MLS-C01 Modeling Practice Question

A data scientist is using SageMaker to train a linear learner algorithm. After training, the evaluation shows that the model has high bias. Which action is most likely to reduce bias?

⚠ Common exam trap

A common mix-up: candidates confuse bias with variance and incorrectly choose regularization (Option A) to fix underfitting, when regularization actually increases bias and is used to combat overfitting (high variance).

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

Add feature crosses for categorical variables

High bias indicates that the model is underfitting the data, meaning it is too simple to capture the underlying patterns. Adding feature crosses for categorical variables creates interaction features that allow the linear learner to model non-linear relationships, increasing model complexity and reducing bias. This is a standard technique in linear models to address underfitting without switching to a non-linear algorithm.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
Increase the L2 regularization strength
Why it's wrong here
Increasing regularization penalizes complexity and increases bias.
✗
Reduce the amount of training data
Why it's wrong here
Less data typically leads to higher bias because the model has fewer examples to learn from.
✓
Add feature crosses for categorical variables
Why this is correct
Adding feature crosses increases model capacity to capture interactions, reducing bias.
✗
Remove some features that have low variance
Why it's wrong here
Removing features reduces model complexity and increases bias.

Go deeper

MLS-C01 Modeling Practice Question

Why each option matters

Option-by-option breakdown

Related to this question