Databricks Machine Learning Associate Question 47
Select 3You are using Databricks AutoML to train a machine learning model for a regression task. Which of the following steps in the machine learning workflow are automatically handled by AutoML?
- A
Data preprocessing, such as handling missing values and encoding categorical features
- B
Feature engineering, such as creating domain-specific features using business logic
- C
Model selection and hyperparameter tuning
- D
Generating a notebook with code for reproducibility
- E
Deploying the final model to a production environment
Show answer and explanation
Correct answers: A, C, D
Explanation
Databricks AutoML simplifies the machine learning workflow by automating key steps like data preprocessing, model selection, hyperparameter tuning, and generating reproducible code. However, tasks requiring domain expertise (e.g., feature engineering) and production deployment are beyond its scope and require manual intervention.
- A. Correct.
AutoML handles basic data preprocessing tasks like handling missing values and encoding categorical features, as these are essential steps for preparing data for machine learning.
- B. Incorrect.
AutoML does not perform domain-specific feature engineering, as it requires domain knowledge and business logic that cannot be automated.
- C. Correct.
AutoML performs model selection and hyperparameter tuning by testing multiple algorithms and configurations to identify the best-performing model.
- D. Correct.
AutoML generates a notebook with the code used during the experiment, which can be used for reproducibility and further customization.
- E. Incorrect.
AutoML does not handle deployment of the model to production; this step requires additional configuration and integration with deployment tools.