Root Mean Squared Error (RMSE)

This metric is the square root of the average squared errors between the actual values and forecasts for each unit of time. It is an extension of the mean squared error. A lower RMSE value implies a higher accuracy of the model. Like MSE, this metric is sensitive towards outliers. A few large deviations in forecasting can severely punish a model due to the squared error. RMSE is easier to understand because it is in the same unit with the variable of interest. A forecast method that minimizes the root mean squared error will lead to forecasts of the mean.