Deterministic Echo State Networks Based Stock Price Forecasting

Jingpei Dan,Bin Fang,Wenbo Guo,Weiren Shi,Tingping Zhang

doi:10.1155/2014/137148

Jingpei Dan, Bin Fang + Show 3 more

Open Access

https://doi.org/10.1155/2014/137148

Copy DOI

Abstract

Echo state networks (ESNs), as efficient and powerful computational models for approximating nonlinear dynamical systems, have been successfully applied in financial time series forecasting. Reservoir constructions in standard ESNs rely on trials and errors in real applications due to a series of randomized model building stages. A novel form of ESN with deterministically constructed reservoir is competitive with standard ESN by minimal complexity and possibility of optimizations for ESN specifications. In this paper, forecasting performances of deterministic ESNs are investigated in stock price prediction applications. The experiment results on two benchmark datasets (Shanghai Composite Index and S&P500) demonstrate that deterministic ESNs outperform standard ESN in both accuracy and efficiency, which indicate the prospect of deterministic ESNs for financial prediction.

Highlights

Prediction in financial or stock markets is a challenging research topic since the stock market is mostly complex and volatile
The echo state network (ESN) models perform competitively in forecasting accuracy, the deterministic ESN models have obvious advantages in efficiency which is indicated by the average time saving of 23.46%, 23.45%, and 23.41% for Simple cycle reservoir (SCR), DLR with backward connections (DLRB), and Delay line reservoir (DLR), respectively
A new method for stock price forecasting by applying deterministic ESN models is presented in this paper

Summary

Introduction

Prediction in financial or stock markets is a challenging research topic since the stock market is mostly complex (nonlinear) and volatile. A new form of RNN training methods, echo state network (ESN), has been proposed by Jaeger and Haas [1], which is simple and applicable for time series prediction with high accuracy and computational efficiency. During these ten years, ESNs have been applied in many areas, including time series forecasting [2–7], wireless communication [1], robot control [8], and speech recognition [9]. This study investigates the performance of deterministic ESN for time series forecasting and its application of stock price prediction. Echo state network is a recurrent discrete-time neural network with input, internal units (dynamic reservoir), and output. The memoryless readout is the only part that needs to be trained linearly with echo states; the training becomes a simple linear regression, which makes the application of RNNs fast and easy

Methods

Results

Conclusion