A novel hybrid ensemble model to predict FTSE100 index by combining neural network and EEMD

Abstract

Prediction stock price is considered the most challenging and important financial topic. Thus, its complexity, nonlinearity and much other characteristic, single method could not optimize a good result. Hence, this paper proposes a hybrid ensemble model based on BP neural network and EEMD to predict FTSE100 closing price. In this paper there are five hybrid prediction models, EEMD-NN, EEMD-Bagging-NN, EEMD-Cross validation-NN, EEMD-CV-Bagging-NN and EEMD-NN-Proposed method. Experimental result shows that EEMD-Bagging-NN, EEMD-Cross validation-NN and EEMD-CV-Bagging-NN models performance are a notch above EEMD-NN and significantly higher than the single-NN model. In addition, EEMD-NN-Proposed method prediction performance superiority is demonstrated comparing with the all presented model in this paper, and was feasible and effective in prediction FTSE100 closing price. As a result of the significant performance of the proposed method, the method can be utilized to predict other financial time series data.