Non-traditional methods of forecasting

The traditional, statistical approach to forecasting has been based upon the identification, specification and estimation of a single model. Recently, we have seen the rise of computationally-intensive methods which depart from this protocol, such as multiple model switching, combinations and neural network methods. At the same time, we are also seeing an increased awareness of the judgements role in forecasting, also to deal with the inadequacies of model specification. This paper seeks to address the issue of achieving a balance between data and judgement and the need to develop formal methods for it to be effective.