MAPE (Mean Absolute Percentage Error)

Definition

MAPE measures forecast accuracy. It’s the average of the absolute percentage differences between forecast and actual values. A forecast with 10% MAPE means the forecast was off by 10% on average.

What it tells you

Lower is better. A 5–10% MAPE on weekly forecasts is very good for hotel revenue management; 15–25% is normal; over 30% means the forecast methodology needs revisiting.

How to track it

Compare forecast values to actuals after the period closes. Compute the absolute percentage error for each day; average them.

Where it fits

MAPE is the retroactive measure of forecast quality. If you’re using AI-assisted forecasting, MAPE verifies whether the AI is actually helping vs. just being expensive. (Peaqplus publishes monthly MAPE / SMAPE / MAE on customer data.)