Walmart Apollo, LLC

Xuan Cao

Wei Shen

Lu Wang

Georgios Rovatsos

Jingsi Zhang

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

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 cause the one or more processors to perform (1) receiving a request to generate one or more campaigns; (2) determining one or more predicted bids for one or more keywords in the one or more campaigns; (3) adjusting the one or more predicted bids for the one or more campaigns; (4) pacing the one or more predicted bid, as adjusted, for the one or more campaigns; and repeating (2)-(4) at one or more periodic intervals. Other embodiments are disclosed herein.

Systems and methods for improved online predictions

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 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.

Growing community of inventors

Santa Clara, CA, United States of America

Xuan Cao