The role of functional activation in neural networks in the context of financial time series analysis
Authors:
- Lviv Polytechnic National UniversityLULviv Polytechnic National University
- A. P. SenykASA. P. Senyk
- O. S. ManziyOMO. S. Manziy
- V. R. PelekhVPV. R. Pelekh
- Y. V. FutrykYFY. V. Futryk
- Y. A. SenykYSY. A. Senyk
- National Forestry University of UkraineNUNational Forestry University of Ukraine
- 1 January 2025
- journal article
- Published by Lviv Polytechnic National University in Mathematical Modeling and Computing
- Vol. 12 (1) , 299-309
Abstract
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.Keywords
This publication has 12 references indexed in Scilit:
- Application of the Bayesian approach to modeling credit risksMathematical Modeling and Computing, 2024
- Information system of analysis for segmentation of the securities portfolio of the product marketScientific Messenger of LNU of Veterinary Medicine and Biotechnologies. Series: Economical Science, 2023
- Siamese neural networks in recommendationNeural Computing and Applications, 2023
- The role of artificial neural network and machine learning in utilizing spatial informationSpatial Information Research, 2022
- Information System Supporting Decision-making Processes for Forming of Securities PortfolioComputer systems and network, 2022
- A Novel Implementation of Siamese Type Neural Networks in Predicting Rare Fluctuations in Financial Time SeriesRisks, 2022
- The Role of Neural Network Activation FunctionsIEEE Signal Processing Letters, 2020
- Siamese Neural Networks: An Overview2020
- RETRACTED ARTICLE: Prediction research of financial time series based on deep learningSoft Computing, 2020
- Application of Siamese Neural Networks for the Type of Emergency Determination2019