Application of Neural Networks in Forecasting SSE Composite Index

Abstract:

The methodology is proposed to forecast the daily SSE Composite Index based on artificial neural network and wavelet analysis. The original Composite Index series is decomposed into various components using wavelet techniques at first. The neural network is applied for modeling components of the decomposed series. The final forecast is obtained by combining the components series forecasts. The empirical results show the superior performance of the proposed methodology as compared to the neural network forecasting models. In addition, the results show the obvious difference among different type network in forecasting performance.

• Periodical: Applied Mechanics and Materials (Volumes 321-324)
• Pages: 1921-1924
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.321-324.1921
• Online since: June 2013
• Authors: Yong Gang Xue, Ming Li Zhang
• Keywords: Forecasting Model, Neural Network (NN), Wavelet Analysis

References

[1] Ricardo de A. A quantum-inspired evolutionary hybrid intelligent approach for stock market prediction. International Journal of Intelligent Computing and Cybernetics, Vol. 2(2010),pp.24-54.

DOI: 10.1108/17563781011028532

[2] An-Sing Chena , Mark T. L , Hazem Daoukc. Application of neural networks to an emerging financial market: forecasting and trading the Taiwan Stock Index. Computers & Operations Research,Vol.30(2003), p.901–923.

DOI: 10.1016/s0305-0548(02)00037-0

[3] Chih-Hsiung Tseng et al. Artificial neural network model of the hybrid EGARCH volatility of the Taiwan stock index option prices. Physica A ,Vol.387(2008),p.3192–3200.

DOI: 10.1016/j.physa.2008.01.074

[4] Alper Ozun, Atilla Cifter. A wavelet network model for analysing exchange rate effects on interest rates. Journal of Economic Studies, Vol.37(2010), pp.405-418.

DOI: 10.1108/01443581011073408

[5] Mala Raghavan, Jonathan Dark, Elizabeth A M. Impact of capital control measures on the Malaysian stock market- A multiresolution analysis. International Journal of Managerial Finance, Vol.6(2010),pp.116-127.

DOI: 10.1108/17439131011032040

[6] Salwa Ben Ammou, Zied Kacem, Nabiha Haouas. Risk reduction using wavelets for denoising principal-components regression models . The Journal of Risk Finance, Vol.11(2010), pp.180-203.

DOI: 10.1108/15265941011025198

[7] V.N. Alexandrov et al. Hybridizing Exponential Smoothing and Neural Network for Financial Time Series Predication. Berlin Heidelberg : Springer-Verlag ,.(2006)

[8] Lee, C., Chiang, Y., Shih, C., Chun-Li Tsai. Noisy Time Series Prediction using M-estimator Based Robust Radial Basis Function Neural Networks with Growing and Pruning Techniques. Expert Systems with Application,Vol.36(2009),pp.4717-4724.

DOI: 10.1016/j.eswa.2008.06.017

[9] Sharmishtha Mitra, Amit Mitra. Modeling exchange rates using wavelet decomposed genetic neural networks. Statistical Methodology, Vol.3(2006), p.103–124.

DOI: 10.1016/j.stamet.2005.07.002