Information technology for time series forecasting based on the evolutionary method of the forecasting scheme synthesis
Оксана Юріївна Мулеса, Anatoliy Ye. Batyuk, Fedir Geche, Olena Melnyk, Mykola Mykhailovych Palinchak, Тамара Радівілова · 2021 IEEE 16th International Conference on Computer Sciences and Information Technologies (CSIT) · 2021
The research deals with the development of information technology for time series forecasting. The core principle of the technology is the method of evolutionary synthesis on forecast schemes for fundamental forecasting models. The paper evaluates the process of constructing the objective function and analyzes the critical stages of the genetic algorithm for optimal resolution detection. Authors apply forecast volatility as a quality indicator. Application of the technology results in production rules for forecast future values determination. The authors conducted experimental verification of the research results. The paper justifies the efficiency of the developed technology.