🔬 WMAPE (Weighted Mean Absolute Percentage Error)

WMAPE (Weighted Mean Absolute Percentage Error)#

MAPE weighted by volume so large items count more.

Important

✨ AI-generated content. This page was written with the assistance of an AI language model and is provided as a learning aid. Despite careful review, it may still contain mistakes, omissions, or out-of-date information. Whether you are new to the topic, a team lead, or a senior practitioner, treat it as a starting point rather than an authoritative reference: read it critically and independently verify anything you act on (code, commands, figures, and factual claims) against official documentation and primary sources before relying on it.

What it is#

Weighted Mean Absolute Percentage Error divides the total absolute error by the total actual demand — the sum of errors over the sum of actuals:

\[\text{WMAPE} = \frac{\sum_i |y_i - \hat{y}_i|}{\sum_i |y_i|}.\]

Rather than averaging per-item percentages, it weights each error by its volume.

Why weighting matters#

Plain MAPE treats a 50% miss on a tiny item the same as on a huge one and blows up when actuals are near zero. WMAPE lets high-volume items dominate — reflecting real business impact — and stays defined as long as total demand isn’t zero, making it a retail and demand-planning staple.

Its trade-off#

Because big items dominate, WMAPE can hide poor accuracy on the long tail of small items — a model can score well while badly missing many low-volume SKUs. It is closely related to WAPE, and best read alongside a per-item metric to catch tail errors.

Theme: Model Evaluation & Uncertainty · All terminology

Hint

Mind map — connected ideas

MASE (Mean Absolute Scaled Error) · sMAPE (Symmetric Mean Absolute Percentage Error) · Mean Absolute Percentage Error (MAPE) · WAPE (Weighted Absolute Percentage Error) · Mean Absolute Error (MAE) · Root Mean Squared Error (RMSE)

Hint

More in Model Evaluation & Uncertainty

Average Absolute Error (AAE) · Baseline Heuristics · Bootstrap · Bootstrap Confidence Intervals (CIs) · Coverage · Cramér’s V · DeLong’s Test · KS Statistic (Kolmogorov–Smirnov Statistic) · Likelihood Ratio (LR) · Mann–Whitney U Test (also called the Wilcoxon rank-sum test) · MASE (Mean Absolute Scaled Error) · Mean Absolute Error (MAE) · Mean Absolute Percentage Error (MAPE) · Mean Squared Error (MSE)