Databricks Machine Learning Associate Question 63
Select 4A data scientist is using Databricks AutoML to build a regression model for predicting house prices. They want to understand which evaluation metrics AutoML can use to assess the performance of the generated models. Which of the following metrics are supported by Databricks AutoML for regression problems?
- A
Mean Absolute Error (MAE)
- B
Root Mean Squared Error (RMSE)
- C
R-squared (R²)
- D
F1 Score
- E
Mean Squared Logarithmic Error (MSLE)
Show answer and explanation
Correct answers: A, B, C, E
Explanation
Databricks AutoML supports several evaluation metrics for regression problems, including MAE, RMSE, R², and MSLE. These metrics help assess the performance of regression models in different ways. However, metrics like F1 Score are specific to classification tasks and are not relevant for regression.
- A. Correct.
Mean Absolute Error (MAE) is a commonly used evaluation metric in regression problems that measures the average magnitude of errors in a set of predictions, without considering their direction. It is supported by Databricks AutoML for regression.
- B. Correct.
Root Mean Squared Error (RMSE) is another supported regression metric that evaluates the square root of the average squared differences between predicted and actual values, effectively penalizing larger errors more heavily.
- C. Correct.
R-squared (R²) measures the proportion of variance in the dependent variable that is predictable from the independent variables. It is supported by Databricks AutoML for regression evaluation.
- D. Incorrect.
F1 Score is not applicable for regression problems as it is specifically designed for classification tasks, balancing precision and recall.
- E. Correct.
Mean Squared Logarithmic Error (MSLE) is a valid regression metric supported by Databricks AutoML. It is particularly useful when the target variable spans several orders of magnitude, as it penalizes under-predictions more than over-predictions.