DEA in performance evaluation of crude oil prediction models

Forecasts play a crucial role in driving our decisions and shaping our future plans. In practice, prediction problems differ with respect to many dimensions; however, regardless of how one defines the prediction problem, a common issue faced by both academics and professionals is related to the performance evaluation of competing prediction models. Although most studies tend to use several performance criteria and, for each criterion, one or several metrics to measure each criterion, the assessment of the relative performance of competing forecasting models is generally restricted to ranking by measure, which usually leads to different monocriteria rankings. The lack of a multicriteria framework for performance evaluation of competing prediction models has motivated this line of research, in which we have proposed several frameworks based on DEA analysis. This chapter reports on the use of DEA in evaluating the performance of competing prediction models. For illustration purposes, we use forecasting of crude oil price volatility as an application area.