Regression Metrics

How do you know if your regression model is good? You need metrics that measure prediction quality.

Mean Absolute Error (MAE)

The average of absolute differences between predictions and actual values.

Mean Squared Error (MSE) and RMSE

R² Score (Coefficient of Determination)

Choosing the Right Metric

Key Takeaways

• MAE: Average absolute error, easy to interpret
• MSE: Penalizes large errors, used in optimization
• RMSE: Square root of MSE, same units as target
• R²: Proportion of variance explained (0-1 is good, >0.7 often acceptable)
• Different metrics for different purposes
• Always use test data for final evaluation!