The use of GARCH-neural network model for forecasting the volatility of bid-ask spread of the Chinese stock market

Author

Li Si-ming ; Lin Zhang-xi ; Xiao Zhong-yi ; Ma Jun-wei

fYear

2012

fDate

20-22 Sept. 2012

Firstpage

1899

Lastpage

1903

Abstract

The bid-ask spread is an important indicator of the financial market liquidity and efficiency. In this paper, we study the dynamic of spread volatility of 40 constituent stocks of Shenzhen stock exchange Index (SZEI) in Chinese stock market, using GARCH family models. Perfected GARCH model is identified according to AIC and BIC criteria, then a hybrid GARCH-Neural Network (GARCH-NN) model based on it is proposed to forecast the volatility of SZEI bid-ask spread. Forecast performances are obtained by the perfected GARCH model is compared with that in GARCH-NN based on the SZEI bid-ask spread dataset. The results show that the hybrid model we propose makes better results.

Keywords

autoregressive processes; economic indicators; forecasting theory; neural nets; stock markets; tendering; AIC criteria; BIC criteria; Chinese stock market; GARCH-NN model; GARCH-neural network model; SZEI bid-ask spread volatility forecasting; Shenzhen stock exchange index; financial market efficiency; financial market liquidity; performance forecasting; Computational modeling; Data models; Forecasting; Mathematical model; Neural networks; Predictive models; Stock markets; GARCH models; Neural Network model; bid-ask spread; volatility;

fLanguage

English

Publisher

ieee

Conference_Titel

Management Science and Engineering (ICMSE), 2012 International Conference on

Conference_Location

Dallas, TX

ISSN

2155-1847

Print_ISBN

978-1-4673-3015-2

Type

conf

DOI

10.1109/ICMSE.2012.6414430

Filename

6414430