Article ID: | iaor2008321 |
Country: | Netherlands |
Volume: | 29 |
Issue: | 2 |
Start Page Number: | 227 |
End Page Number: | 236 |
Publication Date: | Mar 2007 |
Journal: | Journal of Policy Modeling |
Authors: | Panda Chakradhara, Narasimhan V. |
Keywords: | neural networks |
This paper brings into play neural network to make one-step-ahead prediction of weekly Indian rupee/US dollar exchange rate. We also compare the forecasting accuracy of neural network with that of linear autoregressive and random walk models. Using six forecasting evaluation criteria, we find that neural network has superior in-sample forecast than linear autoregressive and random walk models. Neural network is also found to beat both linear autoregressive and random walk models in out-of-sample forecasting. This finding provides evidence against the efficient market hypothesis and suggests that there exists always a possibility of extracting information hidden in the exchange rate and predicting it into the future. The findings in the study have implications for both policy makers and investors in the foreign exchange market.