Long-term prediction in Tehran stock market using a new architecture of Deep neural networks

Financial markets play an important role in the economy of modern societies. Therefore, many researchers have investigated to forecast these markets using various statistical and soft computing methods. Financial time series are essentially complex, dynamic, nonlinear, noisy, non parametric and chaotic in nature, so they cannot describe by analytical equations with few parameters, because their dynamics are too complex or unknown. In recent years, deep learning methods have attracted lots of attention, due to their exceptional performance compared to other existing approaches in many learning problems. The objective of this paper is long term prediction of price time series in Tehran Stock Exchange. For this purpose, a new architecture of two deep learning methods, Long Short Term Memory (LSTM) and Recurrent Neural Network (RNN), for ten steps ahead simultaneous prediction, are proposed. That is a multi variable structure with multi outputs. By using the output error feedbacks as the internal inputs, the network can learn error dynamics during the training phase. Experimental results show the high capability of our proposed structure for both methods in multi steps ahead stock price forecasting and the superiority of the Long Short Term Memory network compared to Recurrent Neural Network for long term predictions.