provide a theoretical justification of the use of random subspace methods and show their usefulness when forecasting monthly … used to construct a forecast. Second, we discuss random projection regression, where artificial predictors are formed by … squared forecast error for both randomized methods. We identify settings in which one randomized method results in more …

This paper seeks to enhance forecast accuracy by combining three individual forecasting models. These models include … terms of predictive ability the composite model outperforms the individual forecasting models. In addition, the results … reveal that the forecast accuracy gains arising from combining the individual forecasts range from nearly 8% to over 95%. …