Computer prediction of opposite events on the basis of modification of the transition probabilities of Markov chains

Abstract

The article presents the results of the development of the mathematical support of the information system, the
result of which is the simulation of the occurrence of a random event. Modeling is aimed at revealing the regularity of occurrence
of a real-world event and predicting the occurrence of this event in a single case. The model is aimed at revealing the probabilistic
characteristics of an event in the terminology of Markov chains using the ideas of the ant algorithm Marco Dorigo. The basic
idea of applying the Dorigo ant form is to obtain estimates of the unknown transition probabilities of the Markov chain for a
real event on the basis of the observed intensity of the transitions. It is assumed that the relative frequency of the event is

54

C.С. Оспанов, Е.Т. Рамазанов

known. And also the constructed model reveals the patterns of the chain (the similarity of Viterbi’s paths) of the transitions of
the occurrence of an event. In the implementation of the model, the Monte Carlo method is used to play the opposite events.