Forecasting stochastic neural network based on financial empirical mode decomposition. (June 2017)

• Record Type: Journal Article
• Authors: Wang, Jie; Wang, Jun
• Is Part Of: Neural networks. Volume 90(2017)
• Page Start: 8
• Page End: 20
• Publication Date: 2017-06
• Subjects: EMD–STNN forecasting model -- Stock market fluctuation -- Empirical mode decomposition -- Stochastic time strength function -- Multiscale-MCID analysis; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2017.03.004
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: In an attempt to improve the forecasting accuracy of stock price fluctuations, a new one-step-ahead model is developed in this paper which combines empirical mode decomposition (EMD) with stochastic time strength neural network (STNN). The EMD is a processing technique introduced to extract all the oscillatory modes embedded in a series, and the STNN model is established for considering the weight of occurrence time of the historical data. The linear regression performs the predictive availability of the proposed model, and the effectiveness of EMD–STNN is revealed clearly through comparing the predicted results with the traditional models. Moreover, a new evaluated method ( q -order multiscale complexity invariant distance) is applied to measure the predicted results of real stock index series, and the empirical results show that the proposed model indeed displays a good performance in forecasting stock market fluctuations. Highlights: A new hybrid forecasting model is established by combining EMD method with a stochastic time strength neural network. The forecasting efficiency of stock price fluctuations is improved by the model. The forecasting results of the proposed model are more accurate than compared models. A new distance analysis method is applied to confirm the predicting results.