Principle component forecast averaging — Application to the UK electricity market

In the paper, a forecast combination via dimension reduction techniques is applied to forecasting electricity spot prices. We propose to use a Factor Averaging (FA) method, which is based on a principle component approach. This methodology allows to extract information from a large panel of forecasts and helps to solve two important issues: collinearity of forecasts and common bias of different predicting methods. The empirical performance of FA and other forecast averaging methods is evaluated using the data describing the UK market. Twenty four individual methods are used to calculate one day ahead forecast of 48 hal-hourly prices. The outcomes prove that FA is more efficient in terms of the RMSE than other forecast combining approaches. Gains from using FA varies between 8-20% when comparing the average daily RMSE and between 1-40% when individual half-hourly periods are considered.