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.
Highlights
Forecasting stock prices is an attractive pursuit for investors and researchers who want to beat the stock market
We need to make sure that our proposed feature fusion long short-term memory (LSTM)-convolutional neural networks (CNNs) model is meaningful
The results show that the feature fusion LSTM-CNN model is the best model for forecasting stock prices
Summary
Forecasting stock prices is an attractive pursuit for investors and researchers who want to beat the stock market. Fama [2] proposed efficient market theory, which states that a stock price already reflects all new information related to the stock and implies that no one can beat the market because stock prices are already set fairly. Contrary to this theory, many attempts have been made to predict stock prices to obtain profits using various techniques [3, 4, 5, 6] since determining the market timing for buying or selling a stock at a certain price is an important part of a trading strategy [7]. French et al [8] proposed using the generalized autoregressive conditional heteroscedasticity (GARCH) model to predict stock prices using the relationship between a stock’s
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
