A0452
Title: Global combinations of expert forecasts
Authors: Ryan Thompson - University of New South Wales (Australia) [presenting]
Andrey Vasnev - University of Sydney (Australia)
Yilin Qian - University of Sydney (Australia)
Abstract: Expert forecast combination- aggregating individual forecasts from multiple subject-matter experts- is a proven approach to economic forecasting. To date, research in this area has exclusively concentrated on local combination methods, which handle separate but related forecasting tasks in isolation. Yet, the machine learning community has known for over two decades that global methods, which exploit task-relatedness, can improve on local methods that ignore it. Motivated by the possibility for improvement, a framework is introduced for globally combining expert forecasts. Through this framework, global versions of several existing forecast combinations are developed. To evaluate the efficacy of these new global forecast combinations, extensive comparisons are reported using synthetic and real data. Our real data comparisons, which involve expert forecasts of core economic indicators in the Eurozone, are the first empirical evidence that the accuracy of global combinations of expert forecasts can surpass local combinations.
