🔬 WAPE (Weighted Absolute Percentage Error)

WAPE (Weighted Absolute Percentage Error)#

Total absolute error divided by total actuals.

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 Despite careful review, it may still contain mistakes, omissions, or out-of-date information.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 Absolute Percentage Error divides the total absolute forecast error by the total actual demand:

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

It expresses aggregate error as a single percentage, weighting each item by its volume.

Why retailers use it#

Unlike MAPE, WAPE doesn’t blow up when individual actuals are near zero (common for slow-moving SKUs), and it lets high-volume items dominate — reflecting real demand. It stays defined as long as total demand isn’t zero, which makes it the default accuracy metric in demand planning.

How it connects#

WAPE is effectively the same quantity as WMAPE, and it is the number that drives inventory — high WAPE means forecasts are far off, feeding both overstock and stockouts. Cutting WAPE is how planners shrink those costly failure modes.

Theme: Model Evaluation & Uncertainty · All terminology

Hint

Mind map — connected ideas

WMAPE (Weighted Mean Absolute Percentage Error) · MASE (Mean Absolute Scaled Error) · Mean Absolute Percentage Error (MAPE) · Overstock % · Stockouts · Mean Absolute Error (MAE)

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)