Shopify Patent: ML Product Categorization Method
Summary
The USPTO granted Shopify Inc. Patent US12608733B2 covering a machine learning method for product categorization using taxonomy trees. The patent describes inputting product information into a trained ML model to generate probability arrays across taxonomy levels, then iteratively selecting categories based on probability thresholds until a final category prediction is determined. This protects Shopify's algorithmic approach to automated product classification within its e-commerce platform.
What changed
The USPTO issued Patent US12608733B2 to Shopify Inc. covering a method for categorizing products using a machine learning model trained on a taxonomy tree structure. The system receives product information, generates probability arrays for each taxonomy level, and iteratively selects categories by comparing child node probabilities against a threshold until a final category prediction is reached.
E-commerce platform operators and product listing systems should be aware of this intellectual property grant when developing or licensing automated product categorization solutions. While the patent does not create immediate compliance obligations, it establishes proprietary protection around ML-based taxonomy-driven classification methods that may be relevant to similar product categorization implementations.
Archived snapshot
Apr 22, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
Method, article of manufacture, and system for providing category suggestions
Grant US12608733B2 Kind: B2 Apr 21, 2026
Assignee
SHOPIFY INC.
Inventors
Kshetrajna Raghavan, Kyle Bruce Tate, Xinyi Zhao
Abstract
A method for categorizing a product, the method including receiving information for the product; inputting the information into a trained machine learning model for a taxonomy tree; receiving a plurality of arrays, each array representing a level in the taxonomy tree and consisting of probabilities for each category represented in the level that the product is categorized in that category; choosing, from a highest level tier array, a category having a highest probability, thereby designating a tier prediction; collecting, from a second level tier array, all children of the tier prediction; determining whether a highest probability from the children of the tier prediction exceeds a threshold, and if yes, choosing the category with the highest probably as a new tier prediction; and repeating the determining; when the threshold is not exceeded or if the tier prediction has no children, and selecting the tier prediction as a predicted category.
CPC Classifications
G06Q 30/0601-0645 G06Q 30/08 G06N 3/084 G06N 5/01
Filing Date
2022-08-03
Application No.
17880045
Claims
20
Parties
Related changes
Get daily alerts for USPTO Patent Grants - Business Methods (G06Q)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Grants - Business Methods (G06Q) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.