AI-900 Question 129
Select 3A data scientist wants to create a machine learning model to predict customer churn but has limited experience with coding and data preprocessing. How can Azure's automated machine learning (AutoML) help in this scenario?
- A
It can automatically preprocess the data, including handling missing values and scaling features.
- B
It requires the data scientist to manually select the best machine learning algorithm.
- C
It generates multiple models and ranks them based on performance metrics.
- D
It automatically deploys the selected model to a production environment without any user input.
- E
It allows the data scientist to specify evaluation criteria, such as accuracy or F1 score, to optimize the model.
Show answer and explanation
Correct answers: A, C, E
Explanation
Azure's automated machine learning simplifies the process of building machine learning models by automating many complex tasks, such as data preprocessing, model selection, and hyperparameter tuning. It also provides flexibility by allowing users to define evaluation criteria to optimize the model for specific business objectives. However, deployment still requires user input and configuration to ensure proper integration into the production environment.
- A. Correct.
Azure AutoML includes automated data preprocessing capabilities, such as handling missing values, scaling numerical features, and encoding categorical variables, which simplifies the process for users with limited experience.
- B. Incorrect.
This is incorrect because Azure AutoML automatically selects and tests multiple algorithms, eliminating the need for the data scientist to manually choose the best one.
- C. Correct.
Azure AutoML generates and evaluates multiple models, providing rankings based on specified performance metrics, which helps users identify the most effective model.
- D. Incorrect.
This is incorrect because, while Azure AutoML facilitates deployment, it requires user confirmation and configuration for deploying a model to production.
- E. Correct.
Azure AutoML allows users to define evaluation criteria, such as accuracy, precision, recall, or F1 score, to guide the optimization process and ensure the model meets specific requirements.