Abstract
Forecasting stock price trends accurately appears a huge challenge because the environment of stock markets is extremely stochastic and complicated. This challenge persistently motivates us to seek reliable pathways to guide stock trading. While the Long Short-Term Memory (LSTM) network has the dedicated gate structure quite suitable for the prediction based on contextual features, we propose a novel LSTM-based model. Also, we devise a multiscale convolutional feature fusion mechanism for the model to extensively exploit the contextual relationships hidden in consecutive time steps. The significance of our designed scheme is twofold. (1) Benefiting from the gate structure designed for both long- and short-term memories, our model can use the given stock history data more adaptively than traditional models, which greatly guarantees the prediction performance in financial time series (FTS) scenarios and thus profits the prediction of stock trends. (2) The multiscale convolutional feature fusion mechanism can diversify the feature representation and more extensively capture the FTS feature essence than traditional models, which fairly facilitates the generalizability. Empirical studies conducted on three classic stock history data sets, i.e., S&P 500, DJIA, and VIX, demonstrated the effectiveness and stability superiority of the suggested method against a few state-of-the-art models using multiple validity indices. For example, our method achieved the highest average directional accuracy (around 0.71) on the three employed stock data sets.
Highlights
Forecasting the variation trend of stocks is always one of the hot topics in the academic and practical studies of stock markets. e innately dynamic, chaotic, and nonstationary properties of stock markets make it extremely challenging to predict the tendency of financial time series (FTS) precisely
(1) Benefiting from the gate structure designed for both long- and short-term memories, our model can use the given stock history data more adaptively than traditional models, which greatly guarantees the prediction performance in financial time series (FTS) scenarios and profits the prediction of stock trends. (2) e multiscale convolutional feature fusion mechanism can diversify the feature representation and more extensively capture the FTS feature essence than traditional models, which fairly facilitates the generalizability
Numerous studies anticipating stock price variation trends have been performed based on the FTS analysis. e widely used techniques can be roughly divided into three categories: statistical econometric models or tools, regression algorithms, and deep learning methods. is study focuses on machine learning-based techniques, so we primarily review the latter two in the following
Summary
Forecasting the variation trend of stocks is always one of the hot topics in the academic and practical studies of stock markets. e innately dynamic, chaotic, and nonstationary properties of stock markets make it extremely challenging to predict the tendency of financial time series (FTS) precisely. E innately dynamic, chaotic, and nonstationary properties of stock markets make it extremely challenging to predict the tendency of financial time series (FTS) precisely. Given that the fluctuation of the stock price is affected by multiple aspects of social economic life, it has great economic and social values to forecast the developing trend of the stock price effectively. Both investors and for-profit institutions require scientific and intelligent methods to analyze and evaluate the price history so as to facilitate establishing the appropriate trade strategies. Due to the Scientific Programming difference between short and long terms, one fine-turning model probably works well in the short-term prediction, whereas could be poor in a longer time series
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.
