Forecasting GDP growth based on Ant Colony Clustering Algorithm and RBF neural network

Author

Zhao, Jianna ; Wang, Xinying ; Wu, Zhuozheng

Author_Institution

North China Electr. Power Univ., Baoding

fYear

2008

fDate

1-3 Sept. 2008

Firstpage

1839

Lastpage

1843

Abstract

In order to forecast GDP growth much more accurate, a hybrid intelligent system is applied to improve the precision of forecasting, which combines ant colony clustering algorithm (ACCA) and RBF neural network. At first, we can make use of ACCA to cluster the data. And then, this clustered data is used to develop classification rules and train RBF neural network. The effectiveness of our methodology was verified by experiment data.

Keywords

economic forecasting; economic indicators; evolutionary computation; learning (artificial intelligence); optimisation; pattern classification; pattern clustering; radial basis function networks; GDP growth forecasting; Gross Domestic Product; RBF neural network training; ant colony clustering algorithm; data classification rule; evolutionary algorithm; intelligent system; Ant colony optimization; Automation; Clustering algorithms; Economic forecasting; Economic indicators; Logistics; Mathematical model; Neural networks; Predictive models; Radial basis function networks; GDP forecast; RBF neural network; ant colony Algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Automation and Logistics, 2008. ICAL 2008. IEEE International Conference on

Conference_Location

Qingdao

Print_ISBN

978-1-4244-2502-0

Electronic_ISBN

978-1-4244-2503-7

Type

conf

DOI

10.1109/ICAL.2008.4636457

Filename

4636457