Improving short-term EOP prediction using combination procedures

A well known problem with EOP prediction is that a prediction strategy proved to be the best for some testing period and prediction length may not remain as such for other period of time. In this paper we consider possible strategies to combine EOP predictions made using different analysis technique to obtain a final prediction with the best accuracy corresponding to the least prediction error between input predictions. This approach can be used to improve the short-term real-time EOP forecast.