Abstract
Stock price prediction is a popular yet challenging task and deep learning provides the means to conduct the mining for the different patterns that trigger its dynamic movement. In this paper, the task is to predict the close price for 25 companies enlisted at the Bucharest Stock Exchange, from a novel data set introduced herein. Towards this scope, two traditional deep learning architectures are designed in comparison: a long short-memory network and a temporal convolutional neural model. Based on their predictions, a trading strategy, whose decision to buy or sell depends on two different thresholds, is proposed. A hill climbing approach selects the optimal values for these parameters. The prediction of the two deep learning representatives used in the subsequent trading strategy leads to distinct facets of gain.
Highlights
Stock price prediction has been an evergoing challenge for economists and for machine learning scientists
The accuracy of estimation of the long short-term memory network (LSTM) and convolutional neural network (CNN) is measured in comparison
The effect of the deep learning prediction is illustrated in a trading scheme, based on thresholds that are heuristically determined
Summary
Stock price prediction has been an evergoing challenge for economists and for machine learning scientists. Different approaches have been applied over the decades to model either long-term or short-term behavior, taking into account daily prices and other technical indicators from stock markets around the world. Deep learning has entered the stock market realm, through its specific technique to model long-term data dependencies, the long short-term memory network (LSTM). A convolutional neural network (CNN) with 1D (temporal) convolutions is employed to produce an estimation of the day close price value. The difference between the current close price and its estimated value for the following day is measured against two thresholds— depending on which of them is higher—in order to pursue a BUY or SELL action.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
