Weighted Absolute Percentage Error (WAPE)

This metric is calculated by weighting the error between the actual values and forecasts with the sum of the actual values over all units of time. A lower WAPE value implies a higher accuracy of the model. WAPE is an error metric that is robust to outliers. A disadvantage of WAPE is that it produces undefined values when the sum of actual values are zero over all units of time. In these cases, Demand Modeler treats the actual value in the denominator as one, thus the calculation is equivalent to the absolute differences between actual values and forecasts. In the context of demand forecasting, weighted mean absolute percentage error (WMAPE) is equivalent to WAPE when the errors are weighted by sales volume.