Systems and methods for managing, distributing and deploying a recursive decisioning system based on continuously updating machine learning models
AssigneeSavvi Ai Inc.
InventorAlex Muller
Life of this patent
Estimating the term…
Abstract
The present disclosure relates generally to the generation and deployment of a machine learning-enabled decision engine (MLDE). The MLDE includes decision options that are composed of a discrete list of selectable options. Further, the MLDE includes data inputs that can be used to influence decisions made by the machine learning models of the MLDE. Controls are applied to the MLDE to overlay and bound the decisioning within guidelines established by an operator of the MLDE. Once the MLDE is established, the MLDE is validated and deployed for use by software applications to make decisions.
Claims22
(canceled)
A computer-implemented method, comprising:
- receiving a request to generate a decision, wherein the request includes a set of data inputs, wherein the request is associated with a microservice that implements a machine-learning enabled decisioning engine (MLDE), and wherein the MLDE is associated with a set of decision options;
- processing the set of decision options and the set of data inputs through the MLDE to generate a set of predicted performance metrics for the set of decision options;
- generating an initial ranked list of decision options (RLDO) from the set of decision options, wherein the initial RLDO is generated based on the set of predicted performance metrics;
- identifying a set of controls applicable to the initial RLDO, wherein the set of controls is identified according to the set of data inputs, and wherein the set of controls includes a set of rules for modifying the initial RLDO based on the set of data inputs;
- generating a modified RLDO, wherein the modified RLDO is generated by modifying the initial RLDO according to the set of rules to ensure compliance with the set of controls;
- and
- providing the modified RLDO to fulfill the request.
A system, comprising:
- one or more processors;
- and
- memory storing thereon instructions that, as a result of being executed by the one or more processors, cause the system to:
- receive a request to generate a decision, wherein the request includes a set of data inputs, wherein the request is associated with a microservice that implements a machine-learning enabled decisioning engine (MLDE), and wherein the MLDE is associated with a set of decision options;
- process the set of decision options and the set of data inputs through the MLDE to generate a set of predicted performance metrics for the set of decision options;
- generate an initial ranked list of decision options (RLDO) from the set of decision options, wherein the initial RLDO is generated based on the set of predicted performance metrics;
- identify a set of controls applicable to the initial RLDO, wherein the set of controls is identified according to the set of data inputs, and wherein the set of controls includes one or more rules for modifying the initial RLDO based on the set of data inputs;
- generate a modified RLDO, wherein the modified RLDO is generated by modifying the initial RLDO according to the one or more rules to ensure compliance with the set of controls;
- and
- provide the modified RLDO to fulfill the request.
A non-transitory computer-readable storage medium storing thereon executable instructions that, as a result of being executed by one or more processors of a computer system, cause the computer system to:
- receive a request to generate a decision, wherein the request includes a set of data inputs, wherein the request is associated with a microservice that implements a machine-learning enabled decisioning engine (MLDE), and wherein the MLDE is associated with a set of decision options;
- process the set of decision options and the set of data inputs through the MLDE to generate a set of predicted performance metrics for the set of decision options;
- generate an initial ranked list of decision options (RLDO) from the set of decision options, wherein the initial RLDO is generated based on the set of predicted performance metrics;
- identify a set of controls applicable to the initial RLDO, wherein the set of controls is identified according to the set of data inputs, and wherein the set of controls includes one or more rules for modifying the initial RLDO based on the set of data inputs;
- generate a modified RLDO, wherein the modified RLDO is generated by modifying the initial RLDO according to the one or more rules to ensure compliance with the set of controls;
- and
- provide the modified RLDO to fulfill the request.
Dependencies are inferred from the claim text.