2014 | OriginalPaper | Buchkapitel
Intelligent System for Time Series Prediction in Stock Exchange Markets
verfasst von : Nicoleta Liviana Tudor
Erschienen in: Business Information Systems
Verlag: Springer International Publishing
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This article presents an intelligent system using artificial neural techniques for time series prediction in stock exchange markets. For this purpose, is developed a hybrid neural network with supervised learning algorithm able to learn to predict the evolution of stock exchange for a given period of time. The learning model proposed for the intelligent system considers a First Input First Output (FIFO) queue with input values taken from the values obtained by prediction by the neural network at previous time. Analysis of the performance parameters of the neural network uses the method of the coefficient of certainty of neural prediction. Experimental study highlights the effectiveness of the proposed learning model for hybrid neural predictive system properties and its usefulness.