Home Depot Product Authority, LLC

Estelle Afshar

Huiming Qu

Matthew Hagen

Shubham Agarwal

Shawn Coombs

Rini Devnath

Ramesh Gundeti

Prat Vemana

Kevin Hofmann

Jiaqi Wang

Ala Eddine Ayadi

A computer-implemented method for determining image similarity includes determining, by a first neural network, a first feature value associated with a first characteristic of a first product based on an image of the first product. The method also includes determining, by a second neural network, a second feature value associated with a second characteristic of the first product based on the image of the first product. The method further involves calculating a first vector space distance between the first feature value and a third feature value associated with the first characteristic of a second product, and calculating a second vector space distance between the second feature value and a fourth feature value associated with the second characteristic of the second product. Additionally, the method includes determining a similarity value based on the first vector space distance and the second vector space distance.

Determining visually similar products

This disclosure includes systems and methods for providing purchase recommendations to a user that may include items frequently purchased with a product selected by the user. The determination of which items are frequently purchased with which other items may account for both online and in-store transactions and may further account for both pairwise and multi-wise relationships. The recommendations may be provided on an electronic user interface, such as a website, in response to the user's selection of the product through the electronic user interface. The recommendations may be tailored to the user's selected product so that the recommended items are available in the same delivery channel as the user-selected product.

Product recommendations based on items frequently bought together

A method for machine learning-based classification may include training a machine learning model with a full training data set, the full training data set comprising a plurality of data points, to generate a first model state of the machine learning model, generating respective embeddings for the data points in the full training data set with the first model state of the machine learning model, applying a clustering algorithm to the respective embeddings to generate one or more clusters of the embeddings, identifying outlier embeddings from the one or more clusters of the embeddings, generating a reduced training data set comprising the full training data set less the data points associated with the outlier embeddings, training the machine learning model with the reduced training data set to a second model state, and applying the second model state to one or more data sets to classify the one or more data sets.

Optimizing training data for image classification

Growing community of inventors

Atlanta, GA, United States of America

Estelle Afshar