Forecast Evaluation of the Exchange Rate Using Artificial Neural Networks and Asymmetric Cost Functions

Munir Andrés Jalil & Martha Misas

 

Abstract

We compare forecasts obtained via linear vs. non linear specifications. The models are adjusted to the daily percentage change of the exchange rate and the  comparison is done using both symmetric and asymmetric cost functions. Results show that the non linear model (which here takes the form of an Artificial Neural Network –ANN) performs better in terms of forecasting ability when evaluated with both types of cost functions. Further more, when using asymmetric costs, the ANN is a much better predictor than its linear counterpart

 

Key words: Time series models, Nonlinear models, Foreign exchange.

 

PDF (Spanish)