A bank wants to launch a low-rate credit promotion. The bank is located in a town that recently experienced economic hardship. Only some of the bank's customers were affected by the crisis, so the bank's credit team must identify which customers to target with the promotion. However, the credit team wants to make sure that loyal customers' full credit history is considered when the decision is made.
The bank's data science team developed a model that classifies account transactions and understands credit eligibility. The data science team used the XGBoost algorithm to train the model. The team used 7 years of bank transaction historical data for training and hyperparameter tuning over the course of several days.
The accuracy of the model is sufficient, but the credit team is struggling to explain accurately why the model denies credit to some customers. The credit team has almost no skill in data science.
What should the data science team do to address this issue in the MOST operationally efficient manner?

1. A. Use Amazon SageMaker Studio to rebuild the mode
2. B. Create a notebook that uses the XGBoost training container to perform model trainin
3. C. Deploy the model at an endpoin
4. D. Enable Amazon SageMaker Model Monitor to store inference
5. E. Use the inferences to create Shapley values that help explain model behavio
6. F. Create a chart that shows features and SHapley Additive explanation (SHAP) values to explain to the credit team how the features affect the model outcomes.
7. G. Use Amazon SageMaker Studio to rebuild the mode
8. H. Create a notebook that uses the XGBoost training container to perform model trainin
9. I. Activate Amazon SageMaker Debugger, and configure it to calculate and collect Shapley value
10. J. Create a chart that shows features and SHapley Additive explanation (SHAP) values to explain to the credit team how the features affect the model outcomes.
11. K. Create an Amazon SageMaker notebook instanc
12. L. Use the notebook instance and the XGBoost library to locally retrain the mode
13. M. Use the plot_importance() method in the Python XGBoost interface to create a feature importance char
14. N. Use that chart to explain to the credit team how the features affect the model outcomes.
15. O. Use Amazon SageMaker Studio to rebuild the mode
16. P. Create a notebook that uses the XGBoost training container to perform model trainin
17. Q. Deploy the model at an endpoin
18. R. Use Amazon SageMakerProcessing to post-analyze the model and create a feature importance explainability chart automatically for the credit team.

Correct Answer: C

A health care company is planning to use neural networks to classify their X-ray images into normal and abnormal classes. The labeled data is divided into a training set of 1,000 images and a test set of 200 images. The initial training of a neural network model with 50 hidden layers yielded 99% accuracy on the training set, but only 55% accuracy on the test set.
What changes should the Specialist consider to solve this issue? (Choose three.)

1. A. Choose a higher number of layers
2. B. Choose a lower number of layers
3. C. Choose a smaller learning rate
4. D. Enable dropout
5. E. Include all the images from the test set in the training set
6. F. Enable early stopping

Correct Answer: ADE

A Machine Learning Specialist receives customer data for an online shopping website. The data includes demographics, past visits, and locality information. The Specialist must develop a machine learning approach to identify the customer shopping patterns, preferences and trends to enhance the website for better service and smart recommendations.
Which solution should the Specialist recommend?

1. A. Latent Dirichlet Allocation (LDA) for the given collection of discrete data to identify patterns in thecustomer database.
2. B. A neural network with a minimum of three layers and random initial weights to identify patterns in the customer database
3. C. Collaborative filtering based on user interactions and correlations to identify patterns in the customer database
4. D. Random Cut Forest (RCF) over random subsamples to identify patterns in the customer database

Correct Answer: C

A Marketing Manager at a pet insurance company plans to launch a targeted marketing campaign on social media to acquire new customers Currently, the company has the following data in Amazon Aurora
• Profiles for all past and existing customers
• Profiles for all past and existing insured pets
• Policy-level information
• Premiums received
• Claims paid
What steps should be taken to implement a machine learning model to identify potential new customers on social media?

1. A. Use regression on customer profile data to understand key characteristics of consumer segments Find similar profiles on social media.
2. B. Use clustering on customer profile data to understand key characteristics of consumer segments Find similar profiles on social media.
3. C. Use a recommendation engine on customer profile data to understand key characteristics of consumer segment
4. D. Find similar profiles on social media
5. E. Use a decision tree classifier engine on customer profile data to understand key characteristics of consumer segment
6. F. Find similar profiles on social media

Correct Answer: C

A Machine Learning Specialist is assigned a TensorFlow project using Amazon SageMaker for training, and needs to continue working for an extended period with no Wi-Fi access.
Which approach should the Specialist use to continue working?

1. A. Install Python 3 and boto3 on their laptop and continue the code development using that environment.
2. B. Download the TensorFlow Docker container used in Amazon SageMaker from GitHub to their local environment, and use the Amazon SageMaker Python SDK to test the code.
3. C. Download TensorFlow from tensorflow.org to emulate the TensorFlow kernel in the SageMaker environment.
4. D. Download the SageMaker notebook to their local environment then install Jupyter Notebooks on their laptop and continue the development in a local notebook.

Correct Answer: D