This paper develops a decision-analytic model to value commodity price forecasts in the presence of futures markets. The method is applied to a data set on crude oil prices. We find that to be valuable, forecasts must be accurate at predicting both gains and losses, and that there are positive and diminishing marginal returns to forecast value from improvement in key measures of accuracy. We also find that forecast value is specific to user class, and that value is unique to specific users within the class.

You can access this article if you purchase or spend a download.