MLA-C01 Question 154
Single answerYou are building a machine learning pipeline on AWS to predict customer churn for a subscription-based service. After preprocessing your data using Amazon SageMaker Processing Jobs, you want to train a model using an algorithm that automatically tunes hyperparameters to optimize performance. Which SageMaker built-in algorithm should you choose to achieve this?
- A
Linear Learner
- B
XGBoost
- C
BlazingText
- D
Autopilot
Show answer and explanation
Correct answer: D
Explanation
SageMaker Autopilot is the correct choice for this scenario as it automates the entire machine learning workflow, including preprocessing, model selection, and hyperparameter optimization. This makes it ideal for efficiently building and tuning predictive models like customer churn prediction without requiring manual effort in hyperparameter tuning.
- A. Incorrect.
Linear Learner is a built-in algorithm for binary or multi-class classification and regression tasks, but it does not automatically tune hyperparameters. You would need to explicitly set up hyperparameter tuning jobs.
- B. Incorrect.
XGBoost is a popular gradient boosting algorithm available in SageMaker, but like Linear Learner, it requires a separate hyperparameter tuning job to optimize its parameters.
- C. Incorrect.
BlazingText is used for natural language processing tasks like text classification or word embeddings and does not inherently include automatic hyperparameter tuning.
- D. Correct.
Autopilot is a SageMaker feature that automatically builds, trains, and tunes the best machine learning models based on your data, including hyperparameter optimization.