Deep causal learning for continuous testing, diagnosis, and optimization

A method comprising:

• generating, based on one or more assumptions for a randomized selection of process decisions, the one or more assumptions identifying external factors based on prior injections of experimental units into the system, a plurality of experimental units for a treatment assignment, the treatment assignment clustering the experimental units based on the identified external factors;
• injecting the plurality of experimental units for the treatment assignment into a system of interest to generate inferences about causal effects of the process decisions;
• in response to injecting the plurality of experimental units into the system of interest, identifying one or more measures of precision associated with the inferences about the causal effects;
• and
• updating the identification of the external factors in the one or more assumptions and modifying the experimental units for the treatment assignment based on the one or more measures of precision to identify at least one causal interaction of the process decisions within the system of interest.

An apparatus comprising:

• processor-executed means for generating a plurality of experimental units for a treatment assignment based on one or more assumptions for a randomized selection of process decisions, the one or more assumptions identifying external factors based on prior injections of experimental units into the system, the treatment assignment clustering the experimental units based on the identified external factors;
• processor-executed means for injecting the plurality of experimental units for the treatment assignment into a system of interest to generate inferences about causal effects of the process decisions;
• processor-executed means for identifying one or more measures of precision associated with the inferences about the causal effects in response to the injection of the plurality of experimental units into the system of interest;
• and
• processor-executed means for updating the identification of the external factors in the one or more assumptions and modifying the experimental units for the treatment assignment based on the one or more measures of precision to identify at least one causal interaction of the process decisions within the system of interest.

A non-transitory computer-readable medium encoded with instructions that, when executed, cause a processor of a system to:

• generate, based on one or more assumptions for a randomized selection of process decisions, the one or more assumptions identifying external factors based on prior injections of experimental units into the system, a plurality of experimental units for a treatment assignment, the treatment assignment clustering the experimental units based on the identified external factors;
• inject the plurality of experimental units for the treatment assignment into a system of interest to generate inferences about causal effects of the process decisions;
• identify one or more measures of precision associated with the inferences about the causal effects in response to injecting the plurality of experimental units into the system of interest;
• and
• update the identification of the external factors in the one or more assumptions and modify the experimental units for the treatment assignment based on the one or more measures of precision to identify at least one causal interaction of the process decisions within the system.