Mean Absolute Percentage Error for regression models
This work addresses the theoretical foundations of MAPE as a regression metric, which is incremental for researchers and practitioners in machine learning and statistics.
The paper investigates the use of Mean Absolute Percentage Error (MAPE) for regression models, proving the existence of an optimal MAPE model and demonstrating the universal consistency of Empirical Risk Minimization based on MAPE, with applications to kernel regression on simulated data.
We study in this paper the consequences of using the Mean Absolute Percentage Error (MAPE) as a measure of quality for regression models. We prove the existence of an optimal MAPE model and we show the universal consistency of Empirical Risk Minimization based on the MAPE. We also show that finding the best model under the MAPE is equivalent to doing weighted Mean Absolute Error (MAE) regression, and we apply this weighting strategy to kernel regression. The behavior of the MAPE kernel regression is illustrated on simulated data.