A B S T R A C T
The purpose of the research - is to predict the release of products (services) in the ICT sector using fuzzy time series (FTS).
The methodology of the research - in the course of the research, methods of processing statistical indicators, discrete images, fuzzy logic and implication rules, fuzzy mathematical apparatus, as well as modern programming packages were used.
The practical importance of the research – since real events are associated with certain uncertainty, for each indicator in the time order, a fuzzy variable can be assigned, which is characterized by the function of belonging. Fuzzy time rows allow you to cope with the problem, process both numerical and linguistic information, as well as discover new patterns and extract knowledge that is inaccessible to other models.
The results of the research - in the presented article, results are obtained on the collection of statistical indicators for forecasting the average monthly nominal wage and the probable future trend. Thus, the modern situation in the field of modeling and forecasting based on time series is characterized by the further development of methods called Times-Series data Mining and the implementation of models based on artificial intelligence technologies .
The originality and scientific novelty of the reseach - the study of modeling methods with fuzzy time series, the analysis of their opportunities and shortcomings revealed a number of unresolved problems: the problem of increasing the accuracy and informativeness of the forecast, the lack of efficiency criteria and methods for evaluating the results of fuzzy modeling, etc.