How do you evaluate regression vs classification models?

How do you evaluate regression vs classification models?medium

Type: conceptual
Topic: do-you-evaluate-regression-vs-classification-models
Frequency: common
Tags: machine-learning, how, you, evaluate, regression, classification

Answer

Regression: MAE, MSE, RMSE, MAPE, R². Classification: accuracy, precision, recall, F1, AUC-ROC, log loss.

Explanation

Regression: MAE, MSE, RMSE, MAPE, R². Classification: accuracy, precision, recall, F1, AUC-ROC, log loss. For imbalanced classification, AUC-ROC and F1 are more informative than accuracy. For business-critical regression (demand forecast), MAPE is intuitive but breaks near zero — use sMAPE or RMSE with domain thresholds.

Follow-upWhen would you choose one approach over the other?