Stock market trend prediction using deep neural network via chart analysis: a practical method or a myth?

In this study, we investigate the feasibility of using deep learning for stock market prediction and technical analysis. We explore the dynamics of the stock market and prominent classical methods and deep learning-based approaches that are used to forecast prices and market trends. Subsequently, we evaluate prior research applicability for stock markets and their efficacy in real-world applications. Our analysis reveals that the most prominent studies regarding LSTMs and DNNs predictors for stock market forecasting create a false positive. Therefore, these approaches are impractical for the real market if the temporal context of predictions is overlooked. In addition, we identify specific errors in these studies and explain how they may lead to suboptimal or misleading results. Furthermore, we examine alternative deep learning architectures that may be better suited for predicting dynamical systems including CNN, LSTM, Transformer, and their combinations on real data of 12 stocks in the Tehran Stock Exchange (TSE). We propose an optimal CNN-based method, which can better capture the dynamics of semi-random environments such as the stock market, providing a more sophisticated prediction. However, our finding indicates that even with this enhanced method, the predictive aspect of vanilla DNN algorithms is minimal for an environment as noisy and chaotic as the stock market, particularly when working with small data sets. Finally, we discuss why our algorithm can avoid false positives and provide a better solution for time-series and trend prediction.