EasyDeepLearn

What are the pitfalls of MAPE (Mean Absolute Percentage Error)?

medium

Answer

  • MAPE  =  mean(y    yhat  /  y)    100\mathrm{MAPE}\; = \;\mathrm{mean}( \mid y\; - \;y_{\mathrm{hat}} \mid \; / \; \mid y \mid )\; \cdot \;100%.
  • Issues: (1) undefined when y = 0 and explodes when y is close to 0; (2) asymmetric — over-forecasting is bounded (max 100% error), under-forecasting is unbounded; (3) biases model selection toward under-prediction.
  • Alternatives: sMAPE (symmetric), MASE (compare to naive forecast), WAPE (weighted / total absolute error / total absolute y), or use quantile losses.
  • Never use MAPE with targets that can be zero or negative.
Check yourself — multiple choice
  • MAPE handles zeros gracefully
  • MAPE is undefined for y=0, asymmetric, and biases toward under-prediction
  • MAPE is symmetric
  • MAPE is always the best regression metric

MAPE: undefined at zero, asymmetric penalty ⇒ biases toward under-forecasting.

#metrics-regression

Practise Supervised Learning

215 interview questions in this topic.

Related questions