Determining retraining of predictive models
AssigneeAccenture Global Solutions Limited
InventorAndrew E. Fano
Life of this patent
Estimating the term…
Abstract
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining retraining predictive models. One of the methods includes maintaining, by a computer system of an enterprise, one or more predictive models. The computer system receives operational data and uses each of the one or more predictive models to generate predictions using the received operational data. An indication of a systemic change in the computer system is received. The method includes determining that one or more retraining rules specify that at least one of the one or more predictive models should be retrained due to the systemic change, and in response, obtaining updated training data and retraining the predictive model using the updated training data.
Claims20
A computer-implemented method comprising:
- maintaining, by a computer system of an enterprise, one or more predictive models, wherein the computer system receives operational data and uses each of the one or more predictive models to generate predictions using the received operational data;
- receiving an indication of a systemic change in the computer system;
- determining that one or more retraining rules specify that at least one of the one or more predictive models should be retrained due to the systemic change;
- and
- in response, obtaining updated training data and retraining the predictive model using the updated training data.
A computer-implemented method comprising:
- maintaining, by a computer system of an enterprise, one or more predictive models, wherein the computer system uses each of the one or more predictive models to generate predictions using received operational data;
- receiving an indication of a change in the operational data;
- computing a measure of impact of the change in the operational data;
- determining that one or more retraining rules specify that at least one of the one or more predictive models should be retrained due to the measure of impact of the change in the operational data;
- and
- in response, obtaining updated training data and retraining the predictive model using the updated training data.
A computer program product, encoded on one or more non-transitory computer storage media, comprising instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:
- maintaining, by a computer system of an enterprise, one or more predictive models, wherein the computer system receives operational data and uses each of the one or more predictive models to generate predictions using the received operational data;
- receiving an indication of a systemic change in the computer system;
- determining that one or more retraining rules specify that at least one of the one or more predictive models should be retrained due to the systemic change;
- and
- in response, obtaining updated training data and retraining the predictive model using the updated training data.
Dependencies are inferred from the claim text.