi-objective machine learning algorithms

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 a request for a machine learned prediction for an item; determining that a number of entries in item user interaction data of the item is below a predetermined number-of-entries threshold; incorporating category interaction data of a hierarchical category of the item from a predetermined time period into the item user interaction data of the item; determining an initial machine learned prediction for the item using at least the category interaction data, as incorporated into the item user interaction data; and facilitating altering a graphical user interface (GUI) of an electronic device using the initial machine learned prediction for the item. Other embodiments are disclosed herein.

Systems and methods for bootstrapped machine learning algorithm training

Systems and methods including one or more processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of obtaining a uniform resource locator (URL) of a first webpage that is shown on a graphical user interface and that is external to a website of a retailer (where, in some embodiments, the URL is obtained from a referral website or is entered by a user from a chat window or search box), using a web scraper to extract web text displayed on the first webpage on the graphical user interface, processing the web text displayed on the first webpage on the graphical user interface to determine an interest of a user, using a set of rules to determine items related to the web text displayed on the first webpage on the graphical user interface, and coordinating displaying the items on a second webpage to promote the items as related to the interest of the user, where the second webpage is internal or external to the website of the retailer.

Systems and methods for processing or mining visitor interests from graphical user interfaces displaying referral websites

Systems and methods including one or more processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of: categorizing a plurality of customers based on whether or not each customer of the plurality of customers had (1) an online store transaction with a retailer, (2) an offline store transaction with the retailer, or (3) an online interaction with the retailer within a predetermined period of time; predicting, using a lifetime value (LTV) update model, a LTV for customers who did have an interaction or transaction with the retailer; predicting, using one or more LTV decay functions, the LTV for customers who did not have an interaction or transaction with the retailer; and determining an online advertisement for each customer based on the LTV for each customer.

Method and system for online helpdesk are disclosed. According to one embodiment, a CustomerOps platform is designed to provide customer operations to a plurality of businesses large or small. By providing a server or a cluster of servers, various activities (e.g., inquiries and responses) between a user and a business are captured and the data stream thereof is archived to a designated server. The stored data can be retrieved to view the various activities so as to engage the user contextually whenever there is a need. Such a CustomerOps platform facilitates efficient and more relevant human or automated assistance when the user desires to get engaged with the business that provides a service/product interesting to the user.

Method and system for online helpdesk

Method and system for electronically engaging customers for multiple business entities are disclosed. According to one embodiment, a CustomerOps platform is designed to provide customer operations to a plurality of computer applications (e.g. websites with multiple webpages, desktop programs and mobile applications) operated by respective businesses large or small. By providing a server or a cluster of servers, various activities by a user interacting with a designated computer application are captured and the data stream thereof is transported to a designated server. The stored data can be retrieved to assist the business of the designated computer application to engage the user contextually whenever there is a need. Such a CustomerOps platform facilitates efficient and more relevant human or automated assistance when the user desires to get engaged with the business that provides the designated computer application.

Method and system for electronically engaging customers

A group communication system is disclosed. The group communication system integrates a number of electronic communication tools to meet various communications among registered users. The group communication system allows groups of users to be formed, where members of each of the groups can participate in various communications with other members. Communications within a group are considered private to all members in the group.

Method and system for forming groups in collaborative communication system

Techniques for electronically engaging customers across all different platforms are disclosed. Based on unique device identifiers captured together with interactions by users with one or more applications provided by a business, a message prepared in a first format is automatically converted to a corresponding message in a second format according to what the devices the user have been interacting with can support. Depending on implementation, the message may be a response by the business to an inquiry from a user or a promotion by the business to be distributed to a group of selected users maintained by the business. The interactions include activities a user has had with one or more of the applications provided by the business and provide the statistical or actual data for the business to determine the group of users to receive the message.

Growing community of inventors

Sunnyvale, CA, United States of America

Lu Wang