Novel stock market prediction using a hybrid model of adptive linear combiner and differential evolution

Abstract

The paper proposes a novel forecasting model for efficient prediction of small and long range predictions of stock indices particularly the DJIA and S&P500. The model employs an adaptive structure containing a linear combiner with adjustable weights implemented using differential evolution. The learning algorithm using DE is dealt in details. The key features of known stock time series are extracted and used as inputs to the model for training its parameters. Exhaustive simulation study indicates that the performance of the proposed model with test input is quite satisfactory and superior to those provided by previously reported GA and PSO based forecasting models. � 2011 Springer-Verlag Berlin Heidelberg.