Cargando…
Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data
Forecasting stock prices plays an important role in setting a trading strategy or determining the appropriate timing for buying or selling a stock. We propose a model, called the feature fusion long short-term memory-convolutional neural network (LSTM-CNN) model, that combines features learned from...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6377125/ https://www.ncbi.nlm.nih.gov/pubmed/30768647 http://dx.doi.org/10.1371/journal.pone.0212320 |
_version_ | 1783395698132123648 |
---|---|
author | Kim, Taewook Kim, Ha Young |
author_facet | Kim, Taewook Kim, Ha Young |
author_sort | Kim, Taewook |
collection | PubMed |
description | Forecasting stock prices plays an important role in setting a trading strategy or determining the appropriate timing for buying or selling a stock. We propose a model, called the feature fusion long short-term memory-convolutional neural network (LSTM-CNN) model, that combines features learned from different representations of the same data, namely, stock time series and stock chart images, to predict stock prices. The proposed model is composed of LSTM and a CNN, which are utilized for extracting temporal features and image features. We measure the performance of the proposed model relative to those of single models (CNN and LSTM) using SPDR S&P 500 ETF data. Our feature fusion LSTM-CNN model outperforms the single models in predicting stock prices. In addition, we discover that a candlestick chart is the most appropriate stock chart image to use to forecast stock prices. Thus, this study shows that prediction error can be efficiently reduced by using a combination of temporal and image features from the same data rather than using these features separately. |
format | Online Article Text |
id | pubmed-6377125 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-63771252019-03-01 Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data Kim, Taewook Kim, Ha Young PLoS One Research Article Forecasting stock prices plays an important role in setting a trading strategy or determining the appropriate timing for buying or selling a stock. We propose a model, called the feature fusion long short-term memory-convolutional neural network (LSTM-CNN) model, that combines features learned from different representations of the same data, namely, stock time series and stock chart images, to predict stock prices. The proposed model is composed of LSTM and a CNN, which are utilized for extracting temporal features and image features. We measure the performance of the proposed model relative to those of single models (CNN and LSTM) using SPDR S&P 500 ETF data. Our feature fusion LSTM-CNN model outperforms the single models in predicting stock prices. In addition, we discover that a candlestick chart is the most appropriate stock chart image to use to forecast stock prices. Thus, this study shows that prediction error can be efficiently reduced by using a combination of temporal and image features from the same data rather than using these features separately. Public Library of Science 2019-02-15 /pmc/articles/PMC6377125/ /pubmed/30768647 http://dx.doi.org/10.1371/journal.pone.0212320 Text en © 2019 Kim, Kim 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 Kim, Taewook Kim, Ha Young Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data |
title | Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data |
title_full | Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data |
title_fullStr | Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data |
title_full_unstemmed | Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data |
title_short | Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data |
title_sort | forecasting stock prices with a feature fusion lstm-cnn model using different representations of the same data |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6377125/ https://www.ncbi.nlm.nih.gov/pubmed/30768647 http://dx.doi.org/10.1371/journal.pone.0212320 |
work_keys_str_mv | AT kimtaewook forecastingstockpriceswithafeaturefusionlstmcnnmodelusingdifferentrepresentationsofthesamedata AT kimhayoung forecastingstockpriceswithafeaturefusionlstmcnnmodelusingdifferentrepresentationsofthesamedata |