Hybrid ARIMA-BPNN model for time series prediction of the Chinese stock market
Authors:
- 1 April 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 93-97
Abstract
Stock price prediction is a challenging task owing to the complexity patterns behind time series. Autoregressive integrated moving average (ARIMA) model and back propagation neural network (BPNN) model are popular linear and nonlinear models for time series forecasting respectively. The integration of two models can effectively capture the linear and nonlinear patterns hidden in a time series and improve forecast accuracy. In this paper, a new hybrid ARIMA-BPNN model containing technical indicators is proposed to forecast four individual stocks consisting of both main board market and growth enterprise market in software and information services sector. Experiment results show that the proposed method achieves the better one-step-ahead forecasting accuracies namely 78.79%, 72.73%, 59.09% and 66.67% respectively for each series than those of ARIMA, BPNN, and Khashei and Bijari's hybrid models.Keywords
This publication has 10 references indexed in Scilit:
- A hybrid ANFIS model based on empirical mode decomposition for stock time series forecastingApplied Soft Computing, 2016
- Hybrid nonlinear adaptive scheme for stock market prediction using feedback FLANN and factor analysisJournal of the Korean Statistical Society, 2016
- Volatility Forecast Based on the Hybrid Artificial Neural Network and GARCH-type ModelsProcedia Computer Science, 2016
- Prediction of selected Indian stock using a partitioning–interpolation based ARIMA–GARCH modelApplied Computing and Informatics, 2015
- Stock index forecasting based on a hybrid modelOmega, 2012
- Combining nonlinear independent component analysis and neural network for the prediction of Asian stock market indexesExpert Systems with Applications, 2012
- Forecasting stock indices with back propagation neural networkExpert Systems with Applications, 2011
- Using artificial neural network models in stock market index predictionExpert Systems with Applications, 2011
- Predicting direction of stock price index movement using artificial neural networks and support vector machines: The sample of the Istanbul Stock ExchangeExpert Systems with Applications, 2011
- Time series forecasting using a hybrid ARIMA and neural network modelNeurocomputing, 2003