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.
The MAPE is the mean of the absolute differences between actual and forecasted values, expressed as a percentage of actual values.
The lower the MAPE the better the model. A MAPE of zero indicates a perfect predictive model.
An Expected MAPE of 12% indicates that the error made when using a forecasted value will be close to 12% of the actual value.
MAPE is often preferred because it's a simple percentage indicator and values of MAPE can be compared between different entities.
However, the MAPE can be misleadingly high when the actual values are close to zero (because the error is divided by a value close to zero), wrongly suggesting that the model is not accurate. In such cases, other performance indicators should be preferred.