Issue |
E3S Web Conf.
Volume 403, 2023
XII International Scientific and Practical Forum “Environmentally Sustainable Cities and Settlements: Problems and Solutions” (ESCP-2023)
|
|
---|---|---|
Article Number | 08007 | |
Number of page(s) | 13 | |
Section | Development of Sustainable Cities: Economic, Social and Humanitarian Aspects | |
DOI | https://doi.org/10.1051/e3sconf/202340308007 | |
Published online | 25 July 2023 |
Forecasting financial markets using advanced machine learning algorithms
Russian Biotechnological University (ROSBIOTECH), Departments of Computer Science and computer technology of food production, Moscow, Russian Federation
1 Corresponding author: medvedevav@mgupp.ru
This article explores the application of advanced data analysis techniques in the financial sector using neural networks for price forecasting in financial markets. Neural networks, with their ability for self-learning and capturing complex dependencies, offer great potential for accurate financial trend predictions. The article describes the development and utilization of a mathematical model based on convolutional neural networks for forecasting the state of financial markets. The model is trained on historical data, uncovering hidden relationships among various factors and predicting future prices based on acquired knowledge. However, additional research and algorithm optimization are needed to further enhance the accuracy and reliability of the forecasts. The application of neural networks in financial market forecasting represents a crucial area of research that can significantly impact decision-making and the performance of financial operations. Improving the accuracy and reliability of such models can contribute to more effective risk management and better outcomes in the financial sector.
Key words: price forecasting / financial markets / data analysis / neural networks / self-learning
© The Authors, published by EDP Sciences, 2023
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.