MLA-C01 exam dumps

MLA-C01 practice question 290 of 458

AWS Certified Machine Learning Engineer - Associate. Associate level, Amazon Web Services. Free question with the correct answer and a full explanation.

MLA-C01 Question 290

Select 2

You are tasked with building a machine learning model using Amazon SageMaker to predict customer churn. During the process, you notice that your training dataset contains missing values in several features. Which of the following steps should you take to handle this issue effectively in Amazon SageMaker?

  1. A

    Use SageMaker's built-in data preprocessing feature to automatically handle missing values.

  2. B

    Impute missing values using statistical methods such as mean, median, or mode before training the model.

  3. C

    Remove all rows with missing values from the dataset to ensure the model receives clean data.

  4. D

    Train the model without addressing missing values, as SageMaker handles them during model training.

  5. E

    Use SageMaker Data Wrangler to identify and handle missing values as part of the data preprocessing pipeline.

Show answer and explanation

Correct answers: B, E

Explanation

Handling missing values is a critical step in preparing data for machine learning models. SageMaker does not automatically handle missing values during preprocessing or model training, so it is up to the user to address this issue. Imputing missing values with statistical methods and leveraging SageMaker Data Wrangler for preprocessing are both effective strategies. Removing rows with missing values is typically not recommended as it can lead to significant data loss.

  • A. Incorrect.

    SageMaker does not automatically handle missing values during preprocessing; you need to address them explicitly.

  • B. Correct.

    Imputing missing values using statistical methods is a common and effective strategy to handle missing data before training a machine learning model.

  • C. Incorrect.

    Removing rows with missing values can lead to loss of critical data, especially if missing values are prevalent in the dataset. This approach is generally not recommended unless missing data is minimal.

  • D. Incorrect.

    SageMaker does not automatically handle missing values during training; you must preprocess the data to handle them appropriately.

  • E. Correct.

    SageMaker Data Wrangler provides advanced capabilities for data preprocessing, including identifying and handling missing values effectively.

Timed practice exam

Take a MLA-C01 practice test under exam conditions

65 questions in 130 minutes, drawn from this bank, with a score report and a per-question review when you finish.

Start timed exam