The role of functional activation in neural networks in the context of financial time series analysis

Nowadays, neural networks are among the most popular analysis tools. They are effective in solving classification, pattern recognition, and clustering problems. This paper provides a detailed description and analysis of the operational principles of two neural networks, namely a Siamese network and a multilayer perceptron. A model for using these neural networks in time series forecasting is proposed. As an example, a web application was created in which the described neural networks were used to analyze the correlation between pairs of financial assets and assess the risk level of an investment portfolio. Modern information technologies, visualization methods, and advanced analysis tools used in the developed software product provide users with a comprehensive understanding of their investments, allowing them to assess risks and opportunities, as well as determine strategies for maximizing income and diversifying their selected set of financial assets. The research results demonstrate the effectiveness of the Siamese network and multilayer perceptron in forecasting the prices of financial assets on the stock market and applying the obtained results in investment management tasks.