Method and apparatus for evaluating predictive model
US9684634B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 25, 2014 |
| Grant date | Jun 20, 2017 |
| Priority date | — |
| Expiry date | Jul 30, 2035 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06Q10/06375
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
In an approach for evaluating a predictive model, a computer identifies features of training samples in a set of training samples and selects at least one evaluation metric from a set of evaluation metrics as one or more available metrics based on the identified features. The computer applies a predictive model created based on the set of training samples to a set of test samples so as to calculate values of the one or more available metrics and evaluates the predictive model by using the one or more available metrics and the values of the available metrics. With the technical solutions described with respect to the embodiments of the present invention, one or more evaluation metrics that are applicable to specific training sample features may be determined from several evaluation metrics, so that users can precisely evaluate predictive models by using the determined evaluation metrics.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.