Wavelet Analysis Methodology as a Tool for Predicting Cryptocurrency Price Dynamics

Abstract

The stock market allows you to attract free investment resources, redistribute free financial resources between various spheres of the economy, business entities. For this, various tools and mechanisms for raising funds are used. Cryptocurrency is one of the tools of the modern stock market. The attractiveness of cryptocurrency, sharp and rapid changes in cryptocurrency prices necessitate various studies. At the same time, it is important to consider not only the dynamics of prices for cryptocurrencies, but also the mutual dynamics of prices between different types of cryptocurrencies. This is important in the aspect when choosing and building various forecasting models, assessing the mutual dynamics of cryptocurrency prices. To solve such a problem, it is necessary to carry out a complex and comprehensive analysis of the data. At the same time, it is important to obtain additional information that will be useful in the corresponding analysis. For this, it is proposed to use the wavelet ideology. We consider wavelet coherence as a data analysis tool. This choice is justified, and also the feasibility of its use on various datasets is confirmed. The paper deals with the mutual dynamics of prices for various types of cryptocurrencies. For this purpose, the corresponding estimates of the wavelet coherence are considered in the work. These estimates are based on real data. These estimates allow a number of conclusions to be drawn about cryptocurrency price prediction. In the work, information is presented in the form of various graphs and diagrams. This allows us to repeat and check the obtained estimates of the wavelet coherence, to evaluate the results that have been obtained.