I am working on a proof-of-concept in Excel to determine the "best" (i.e. least loss) forecast time series model.
In Excel there will be various forecast models, and based on the AvgRelMAE (average relative MAE using the geometric mean (Davydenko, A., & Fildes, R. (2016). Forecast Error Measures: Critical Review and Practical Recommendations. In Business Forecasting: Practical Problems and Solutions. John Wiley & Sons Inc.) it would select the model with the least loss.
Does anyone have experience in setting up this calculation in Excel?