Abstract

Many studies have demonstrated that back-propagation neural network can be effectively used to uncover the nonlinearity in the financial markets. Unfortunately, back-propagation algorithm suffers the problems of slow convergence, inefficiency, and lack of robustness. This paper introduces a multi-stage optimization approach (MSOA) used in back-propagation algorithm for training neural network to forecast the Chinese food grain price. We divide the training sample of neural network into two parts considering the truth that the recent observations is more important than the older ones. Firstly, we use the first training sample to train the neural network and achieve the network structure. Secondly, we continue to use the second training sample to further optimize the structure of neural network based on the previous step. Empirical results show that MSOA overcomes the weakness of conventional BP algorithm to some extend. Furthermore the neural network based on MSOA can improve the forecasting performance significantly in terms of the error and directional evaluation measurements. The paper also proves accurate price estimation may not be a good predictor of the direction of change in the price levels in food market. The neural network based on MSOA can be used as an alternative forecasting method for future Chinese food price forecasting.

Keywords: Artificial neural network; Back-propagation; Time series forecasting; Multi-stage optimization approach; Food price forecasting

Article Outline

1. Introduction

2. Methodology

2.1. ARIMA time series model

2.2. Artificial neural network model

2.3. A multi-stage optimization approach

3. Data description and forecast evaluation criteria

4. Forecast procedure

4.1. The selection of ARIMA model

4.2. Fitting neural network models to the data

4.2.1. Criterions of selection of the models

4.2.2. Experiment conditions

4.2.3. Comparison between MSOA and conventional BP algorithm

4.2.3.1. Training time and convergence

4.2.3.2. Forecasting accuracy

5. Results

5.1. Quantitative evaluation

5.2. Turning point evaluation

6. Conclusion

Acknowledgements

References