Futureproofing a machine learning model
AssigneeInternational Business Machines Corporation
InventorsKavitha Hassan Yogaraj, Frederik Frank Flother, Vladimir Rastunkov
Life of this patent
Estimating the term…
Abstract
Provided are a computer-implemented method, a system, and a computer program product for futureproofing a machine learning model, in which historical data for updates and changes to a baseline machine learning model are received. A futureproofing metric is generated. An enhanced machine learning model comprising a futureproofed version of the baseline machine learning model is generated with the historical data and the baseline machine learning model as inputs.
Claims20
A computer-implemented method for futureproofing a machine learning model, the computer-implemented method comprising:
- receiving, by a model futureproofing application, historical data for updates and changes to a baseline machine learning model;
- generating a futureproofing metric;
- generating, by the model futureproofing application, an enhanced machine learning model comprising a selected futureproofed version of the baseline machine learning model from a plurality of futureproofed versions of the baseline machine learning model, wherein the plurality of futureproofed versions of the baseline machine learning model are generated by the model futureproofing application with the historical data, objective functions that take into account future events, and the baseline machine learning model as inputs;
- deploying and monitoring the enhanced machine learning model;
- in response to determining that the objective functions are not met to a predetermined threshold degree, providing feedback and changing an evolutionary process for the model futureproofing application;
- and
- in response to determining that the objective functions are met to the predetermined threshold degree, determining that the enhanced machine learning model is to be continued to be used without changes.
A system for futureproofing a machine learning model, the system comprising:
- a memory;
- and
- a processor coupled to the memory, wherein the processor performs operations, the operations comprising:
- receiving, by a model futureproofing application, historical data for updates and changes to a baseline machine learning model;
- generating a futureproofing metric;
- generating, by the model futureproofing application, an enhanced machine learning model comprising a selected futureproofed version of the baseline machine learning model from a plurality of futureproofed versions of the baseline machine learning model, wherein the plurality of futureproofed versions of the baseline machine learning model are generated by the model futureproofing application with the historical data, objective functions that take into account future events, and the baseline machine learning model as inputs;
- deploying and monitoring the enhanced machine learning model;
- in response to determining that the objective functions are not met to a predetermined threshold degree, providing feedback and changing an evolutionary process for the model futureproofing application;
- and
- in response to determining that the objective functions are met to the predetermined threshold degree, determining that the enhanced machine learning model is to be continued to be used without changes.
A computer program product for futureproofing a machine learning model, the computer program product comprising a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code when executed by a computational device is configured to perform operations, the operations comprising:
- receiving, by a model futureproofing application, historical data for updates and changes to a baseline machine learning model;
- generating a futureproofing metric;
- generating, by the model futureproofing application, an enhanced machine learning model comprising a selected futureproofed version of the baseline machine learning model from a plurality of futureproofed versions of the baseline machine learning model, wherein the plurality of futureproofed versions of the baseline machine learning model are generated by the model futureproofing application with the historical data, objective functions that take into account future events, and the baseline machine learning model as inputs;
- deploying and monitoring the enhanced machine learning model;
- in response to determining that the objective functions are not met to a predetermined threshold degree, providing feedback and changing an evolutionary process for the model futureproofing application;
- and
- in response to determining that the objective functions are met to the predetermined threshold degree, determining that the enhanced machine learning model is to be continued to be used without changes.
Dependencies are inferred from the claim text.