Discuss the evaluation metrics that AutoML can use for regression problems. Explain how each metric quantifies the performance of a regression model and which scenarios each metric is most suitable for.

Simulated

Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), R-squared (R²), and Mean Percentage Error (MPE).

22.1%

Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE), Adjusted R-squared, and Median Absolute Deviation (MAD).

10.4%

Root Mean Squared Logarithmic Error (RMSLE), Coefficient of Determination (R²), Mean Bias Deviation (MBD), and Mean Absolute Scaled Error (MASE).

11.7%

Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), R-squared (R²), and Mean Absolute Percentage Error (MAPE).

55.8%

Databricks Certified Machine Learning - Associate