Comparing Neural Networks and ARMA Models in Artificial Stock Market

0361537 - ÚTIA 2012 RIV CZ eng J - Journal Article
Krtek, Jiří - Vošvrda, Miloslav
Comparing Neural Networks and ARMA Models in Artificial Stock Market.
Bulletin of the Czech Econometric Society. Roč. 18, č. 28 (2011), s. 53-65. ISSN 1212-074X
R&D Projects: GA ČR GD402/09/H045
Institutional research plan: CEZ:AV0Z10750506
Keywords : neural networks * vector ARMA * artificial market
Subject RIV: AH - Economics
http://library.utia.cas.cz/separaty/2011/E/krtek-comparing neural networks and arma models in artificial stock market.pdf

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
Permanent Link: http://hdl.handle.net/11104/0198831