Prediction of exchange rate peso-dollar using Artificial Neuronal Networks (ANR´s)
Luis Alberto Zapata Garrido, Hugo Fabián Díaz Mojica · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · 2011
The objective of the present work is to realize predictions of the typeof change peso-dollar being used Artificial Neuronal Networks (ANR´s),for which, the investigation was based to determine the existing relationbetween the obtained results and the effective types of change in the datesof study, to determine the type of neuronal network that adapts more to theprediction of types of change and to analyze the behavior of the variablesof the ANR in the process of prediction of the types of change. In order toobtain this, using software Easy-N-extra, we selected information of twelveeconomic variables of the year 2005 that served as entrance to a system ofneuronal networks, in that the exit was the type of change. Once realizedthe training of the network and established the values of the variables ofentrance for the prediction process, the values of the type of change forthe first month of year 2006 were obtained; of this form, eighteen testswere realized, using different combinations from variables. The obtainedresults show to low allowable errors between the predictions and the realresults.