nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #238

You work at a bank. You need to develop a credit risk model to support loan application decisions. You decide to implement the model by using a neural network in TensorFlow. Due to regulatory…

The correct answer is A. Use Vertex Explainable AI with the sampled Shapley method, and enable Vertex AI Model. To explain predictions of a TensorFlow neural network for a credit risk model and monitor its performance on Vertex AI, use Vertex Explainable AI with sampled Shapley and enable Vertex AI Model Monitoring.

Submitted by stefanr· Apr 18, 2026ML pipeline operationalization

Question

You work at a bank. You need to develop a credit risk model to support loan application decisions. You decide to implement the model by using a neural network in TensorFlow. Due to regulatory requirements, you need to be able to explain the model's predictions based on its features. When the model is deployed, you also want to monitor the model's performance over time. You decided to use Vertex AI for both model development and deployment. What should you do?

Options

  • AUse Vertex Explainable AI with the sampled Shapley method, and enable Vertex AI Model
  • BUse Vertex Explainable AI with the sampled Shapley method, and enable Vertex AI Model
  • CUse Vertex Explainable AI with the XRAI method, and enable Vertex AI Model Monitoring to
  • DUse Vertex Explainable AI with the XRAI method, and enable Vertex AI Model Monitoring to

How the community answered

(53 responses)
  • A
    74% (39)
  • B
    4% (2)
  • C
    8% (4)
  • D
    15% (8)

Why each option

To explain predictions of a TensorFlow neural network for a credit risk model and monitor its performance on Vertex AI, use Vertex Explainable AI with sampled Shapley and enable Vertex AI Model Monitoring.

AUse Vertex Explainable AI with the sampled Shapley method, and enable Vertex AI ModelCorrect

For complex neural networks, the `sampled Shapley` method in Vertex Explainable AI is a robust technique for generating feature-based explanations by providing feature attributions. Enabling Vertex AI Model Monitoring is crucial for continuously tracking the model's performance, such as prediction drift and data skew, after deployment.

BUse Vertex Explainable AI with the sampled Shapley method, and enable Vertex AI Model

This option is identical to A; assuming A is the unique correct answer provided, this would be a duplicate choice.

CUse Vertex Explainable AI with the XRAI method, and enable Vertex AI Model Monitoring to

The `XRAI` method in Vertex Explainable AI is primarily designed for image data to highlight salient regions and is generally not the most appropriate explanation method for tabular data used in a credit risk model.

DUse Vertex Explainable AI with the XRAI method, and enable Vertex AI Model Monitoring to

Similar to C, the `XRAI` method is not typically recommended for explaining predictions based on tabular data features.

Concept tested: Vertex Explainable AI and Model Monitoring

Source: https://cloud.google.com/vertex-ai/docs/explainable-ai/overview

Topics

#Vertex AI#Explainable AI#Model Monitoring#Shapley values

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice