Institute of Information Theory and Automation

Publication details

Comparing Neural Networks and ARMA Models in Artificial Stock Market

Journal Article

Krtek Jiří, Vošvrda Miloslav

serial: Bulletin of the Czech Econometric Society vol.18, 28 (2011), p. 53-65

research: CEZ:AV0Z10750506

project(s): GD402/09/H045, GA ČR

keywords: neural networks, vector ARMA, artificial market

preview: Download

abstract (eng):

Neural networks - feed-forward neural networks and Elman's simple recurrent neural networks - are compared with vector ARMA models - VAR and VARMA - in this paper. They are compared in anartifical stock market. One risk free and one risky asset are traded in the market. There are only trend followers in this model, which use the mentioned models for forecasting change of a price of the risky asset and the dividend. traded in the market


Responsible for information: admin
Last modification: 21.12.2012
Institute of Information Theory and Automation