Systems and methods for machine learning model interpretation
US11514369B2 · kind B2 · utility
2Cited by
1References
21Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jun 11, 2021 |
| Grant date | Nov 29, 2022 |
| Priority date | — |
| Expiry date | Jun 11, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/197
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Systems and methods are described for interpreting machine learning model predictions. An example method includes: providing a machine learning model configured to receive a plurality of features as input and provide a prediction as output, wherein the plurality of features includes an engineered feature including a combination of two or more parent features; calculating a Shapley value for each feature in the plurality of features; and allocating a respective portion of the Shapley value for the engineered feature to each of the two or more parent features.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.