Abstract
We applied Deep Q-Network with a Convolutional Neural Network function approximator, which takes stock chart images as input, for making global stock market predictions. Our model not only yields profit in the stock market of the country where it was trained but generally yields profit in global stock markets. We trained our model only in the US market and tested it in 31 different countries over 12 years. The portfolios constructed based on our model's output generally yield about 0.1 to 1.0 percent return per transaction prior to transaction costs in 31 countries. The results show that there are some patterns on stock chart image, that tend to predict the same future stock price movements across global stock markets. Moreover, the results show that future stock prices can be predicted even if the training and testing procedures are done in different countries. Training procedure could be done in relatively large and liquid markets (e.g., USA) and tested in small markets. This result demonstrates that artificial intelligence based stock price forecasting models can be used in relatively small markets (emerging countries) even though they do not have a sufficient amount of data for training.
Highlights
IntroductionIn ‘‘Efficient Capital Markets [1],’’ Eugene Fama argued that the stock market is highly efficient and the price always fully reflects all available information, which is referred to as the Efficient Market Hypothesis (EMH)
Predicting future stock prices has always been a controversial research topic
We mainly focus on finding patterns that generally yield a profit in a stock market of the single country whose data is used for training our model and in global stock markets
Summary
In ‘‘Efficient Capital Markets [1],’’ Eugene Fama argued that the stock market is highly efficient and the price always fully reflects all available information, which is referred to as the Efficient Market Hypothesis (EMH). He maintained that technical analysis or fundamental analysis (or any analysis) would not yield any consistent over-average profit to investors. Many state-of-the-art image classification models are based upon CNN architecture. Such models usually take 2D images as input with three color channels. Note that in our work, we use CNN as a function approximator in the Q-learning algorithm
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.
