Robert Fildes and Nikolaos Kourentzes, ISF2018, 19th June 2018
Judgement plays a central role in forecasting, as statistical forecasts are often modified before informing user decisions. There is strong evidence that judgemental adjustments can be beneficial, yet inconsistent, often harming forecast accuracy. This has motivated research into how to best manage judgemental adjustments to maximise any benefits. However, a limitation of existing work is that there is very limited research into the dynamics of judgemental adjustments: how experts adjust forecasts across time and whether their effectiveness is consistent across forecast horizons. Furthermore, it is unknown whether experts incorporate the same information, and in the same way, for different horizons. This paper attempts to address these questions by investigating the dynamics of judgemental adjustments from a UK manufacturer. Our findings suggest that there is a clear shift in the type of information integrated in the statistical forecasts, particularly across forecast horizons, resulting in changing behaviour and performance of adjustments.
Download slides.