What About Asymmetric Loss? A Real-Time Quantile-Regression Update on the AUD-Yen Exchange Rate

I use a real-time quantile-regression approach to analyze whether commodity prices have predictive value for movements of the Australian dollar-Japanese yen exchange rate. I use various alternative datasets that contain the Goldman Sachs Commodity Index and its five subindices to analyze the impact of commodities on forecast accuracy of the AUDyen rate. I find evidence that monetary exchange rate forecasting models that include commodity prices are able to outperform a random walk, as far as the forecaster has an asymmetric loss function, and a constant returns model as well