An Artificial World for Forecasting (Dream Valley)
The Project’s goal is to match simulation of complex dynamics and intelligent assessment methods using a novel three-layer construction.
A first layer will be an artificial world, an agent-based model of a real complex system. The system to be used as an example will be a model of a region operating in the both the socio-economic and environmental dimensions. This artificial world will serve as a source of data.
At the second layer, an artificial intelligence will use the data to forecast the key features of the future of the artificial world. In the beginning very rough characterizations of the future (for example, survival or collapse) will be considered. Simplified mathematical models, empirical stochastic models, pattern recognition methods and other techniques will act as the artificial intelligence.
At the third layer, an artificial statistician will assess the reliability of the forecasts given by the artificial intelligence.
The approach, called A3, will provide a research framework for evaluation of forecasting abilities of both known and new assessment methods, against real complex dynamics, including stochastic uncertainties and random shocks.
