Development of an Information and Analytical System for Predicting Price Fluctuations and Long-Term Trends Using Generative-Adversarial Neural Networks
Deep learning methods (DML) have been widely used in financial fields recently, such as stock market forecasting, balance the portfolio, financial information processing, and transaction execution strategies. Stock market forecasting and effective trading strategy construction, when using deep learn...
Published in: | SHS Web of Conferences |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English French |
Published: |
EDP Sciences
2021
|
Subjects: | |
Online Access: | https://doi.org/10.1051/shsconf/202111005010 https://doaj.org/article/e3a0f729bdf248a4ba3239915fe0d260 |
id |
ftdoajarticles:oai:doaj.org/article:e3a0f729bdf248a4ba3239915fe0d260 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:e3a0f729bdf248a4ba3239915fe0d260 2023-05-15T16:01:33+02:00 Development of an Information and Analytical System for Predicting Price Fluctuations and Long-Term Trends Using Generative-Adversarial Neural Networks Filippova Lyudmila Sazonova Anna Leonov Yuriy Shatova Polina 2021-01-01T00:00:00Z https://doi.org/10.1051/shsconf/202111005010 https://doaj.org/article/e3a0f729bdf248a4ba3239915fe0d260 EN FR eng fre EDP Sciences https://www.shs-conferences.org/articles/shsconf/pdf/2021/21/shsconf_icemt2021_05010.pdf https://doaj.org/toc/2261-2424 2261-2424 doi:10.1051/shsconf/202111005010 https://doaj.org/article/e3a0f729bdf248a4ba3239915fe0d260 SHS Web of Conferences, Vol 110, p 05010 (2021) Social Sciences H article 2021 ftdoajarticles https://doi.org/10.1051/shsconf/202111005010 2022-12-31T06:41:09Z Deep learning methods (DML) have been widely used in financial fields recently, such as stock market forecasting, balance the portfolio, financial information processing, and transaction execution strategies. Stock market forecasting and effective trading strategy construction, when using deep learning, are the most popular ways of applying DML in the field of finance. Against the background of the general development of the Russian stock market, the study and investigation of its price dynamics is a highly promising direction for analyzing and forecasting the value of financial assets in which it is planned to invest money. In this study, a new architecture of a conditional generative-adversarial neural network (GAN) with a multi-level perceptron (MLP) as a discriminator and a long short-term memory (LSTM) as a generator for determining trends is proposed. The Box-Jenkins method (ARIMA) is used to determine the confidence interval. Article in Journal/Newspaper DML Directory of Open Access Journals: DOAJ Articles SHS Web of Conferences 110 05010 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English French |
topic |
Social Sciences H |
spellingShingle |
Social Sciences H Filippova Lyudmila Sazonova Anna Leonov Yuriy Shatova Polina Development of an Information and Analytical System for Predicting Price Fluctuations and Long-Term Trends Using Generative-Adversarial Neural Networks |
topic_facet |
Social Sciences H |
description |
Deep learning methods (DML) have been widely used in financial fields recently, such as stock market forecasting, balance the portfolio, financial information processing, and transaction execution strategies. Stock market forecasting and effective trading strategy construction, when using deep learning, are the most popular ways of applying DML in the field of finance. Against the background of the general development of the Russian stock market, the study and investigation of its price dynamics is a highly promising direction for analyzing and forecasting the value of financial assets in which it is planned to invest money. In this study, a new architecture of a conditional generative-adversarial neural network (GAN) with a multi-level perceptron (MLP) as a discriminator and a long short-term memory (LSTM) as a generator for determining trends is proposed. The Box-Jenkins method (ARIMA) is used to determine the confidence interval. |
format |
Article in Journal/Newspaper |
author |
Filippova Lyudmila Sazonova Anna Leonov Yuriy Shatova Polina |
author_facet |
Filippova Lyudmila Sazonova Anna Leonov Yuriy Shatova Polina |
author_sort |
Filippova Lyudmila |
title |
Development of an Information and Analytical System for Predicting Price Fluctuations and Long-Term Trends Using Generative-Adversarial Neural Networks |
title_short |
Development of an Information and Analytical System for Predicting Price Fluctuations and Long-Term Trends Using Generative-Adversarial Neural Networks |
title_full |
Development of an Information and Analytical System for Predicting Price Fluctuations and Long-Term Trends Using Generative-Adversarial Neural Networks |
title_fullStr |
Development of an Information and Analytical System for Predicting Price Fluctuations and Long-Term Trends Using Generative-Adversarial Neural Networks |
title_full_unstemmed |
Development of an Information and Analytical System for Predicting Price Fluctuations and Long-Term Trends Using Generative-Adversarial Neural Networks |
title_sort |
development of an information and analytical system for predicting price fluctuations and long-term trends using generative-adversarial neural networks |
publisher |
EDP Sciences |
publishDate |
2021 |
url |
https://doi.org/10.1051/shsconf/202111005010 https://doaj.org/article/e3a0f729bdf248a4ba3239915fe0d260 |
genre |
DML |
genre_facet |
DML |
op_source |
SHS Web of Conferences, Vol 110, p 05010 (2021) |
op_relation |
https://www.shs-conferences.org/articles/shsconf/pdf/2021/21/shsconf_icemt2021_05010.pdf https://doaj.org/toc/2261-2424 2261-2424 doi:10.1051/shsconf/202111005010 https://doaj.org/article/e3a0f729bdf248a4ba3239915fe0d260 |
op_doi |
https://doi.org/10.1051/shsconf/202111005010 |
container_title |
SHS Web of Conferences |
container_volume |
110 |
container_start_page |
05010 |
_version_ |
1766397354840162304 |