System and method for personalized item recommendations through large-scale deep-embedding architecture

Patent metadata

Field	Value
Publication number	US-11288730-B2
Application number	US-202016777555-A
Country	US
Kind code	B2
Filing date	Jan 30, 2020
Priority date	Jan 30, 2020
Publication date	Mar 29, 2022
Grant date	Mar 29, 2022

Abstract

A method including receiving a basket including basket items selected by a user from an item catalog. The method also can include grouping the basket items of the basket into categories based on a respective item category of each of the basket items. The method additionally can include randomly sampling a respective anchor item from each of the categories. The method further can include generating a respective list of complementary items for the respective anchor item for the each of the categories based on a respective score for each of the complementary items generated using two sets of trained item embeddings for items in the item catalog and using trained user embeddings for the user. The two sets of trained item embeddings and the trained user embeddings can be trained using a triple embeddings model with triplets. The triplets each can include a respective first user of users, a respective first item from the item catalog, and a respective second item from the item catalog, in which the respective first user selected the respective first item and the respective second item in a respective same basket. The method additionally can include building a list of personalized recommended items for the user based on the respective lists of the complementary items for the categories. The method further can include sending instructions to display, to the user on a user interface of a user device, at least a portion of the list of personalized recommended items. Other embodiments are disclosed.

First claim

What is claimed is:

1. A system comprising:
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:
before receiving a basket, training a triple embeddings model with triplets using an adaptive moment estimation optimizer to optimize a co-occurrence log-likelihood of each of the triplets;
receiving the basket comprising basket items selected by a user from an item catalog;
grouping the basket items of the basket into categories based on a respective item category of each of the basket items;
randomly sampling a respective anchor item from each of the categories;
generating a respective list of complementary items for the respective anchor item for the each of the categories based on a respective score for each of the complementary items generated using two sets of trained item embeddings for items in the item catalog and using trained user embeddings for the user, wherein the two sets of trained item embeddings and the trained user embeddings were trained using the triple embeddings model with the triplets, and wherein the triplets each comprise a respective first user of users, a respective first item from the item catalog, and a respective second item from the item catalog, in which the respective first user selected the respective first item and the respective second item in a respective same basket;
building a list of personalized recommended items for the user based on the respective lists of the complementary items for the categories; and
sending instructions to display, to the user on a user interface of a user device, at least a portion of the list of personalized recommended items.

2. The system of claim 1 , wherein building the list of personalized recommended items for the user further comprises:
filtering the respective list of the complementary items for the each of the categories based on complementary subcategories;
performing a weighted sampling of the respective list of the complementary items for the each of the categories to generate a sampled sub-list of the list of the complementary items for the each of the categories; and
merging the sampled sub-lists for the categories to generate a unified list.

3. The system of claim 2 , wherein filtering the respective list of the complementary items for the each of the categories based on the complementary subcategories further comprises:
receiving lift scores for subcategories of the complementary items; and
applying the lift scores for the complementary items to remove, from the respective list of the complementary items, popular co-bought items in the subcategories that are unrelated to a subcategory of the respective anchor item for the each of the categories.

4. The system of claim 2 , wherein performing the weighted sampling of the respective list of the complementary items for the each of the categories further comprises:
for the each of the categories, sampling a respective quantity of items from the respective list of the complementary items proportional to a respective quantity of the basket items in the each of the categories with respect to a total quantity of the basket items in the basket.

5. The system of claim 2 , wherein building the list of personalized recommended items for the user further comprises:
filtering out items from the unified list having subcategories that are identical to subcategories of the basket items.

6. The system of claim 5 , wherein building the list of personalized recommended items for the user further comprises:
sorting each item that remains in the unified list by the respective score of the item.

7. The system of claim 6 , wherein building the list of personalized recommended items for the user further comprises:
performing a category diversification across the unified list.

8. The system of claim 1 , wherein a vector dimension for the trained user embeddings for the user and for each item in each of the two sets of trained item embeddings is 128.

9. The system of claim 1 , wherein the portion of the list of personalized recommended items is displayed to the user on a checkout page for the basket, wherein the checkout page appears on the user interface of the user device.

10. The system of claim 9 , wherein a vector dimension for the trained user embeddings for the user and for each item in each of the two sets of trained item embeddings is 128.

11. A method being implemented via execution of computing instructions configured to run at one or more processors and stored at one or more non-transitory computer-readable media, the method comprising:
before receiving a basket, training a triple embeddings model with triplets using an adaptive moment estimation optimizer to optimize a co-occurrence log-likelihood of each of the triplets;
receiving the basket comprising basket items selected by a user from an item catalog;
grouping the basket items of the basket into categories based on a respective item category of each of the basket items;
randomly sampling a respective anchor item from each of the categories;
generating a respective list of complementary items for the respective anchor item for the each of the categories based on a respective score for each of the complementary items generated using two sets of trained item embeddings for items in the item catalog and using trained user embeddings for the user, wherein the two sets of trained item embeddings and the trained user embeddings were trained using the triple embeddings model with the triplets, and wherein the triplets each comprise a respective first user of users, a respective first item from the item catalog, and a respective second item from the item catalog, in which the respective first user selected the respective first item and the respective second item in a respective same basket;
building a list of personalized recommended items for the user based on the respective lists of the complementary items for the categories; and
sending instructions to display, to the user on a user interface of a user device, at least a portion of the list of personalized recommended items.

12. The method of claim 11 , wherein building the list of personalized recommended items for the user further comprises:
filtering the respective list of the complementary items for the each of the categories based on complementary subcategories;
performing a weighted sampling of the respective list of the complementary items for the each of the categories to generate a sampled sub-list of the list of the complementary items for the each of the categories; and
merging the sampled sub-lists for the categories to generate a unified list.

13. The method of claim 12 , wherein filtering the respective list of the complementary items for the each of the categories based on the complementary subcategories further comprises:
receiving lift scores for subcategories of the complementary items; and
applying the lift scores for the complementary items to remove, from the respective list of the complementary items, popular co-bought items in the subcategories that are unrelated to a subcategory of the respective anchor item for the each of the categories.

14. The method of claim 12 , wherein performing the weighted sampling of the respective list of the complementary items for the each of the categories further comprises:
for the each of the categories, sampling a respective quantity of items from the respective list of the complementary items proportional to a respective quantity of the basket items in the each of the categories with respect to a total quantity

Assignees

• Walmart Apollo Llc

Inventors

• Arora Yokila
• Mantha Aditya
• Gupta Shubham
• Kanumala Praveenkumar
• Guo Stephen Dean
• Achan Kannan

Classifications

• G06Q30/0631 Primary

  Recommending goods or services · CPC title

• G06Q30/0633

  Managing shopping lists, e.g. compiling or processing purchase lists (shipping orders G06Q10/083; order filling G06Q10/087) · CPC title

• G06N20/00

  Machine learning · CPC title

• G06Q30/0603 Primary

  Catalogue creation or management · CPC title