Cargando…

A deep learning framework for financial time series using stacked autoencoders and long-short term memory

The application of deep learning approaches to finance has received a great deal of attention from both investors and researchers. This study presents a novel deep learning framework where wavelet transforms (WT), stacked autoencoders (SAEs) and long-short term memory (LSTM) are combined for stock p...

Descripción completa

Detalles Bibliográficos
Autores principales: Bao, Wei, Yue, Jun, Rao, Yulei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2017
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5510866/
https://www.ncbi.nlm.nih.gov/pubmed/28708865
http://dx.doi.org/10.1371/journal.pone.0180944
_version_ 1783250242209054720
author Bao, Wei
Yue, Jun
Rao, Yulei
author_facet Bao, Wei
Yue, Jun
Rao, Yulei
author_sort Bao, Wei
collection PubMed
description The application of deep learning approaches to finance has received a great deal of attention from both investors and researchers. This study presents a novel deep learning framework where wavelet transforms (WT), stacked autoencoders (SAEs) and long-short term memory (LSTM) are combined for stock price forecasting. The SAEs for hierarchically extracted deep features is introduced into stock price forecasting for the first time. The deep learning framework comprises three stages. First, the stock price time series is decomposed by WT to eliminate noise. Second, SAEs is applied to generate deep high-level features for predicting the stock price. Third, high-level denoising features are fed into LSTM to forecast the next day’s closing price. Six market indices and their corresponding index futures are chosen to examine the performance of the proposed model. Results show that the proposed model outperforms other similar models in both predictive accuracy and profitability performance.
format Online
Article
Text
id pubmed-5510866
institution National Center for Biotechnology Information
language English
publishDate 2017
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-55108662017-08-07 A deep learning framework for financial time series using stacked autoencoders and long-short term memory Bao, Wei Yue, Jun Rao, Yulei PLoS One Research Article The application of deep learning approaches to finance has received a great deal of attention from both investors and researchers. This study presents a novel deep learning framework where wavelet transforms (WT), stacked autoencoders (SAEs) and long-short term memory (LSTM) are combined for stock price forecasting. The SAEs for hierarchically extracted deep features is introduced into stock price forecasting for the first time. The deep learning framework comprises three stages. First, the stock price time series is decomposed by WT to eliminate noise. Second, SAEs is applied to generate deep high-level features for predicting the stock price. Third, high-level denoising features are fed into LSTM to forecast the next day’s closing price. Six market indices and their corresponding index futures are chosen to examine the performance of the proposed model. Results show that the proposed model outperforms other similar models in both predictive accuracy and profitability performance. Public Library of Science 2017-07-14 /pmc/articles/PMC5510866/ /pubmed/28708865 http://dx.doi.org/10.1371/journal.pone.0180944 Text en © 2017 Bao et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Bao, Wei
Yue, Jun
Rao, Yulei
A deep learning framework for financial time series using stacked autoencoders and long-short term memory
title A deep learning framework for financial time series using stacked autoencoders and long-short term memory
title_full A deep learning framework for financial time series using stacked autoencoders and long-short term memory
title_fullStr A deep learning framework for financial time series using stacked autoencoders and long-short term memory
title_full_unstemmed A deep learning framework for financial time series using stacked autoencoders and long-short term memory
title_short A deep learning framework for financial time series using stacked autoencoders and long-short term memory
title_sort deep learning framework for financial time series using stacked autoencoders and long-short term memory
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5510866/
https://www.ncbi.nlm.nih.gov/pubmed/28708865
http://dx.doi.org/10.1371/journal.pone.0180944
work_keys_str_mv AT baowei adeeplearningframeworkforfinancialtimeseriesusingstackedautoencodersandlongshorttermmemory
AT yuejun adeeplearningframeworkforfinancialtimeseriesusingstackedautoencodersandlongshorttermmemory
AT raoyulei adeeplearningframeworkforfinancialtimeseriesusingstackedautoencodersandlongshorttermmemory
AT baowei deeplearningframeworkforfinancialtimeseriesusingstackedautoencodersandlongshorttermmemory
AT yuejun deeplearningframeworkforfinancialtimeseriesusingstackedautoencodersandlongshorttermmemory
AT raoyulei deeplearningframeworkforfinancialtimeseriesusingstackedautoencodersandlongshorttermmemory