Computer Model Management System

A system, comprising:

• a non-transitory memory;
• and
• one or more hardware processors coupled to the non-transitory memory and configured to read instructions from the non-transitory memory to cause the system to perform operations comprising:
• receiving deployment instructions for a machine-learning model of a plurality of machine-learning models stored in a database associated with an enterprise computer system;
• selecting, by a particular computer system included in the enterprise computer system and based on the deployment instructions, a destination within the enterprise computer system for deploying a version of the machine-learning model, the destination being associated with a subset of data sets available to the enterprise computer system;
• deploying the version of the machine-learning model to the selected destination for operation on the subset of data sets;
• collecting performance data associated with the operation of the version of the machine-learning model deployed on the selected destination;
• and
• determining, based on the performance data, whether to roll back the version of the machine-learning model.

A method, comprising:

• receiving deployment instructions for a machine-learning model of a plurality of machine-learning models stored in a database associated with an enterprise computer system
• deploying, by a particular computer system included in an enterprise computer system and based on the deployment instructions, a first version of the machine-learning model to a destination for operation on a subset of data sets available to the enterprise computer system;
• collecting performance data associated with the operation of the first version of the machine-learning model deployed on the selected destination;
• rolling back the first version of the machine-learning model based on the performance data;
• and
• deploying, by the particular computer system, a second version of the machine-learning model to the destination for operation on the subset of data sets.

A non-transitory machine-readable medium having instructions stored thereon that are executed by a computer system to perform operations comprising:

• receiving deployment instructions for a machine-learning model stored in a database associated with an enterprise computer system;
• selecting, by a particular computer system included in the enterprise computer system and based on the deployment instructions, a plurality of versions of the machine-learning model for deployment;
• based on the deployment instructions, selecting, by the particular computer system, a plurality of destinations within the enterprise computer system for deploying the plurality of versions of the machine-learning model, each destination of the plurality of destinations being selected for a version of the machine-learning model and each destination being associated with a subset of data sets available to the enterprise computer system;
• deploying in parallel the plurality of versions of the machine-learning model to the plurality of destinations for operation on the subset of data sets;
• collecting performance data associated with the operation of the plurality of versions of the machine-learning model;
• and
• determining, based on the performance data, whether to roll back one or more versions of the machine-learning model of the plurality of versions of the machine-learning model.