nerdexam
Amazon

MLS-C01 · Question #287

A financial services company wants to automate its loan approval process by building a machine learning (ML) model. Each loan data point contains credit history from a third-party data source and…

The correct answer is C. Use SageMaker Clarify to generate the explanation report. Attach the report to the predicted. To automate loan approvals in SageMaker and generate an explanation report for each prediction with the least development effort, SageMaker Clarify should be used.

Machine Learning Implementation and Operations

Question

A financial services company wants to automate its loan approval process by building a machine learning (ML) model. Each loan data point contains credit history from a third-party data source and demographic information about the customer. Each loan approval prediction must come with a report that contains an explanation for why the customer was approved for a loan or was denied for a loan. The company will use Amazon SageMaker to build the model. Which solution will meet these requirements with the LEAST development effort?

Options

  • AUse SageMaker Model Debugger to automatically debug the predictions, generate the
  • BUse AWS Lambda to provide feature importance and partial dependence plots. Use the plots to
  • CUse SageMaker Clarify to generate the explanation report. Attach the report to the predicted
  • DUse custom Amazon CloudWatch metrics to generate the explanation report. Attach the report to

How the community answered

(31 responses)
  • A
    6% (2)
  • B
    6% (2)
  • C
    84% (26)
  • D
    3% (1)

Why each option

To automate loan approvals in SageMaker and generate an explanation report for each prediction with the least development effort, SageMaker Clarify should be used.

AUse SageMaker Model Debugger to automatically debug the predictions, generate the

SageMaker Model Debugger focuses on identifying and debugging issues during model training, such as gradient problems or overfitting, rather than generating post-prediction explanation reports.

BUse AWS Lambda to provide feature importance and partial dependence plots. Use the plots to

While AWS Lambda can execute custom code, building a system from scratch to generate feature importance and partial dependence plots for individual predictions would require significant development effort compared to using SageMaker Clarify.

CUse SageMaker Clarify to generate the explanation report. Attach the report to the predictedCorrect

Amazon SageMaker Clarify is specifically designed to provide model explainability by generating various types of explanations, including SHAP values, for individual predictions, directly addressing the requirement for a per-prediction explanation report with minimal development effort.

DUse custom Amazon CloudWatch metrics to generate the explanation report. Attach the report to

Amazon CloudWatch metrics are used for monitoring operational data and performance metrics, not for generating detailed, interpretive explanation reports for machine learning model predictions.

Concept tested: SageMaker Clarify for model explainability

Source: https://docs.aws.amazon.com/sagemaker/latest/dg/clarify-feature-attribute-impact-and-rank.html

Topics

#Machine Learning Explainability#Amazon SageMaker Clarify#Model Interpretability#MLOps

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full MLS-C01 Practice