MLS-C01 Question 209
Select 2You are training a random forest model using Amazon SageMaker to classify customer purchasing behavior. During your testing phase, you notice that the model is underfitting the training data, resulting in low accuracy. Which of the following adjustments should you make to improve the model's performance?
- A
Increase the number of trees in the forest.
- B
Decrease the maximum depth of the trees.
- C
Increase the maximum depth of the trees.
- D
Reduce the number of features considered for each split.
- E
Enable early stopping in the training process.
Show answer and explanation
Correct answers: A, C
Explanation
Underfitting occurs when a model is too simple to capture the underlying patterns in the data. To address this, you can increase the number of trees in the random forest, as this provides more opportunities to capture patterns. Additionally, increasing the maximum depth of the trees allows the model to learn more complex patterns in the data. These adjustments improve the model's ability to better fit the training data and increase accuracy.
- A. Correct.
Increasing the number of trees can help reduce underfitting by allowing the model to capture more patterns in the data.
- B. Incorrect.
Decreasing the maximum depth of the trees limits the complexity of the model, which would worsen underfitting instead of improving it.
- C. Correct.
Increasing the maximum depth of the trees allows the model to capture more complex patterns, which can help address underfitting.
- D. Incorrect.
Reducing the number of features considered for each split can make the model less complex and increase underfitting, so this is not a suitable adjustment.
- E. Incorrect.
Early stopping is typically used to prevent overfitting rather than to address underfitting. It is not relevant to this scenario.