Systems and methods for bootstrapped machine learning algorithm training
US11449807B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jan 31, 2020 |
| Grant date | Sep 20, 2022 |
| Priority date | — |
| Expiry date | Jan 29, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N5/02
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform receiving a request for a machine learned prediction for an item; determining that a number of entries in item user interaction data of the item is below a predetermined number-of-entries threshold; incorporating category interaction data of a hierarchical category of the item from a predetermined time period into the item user interaction data of the item; determining an initial machine learned prediction for the item using at least the category interaction data, as incorporated into the item user interaction data; and facilitating altering a graphical user interface (GUI) of an electronic device using the initial machine learned prediction for the item. Other embodiments are disclosed herein.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.