Predicting Financial Prices of Stock Market using Recurrent Convolutional Neural Networks

Abstract

Financial time-series prediction has been long and the most challenging issues in financial market analysis. The deep neural networks is one of the excellent data mining approach has received great attention by researchers in several areas of time-series prediction since last 10 years. “Convolutional neural network (CNN) and recurrent neural network (RNN) models have become the mainstream methods for financial predictions. In this paper, we proposed to combine architectures, which exploit the advantages of CNN and RNN simultaneously, for the prediction of trading signals. Our model is essentially presented to financial time series predicting signals through a CNN layer, and directly fed into a gated recurrent unit (GRU) layer to capture long-term signals dependencies. GRU model perform better in sequential learning tasks and solve the vanishing gradients and exploding issue in standard RNNs. We evaluate our model on three datasets for stock indexes of the Hang Seng Indexes (HSI), the Deutscher Aktienindex (DAX) and the S&P 500 Index range 2008 to 2016, and associate the GRU-CNN based approaches with the existing deep learning models. Experimental results present that the proposed GRU-CNN model obtained the best prediction accuracy 56.2% on HIS dataset, 56.1% on DAX dataset and 56.3% on S&P500 dataset respectively.

Structural Entropy of Economic Systems

“…Reinert argues that the structure of each country's economy must constantly expand through the introduction of new high-tech economic activities. Entropic processes can be contained by improving communications and developing information technology [5][6][7][8][9]. Thus, it is possible to neutralize the factor of information asymmetry in the markets.…”

Mechanisms of Currency Regulation of the National Economy in the Conditions of European Integration of Ukraine

“…European and Latin American experience convinces of the advantages of administrative macroprudential mechanisms of currency market [9] regulation over price ones in order to achieve the global goal of dedollarization of national economies [10]. The choice of regulatory instruments is significantly influenced by the degree of liberalization of foreign exchange markets, which causes the effects after the opening of local markets, the effects of major markets and market closures [11].…”

Predicting stock market using natural language processing

“…Another stream of research uses evolving machine and deep learning models and techniques that perform well on time series tasks, such as convolutional models and recurrent neural networks. Zulqarnain et al . (2020) proposed a combined architecture that takes advantage of both convolutional and recurrent neural networks to predict trading signals.…”