Forecasting stock prices with a feature fusion LSTM-CNN model using different representations of the same data
Top Cited Papers
Open Access
- 15 February 2019
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 14 (2), e0212320
- https://doi.org/10.1371/journal.pone.0212320
Abstract
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.Keywords
Funding Information
- Korean Ministry of Land, Infrastructure and Transport (17CTAP-C129782-01)
This publication has 38 references indexed in Scilit:
- Forecasting stock indices with back propagation neural networkExpert Systems with Applications, 2011
- Using artificial neural network models in stock market index predictionExpert Systems with Applications, 2011
- Design and implementation of NN5 for Hong Kong stock price forecastingEngineering Applications of Artificial Intelligence, 2007
- A link between complete models with stochastic volatility and ARCH modelsFinance and Stochastics, 2004
- Forecasting crashes: trading volume, past returns, and conditional skewness in stock pricesJournal of Financial Economics, 2001
- Flat MinimaNeural Computation, 1997
- The use of technical analysis in the foreign exchange marketJournal of International Money and Finance, 1992
- The Cross‐Section of Expected Stock ReturnsThe Journal of Finance, 1992
- Expected stock returns and volatilityJournal of Financial Economics, 1987
- Efficient Capital Markets: A Review of Theory and Empirical WorkThe Journal of Finance, 1970