Time Series Prediction Using Echo State Network

In the past few years,Time Series Analysis and Prediction based on the Echo State Network(ESN)has gently grief the attention of researchers at home and abroad,which become a central research issue with relevant theoretical and application-related standards.Echo State Networks is one of the most efficient types of Recurrent Neural Networks(RNN).However,they are often present of cluster data,making the process of finding and efficient ESN for specific datasets quite tricky.In our current study,preferring a novel Recurrent Neural Network – Echo State Network to predict the next Stock Market Closing Price between a defined time series based on prior Statistical Dataset.Predicting the stock price movements,in this research also propose the Mackey-Glass system to determine how different global parameters optimize training in the echo state network.Research on the chaos in financial time series data has led us to another understanding of the distribution of relative stock prices over time.By doing research found that Lorentzian and Voigt profile distribution is a good model that can be used to explain the representatives of substantial gains and losses thick tail but did not disclose this in a typical Gaussian model.These distributions serve as an untrained stochastic model for the prediction based on historical price changes in the S&P 500 index and the training of the Echo State Network of benchmarking.The experimental results and output indicate that ESN with Mackey-Glass System demonstrates efficient results compared with different methodologies.