NetflixPatent applicationAI & softwareInterest 3/10

Netflix patents method to keep recommendation math stable during updates

Patent drawing
Patent drawing from the official filing.

Netflix describes a computer method that adjusts new user and item data to match the structure of older data. It creates a transformation to align these new data points with previous versions, ensuring the recommendation system remains consistent as it updates.

Why it mattersThis is a routine technical improvement that helps streaming services maintain accurate and stable recommendations without sudden shifts in user preferences.

In the filing’s own words

Orthogonal low rank embedding stabilization includes receiving a new user embedding matrix, receiving a new item embedding matrix, generating a transformed user embedding matrix and a transformed item embedding matrix from the new user embedding matrix and the new item embedding matrix, generating a transformation that maps the transformed item embedding matrix to an embedding space of a previous version of the item embedding matrix, generating a stabilized user embedding matrix based on the transformation, the new user embedding matrix, and the transformed user embedding matrix, and generating a stabilized item embedding matrix based on the transformation, the new item embedding matrix, and the transformed item embedding matrix.

What exactly they claim (claim 1)

1. A computer-implemented method for stabilizing embeddings, the computer-implemented method comprising: receiving a new user embedding matrix; receiving a new item embedding matrix; generating a transformed user embedding matrix and a transformed item embedding matrix from the new user embedding matrix and the new item embedding matrix; generating a transformation that maps the transformed item embedding matrix to an embedding space of a previous version of the item embedding matrix; generating a stabilized user embedding matrix based on the transformation, the new user embedding matrix, and the transformed user embedding matrix; and generating a stabilized item embedding matrix based on the transformation, the new item embedding matrix, and the transformed item embedding matrix.

Facts

Company
Netflix (NETFLIX, INC.)
Official title
ORTHOGONAL LOW RANK EMBEDDING STABILIZATION
Publication number
US20260359385A1
Application number
19323818
Filed
Sep 9, 2025
Published
Nov 12, 2026
Inventors
2
Claims
20

Classified under

G06F 17/16 Physics & computing

More from Netflix in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.