Time Series Forecasting Performance Indicators

You can assess the performance of your Time Series Forecasting model using one of the performance indicators below:

What Does "Expected" Mean?

The Expected MAPE (Mean Absolute Percentage Error) is the evaluation of the error made when using the predictive model to estimate the future values of the target, over the horizon. For each actual observed value, the predictive model calculates as many forecasted values as requested by the analyst. This is called the horizon of forecasts. Each of those forecasted values is compared to the corresponding actual ones to calculate a performance indicator. Then, for each horizon, a per-horizon performance indicator can be calculated. The Expectedvalue of the performance indicator is the mean of all per-horizon values that have been calculated (Horizon-Wide performance indicator).

Example

If the Expected value of a performance indicator is 12%, the value of that same performance indicator is expected to be close to 12% when using a forecasted value.