The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Aug. 16, 2022

Filed:

Oct. 29, 2019
Applicant:

International Business Machines Corporation, Armonk, NY (US);

Inventors:

Michael Peran, Scarsdale, NY (US);

Josh Price, Lafayette, CO (US);

Daniel Augenstern, Endwell, NY (US);

Rahul Nahar, South Burlington, VT (US);

Pankaj Srivastava, Bedford, NY (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 21/00 (2013.01); G06N 20/00 (2019.01); G06F 16/9535 (2019.01); G06N 5/04 (2006.01); G06Q 30/06 (2012.01); G06Q 10/06 (2012.01);
U.S. Cl.
CPC ...
G06N 20/00 (2019.01); G06F 16/9535 (2019.01); G06N 5/04 (2013.01); G06Q 10/067 (2013.01); G06Q 30/0631 (2013.01);
Abstract

Embodiments of the present disclosure include a computer-implemented method and system for determining when to retrain an individual-item model within a recommendation engine. The computer-implemented method includes defining a consumer feature vector having attributes of historical consumers that impact an individual-item model. The computer-implemented method further includes calculating a historical feature vector relating to the historical consumers. The computer-implemented method also includes determining a retraining threshold for the individual-item model and calculating a new feature vector relating to new consumers. The new feature vector containing new attribute values of the new consumers and defined by the consumer feature vector. The computer-implemented method further includes determining a distance between the historical feature vector and the new feature vector and retraining the individual-item model upon determining that the distance between the historical feature vector and the new feature vector exceeds the retraining threshold.


Find Patent Forward Citations

Loading…