The era of modern financial data modeling seeks machine learning techniques which are suitable for noisy and non-stationary big data. We demonstrate how a general class exponential smoothed recurrent neural networks ( α -RNNs) well suited to dynamical systems arising in applications such as high frequency algorithmic trading. Application exponentially RNNs minute level Bitcoin prices CME future...

The Matrix Profile (MP) algorithm has the potential to revolutionise many areas of data analysis. In this article, several applications financial time series are examined. Several approaches for identification similar behaviour patterns (or motifs) proposed, illustrated, and results discussed. While MP is primarily designed single analysis, it can also be applied multi-variate series. It still ...

With the continuous development of financial markets worldwide to tackle rapid changes such as climate change and global warming, there has been increasing recognition importance time series forecasting in market operation management. In this paper, we propose a new model based on deep learning ensemble model. The is constructed by taking advantage convolutional neural network (CNN), long short...

Phase space reconstruction of financial time series has become an effective approach for financial system analysis. Since the phase space obtained by the traditional method had the large embedding dimension and was susceptible to noise, this paper proposed a novel phase space reconstruction approach based on manifold learning, called manifold learning-based phase space reconstruction (MLPSR), w...