In this preliminary work on the application of Hybrid Algorithms to FinancialForecasting (HAF2) we show a computational approach integrating ArtificialNeural Networks (ANN) and Genetic Algorithms (Gas) facing the problem ofbuilding the optimal model in a multivariate non-linear environment. This is thetypical environment in financial and economical time series where the number ofvariables influencing a given phenomena is really high and moreover thefunctional relations linking them are not a-priori known.Because of their high flexibility Artificial Neural Networks (ANNs) have beenwidely used to build non linear regression models. However, the problem to buildthe best ANN is still open as well as the related problem of the best set ofvariables to be selected as regressors.In this paper we propose an hybrid algorithm (GANND, A Genetic Algorithm forNeural Network Design) integrating Genetic Algorithms and ANN toautomatically build an efficient predictive non linear model starting by theempirical data set. We also show some experimental results obtained by applyingGANND to predict an Italian financial bond (FIB30).

GANND: A Genetic Algorithm for Predictive Neural Network Design - A Financial Application, Economics & Complexity, 4 / Minerva, Tommaso; Paterlini, Sandra; I., Poli. - In: ECONOMICS & COMPLEXITY. - ISSN 1398-1706. - STAMPA. - 2:(2000), pp. 4-14.

GANND: A Genetic Algorithm for Predictive Neural Network Design - A Financial Application, Economics & Complexity, 4

MINERVA, Tommaso;PATERLINI, Sandra;
2000

Abstract

In this preliminary work on the application of Hybrid Algorithms to FinancialForecasting (HAF2) we show a computational approach integrating ArtificialNeural Networks (ANN) and Genetic Algorithms (Gas) facing the problem ofbuilding the optimal model in a multivariate non-linear environment. This is thetypical environment in financial and economical time series where the number ofvariables influencing a given phenomena is really high and moreover thefunctional relations linking them are not a-priori known.Because of their high flexibility Artificial Neural Networks (ANNs) have beenwidely used to build non linear regression models. However, the problem to buildthe best ANN is still open as well as the related problem of the best set ofvariables to be selected as regressors.In this paper we propose an hybrid algorithm (GANND, A Genetic Algorithm forNeural Network Design) integrating Genetic Algorithms and ANN toautomatically build an efficient predictive non linear model starting by theempirical data set. We also show some experimental results obtained by applyingGANND to predict an Italian financial bond (FIB30).
2000
2
4
14
GANND: A Genetic Algorithm for Predictive Neural Network Design - A Financial Application, Economics & Complexity, 4 / Minerva, Tommaso; Paterlini, Sandra; I., Poli. - In: ECONOMICS & COMPLEXITY. - ISSN 1398-1706. - STAMPA. - 2:(2000), pp. 4-14.
Minerva, Tommaso; Paterlini, Sandra; I., Poli
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/697672
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact