EPISTEMIC UNCERTAINTY REDUCTION USING SIMULATIONS, MODELS AND DATA EXCHANGE
A system and methods for operating an outcome modeling engine that incorporates a wide range of input data from various sources including (but not limited to) scientific advances in data analytics, agent-based modeling, discrete event simulation, and the mathematics of entropy to aid in making better decisions about real-world socio-technical systems.
1 . A system for epistemic uncertainty reduction using simulations, models and data exchange, comprising:
a parametric evaluator comprising a processor, a memory, and a plurality of programming instructions stored in the memory and operating on the processor, wherein the programming instructions, when operating on the processor, cause the processor to:
receive a plurality of input data values from external data sources;
compile at least a portion of the plurality of input data values into a list of initial conditions;
provide at least a portion of the initial conditions to a rules management engine;
a rules management engine comprising a processor, a memory, and a plurality of programming instructions stored in the memory and operating on the processor, wherein the programming instructions, when operating on the processor, cause the processor to:
receive a plurality of initial conditions from the parametric evaluator;
compare at least a portion of the initial conditions against a plurality of stored configuration rules;
define a scenario model using a model definition language and based at least in part on at least a portion of the initial conditions and the results of the comparison;
execute a simulated scenario using the scenario model; and
produce a scenario outcome based on the execution results.
2 . The system of claim 1 , further comprising an optimizer comprising a processor, a memory, and a plurality of programming instructions stored in the memory and operating on the processor, wherein the programming instructions, when operating on the processor, cause the processor to:
receive a plurality of initial conditions from the parametric evaluator;
analyze at least a portion of the initial conditions to determine their respective suitability for a particular scenario model; and
recommend at least a portion of the initial conditions for use by the rules management engine, the recommendation being based on the results of the analysis.
3 . The system of claim 1 , wherein the external data sources comprise at least a distributed computational graph.
4 . The system of claim 3 , wherein the scenario outcome is provided to the distributed computational graph for use as input data.
5 . The system of claim 4 , wherein at least a portion of the input data values are received from the distributed computational graph and based on previously-provided scenario outcomes that have been processed by the distributed computational graph.
6 . A method for epistemic uncertainty reduction using simulations, models and data exchange, comprising the steps of:
receiving, at a parametric evaluator, a plurality of input data values from a plurality of external data sources;
compiling a list of initial conditions based at least in part on at least a portion of the input data values;
providing at least a portion of the initial conditions to a rules management engine;
comparing, at the rules management engine, at least a portion of the initial conditions against a plurality of stored configuration rules;
defining a scenario model using a model definition language and based at least in part on at least a portion of the initial conditions and the results of the comparison;
executing a simulated scenario using the scenario model; and
producing a scenario outcome based on the execution results.
7 . The method of claim 6 , further comprising the steps of:
receiving, at an optimizer, a plurality of initial conditions from the parametric evaluator;
analyzing at least a portion of the initial conditions to determine their respective suitability for a particular scenario model; and
recommending at least a portion of the initial conditions for use by the rules management engine, the recommendation being based on the results of the analysis.
8 . The method of claim 6 , wherein the external data sources comprise at least a distributed computational graph.
9 . The method of claim 8 , wherein the scenario outcome is provided to the distributed computational graph for use as input data.
10 . The method of claim 9 , wherein at least a portion of the input data values are received from the distributed computational graph and based on previously-provided scenario outcomes that have been processed by the distributed computational graph.