OPTIMIZATION OF SHOPPING STRATEGY IN CRYPTOCURRENCY MARKETS BASED ON ARTIFICIAL NEURAL NETWORKS

Abstract

This study is relevant in the context of modern finance, where neural networks play a key role in the analysis and forecasting of price dynamics. The research focuses on identifying buy signals for the BTCUSDT and ETHUSDT trading pairs in the cryptocurrency market. To construct a neural network model that can automate the identification of moments beneficial for purchasing selected assets, various technical analysis indicators and convolutional neural networks (CNN) were used. The research includes an analysis of scientific literature, data collection, indicator selection, signal algorithm development, and the construction of neural network models. The main contribution of this work lies in the development and testing of models capable of predicting buy signals with a high accuracy, confirmed by accuracy indicators of over 92%. The findings of this study can be useful for private investors and financial institutions in forming investment strategies based on machine learning.