Title :
Inflation forecasting - a comparison between econometric methods and a computational approach based on genetic-neural fuzzy rule-bases
Author :
Kooths, Stefan ; Mitze, Timo ; Ringhut, Eric
Author_Institution :
Muenster Inst. for Computational Econ., Germany
Abstract :
The paper seeks to determine whether the predictive power of linear econometric models outperforms models based on artificial intelligence methods (computational methods) concerning forecasting inflation. Various models of both types are constructed and compared according to a battery of test statistics. We find some superiority of the computational approach.
Keywords :
economic cybernetics; financial data processing; fuzzy logic; genetic algorithms; knowledge based systems; neural nets; time series; uncertainty handling; artificial intelligence; computational approach; econometric methods; economics; genetic-neural fuzzy rule-bases; inflation forecasting; linear econometric models; time series; Artificial neural networks; Computational intelligence; Econometrics; Economic forecasting; Economic indicators; Exchange rates; Industrial economics; Instruments; Power generation economics; Predictive models;
Conference_Titel :
Computational Intelligence for Financial Engineering, 2003. Proceedings. 2003 IEEE International Conference on
Print_ISBN :
0-7803-7654-4
DOI :
10.1109/CIFER.2003.1196259
