MLA-C01 · Question #175
A company is using Amazon SageMaker AI to develop a credit risk assessment model. During model validation, the company finds that the model achieves 82% accuracy on the validation data. However, the…
The correct answer is B. Implement dropout layers. Use L1 or L2 regularization. Perform k-fold cross-validation. Dropout and L1/L2 regularization reduce overfitting by constraining the model and preventing it from memorizing the training data. K-fold cross-validation helps validate that the model generalizes well across different data splits, improving validation accuracy before deployment.
Question
A company is using Amazon SageMaker AI to develop a credit risk assessment model. During model validation, the company finds that the model achieves 82% accuracy on the validation data. However, the model achieved 99% accuracy on the training data. The company needs to address the model accuracy issue before deployment. Which solution will meet this requirement?
Options
- AAdd more dense layers to increase model complexity. Implement batch normalization. Use early
- BImplement dropout layers. Use L1 or L2 regularization. Perform k-fold cross-validation.
- CUse principal component analysis (PCA) to reduce the feature dimensionality. Decrease model
- DAugment the training dataset. Remove duplicate records from the training dataset. Implement
How the community answered
(43 responses)- A19% (8)
- B70% (30)
- C5% (2)
- D7% (3)
Explanation
Dropout and L1/L2 regularization reduce overfitting by constraining the model and preventing it from memorizing the training data. K-fold cross-validation helps validate that the model generalizes well across different data splits, improving validation accuracy before deployment.
Topics
Community Discussion
No community discussion yet for this question.