文摘
The article includes the following modern approaches to modelling sociodynamic processes: Kolmogorov equation system for Markov process with a discrete set of states, Fokker-Planck equation, multiagent systems, etc. As an example, one demographic task of predicting is solved. We compare the simplest neural network approach with an approach based on a special evolutionary model. The article also justifies applying the neural network modelling for producing solutions to the above mentioned equations, determination of their coefficients on the basis of observations and making more precise models, including the dependence of human behaviour on a psychological type. A possibility of making models more precise as new data come in has been discussed.