This measurement is not as widely used as MSE and MAE, but it is used as the metric for the Kaggle competition that uses the bike-sharing dataset. It is, effectively, the RMSE of the log-transformed predicted and target values. This measurement is useful when there is a wide range in the target variable, and you do not necessarily want to penalize large errors when the predicted and target values are themselves high. It is also effective when you care about percentage errors rather than the absolute value of errors.
The Kaggle competition evaluation page can be found at https://www.kaggle.com/c/bike-sharing-demand/details/evaluation.
The function to compute RMSLE is shown here:
Scala def squaredLogError(actual:Double, ...
