ExamTopics Logo
Mail Us[email protected]
Menu
Amazon Discussions
exam questions

Exam AWS Certified Machine Learning - Specialty All Questions

View all questions & answers for the AWS Certified Machine Learning - Specialty exam
Go to Exam

Exam AWS Certified Machine Learning - Specialty topic 1 question 222 discussion

Exam question from Amazon's AWS Certified Machine Learning - Specialty
Question #: 222
Topic #: 1
[All AWS Certified Machine Learning - Specialty Questions]

A data scientist at a financial services company used Amazon SageMaker to train and deploy a model that predicts loan defaults. The model analyzes new loan applications and predicts the risk of loan default. To train the model, the data scientist manually extracted loan data from a database. The data scientist performed the model training and deployment steps in a Jupyter notebook that is hosted on SageMaker Studio notebooks. The model's prediction accuracy is decreasing over time.

Which combination of steps is the MOST operationally efficient way for the data scientist to maintain the model's accuracy? (Choose two.)

  • A. Use SageMaker Pipelines to create an automated workflow that extracts fresh data, trains the model, and deploys a new version of the model.
  • B. Configure SageMaker Model Monitor with an accuracy threshold to check for model drift. Initiate an Amazon CloudWatch alarm when the threshold is exceeded. Connect the workflow in SageMaker Pipelines with the CloudWatch alarm to automatically initiate retraining.
  • C. Store the model predictions in Amazon S3. Create a daily SageMaker Processing job that reads the predictions from Amazon S3, checks for changes in model prediction accuracy, and sends an email notification if a significant change is detected.
  • D. Rerun the steps in the Jupyter notebook that is hosted on SageMaker Studio notebooks to retrain the model and redeploy a new version of the model.
  • E. Export the training and deployment code from the SageMaker Studio notebooks into a Python script. Package the script into an Amazon Elastic Container Service (Amazon ECS) task that an AWS Lambda function can initiate.
Show Suggested Answer Hide Answer
Suggested Answer: AB 🗳️
by drcok87 at Feb. 11, 2023, 1:32 a.m.
Disclaimers:
  • - ExamTopics website is not related to, affiliated with, endorsed or authorized by Amazon.
  • - Trademarks, certification & product names are used for reference only and belong to Amazon.

Comments

Chosen Answer:
This is a voting comment (?). It is better to Upvote an existing comment if you don't have anything to add.
Switch to a voting comment New
Submit Cancel
loict
7 months, 2 weeks ago
Selected Answer: AB
A. YES - fully automated pipeline B. YES - triggers the pipeline A as needed C. NO - email notification does not allow automation D. NO - manual steps required, not operationaly efficient E. NO - we need another step to trigger the Lambda
upvoted 1 times
...
Mickey321
8 months ago
Selected Answer: AB
Option A uses SageMaker Pipelines to create an automated workflow that extracts fresh data, trains the model, and deploys a new version of the model. This option is operationally efficient because it eliminates the need for manual intervention and ensures that your model is always up to date with the latest data. You can also use SageMaker Pipelines to orchestrate your workflow using a graphical interface or a Python SDK1. Option B configures SageMaker Model Monitor with an accuracy threshold to check for model drift. Model drift occurs when the statistical properties of the target variable change over time, which can affect the performance of your model2.
upvoted 1 times
...
Mllb
1 year ago
Selected Answer: AB
https://aws.amazon.com/blogs/machine-learning/automate-model-retraining-with-amazon-sagemaker-pipelines-when-drift-is-detected/
upvoted 2 times
...
Valcilio
1 year, 1 month ago
Selected Answer: AB
Retrain the model when the accuracy is decreasing is the most recommended way to take of your models.
upvoted 2 times
...
oso0348
1 year, 1 month ago
Selected Answer: AB
The MOST operationally efficient way for the data scientist to maintain the model's accuracy would be to choose options A and B: A. Use SageMaker Pipelines to create an automated workflow that extracts fresh data, trains the model, and deploys a new version of the model. Using SageMaker Pipelines allows the data scientist to automate the entire workflow from data extraction to model deployment. This ensures that the model is trained and deployed on the latest data automatically without the need for manual intervention. The data scientist can set up the pipeline to run on a schedule or trigger it based on certain events. B. Configure SageMaker Model Monitor with an accuracy threshold to check for model drift. Initiate an Amazon CloudWatch alarm when the threshold is exceeded. Connect the workflow in SageMaker Pipelines with the CloudWatch alarm to automatically initiate retraining.
upvoted 2 times
...
AjoseO
1 year, 2 months ago
Selected Answer: AB
Using SageMaker Pipelines to create an automated workflow that extracts fresh data, trains the model, and deploys a new version of the model is an efficient way to automate the process of model retraining and deployment. Configuring SageMaker Model Monitor with an accuracy threshold to check for model drift and initiating an Amazon CloudWatch alarm when the threshold is exceeded is an efficient way to monitor the accuracy of the deployed model and initiate retraining when necessary. This approach helps to maintain the accuracy of the model over time.
upvoted 2 times
...
Jerry84
1 year, 2 months ago
Selected Answer: AB
https://aws.amazon.com/blogs/machine-learning/automate-model-retraining-with-amazon-sagemaker-pipelines-when-drift-is-detected/
upvoted 2 times
...
drcok87
1 year, 2 months ago
B first and then A
upvoted 1 times
...
Community vote distribution
A (35%)
C (25%)
B (20%)
Other
Most Voted
A voting comment increases the vote count for the chosen answer by one.

Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.

SaveCancel
exam
Someone Bought Contributor Access for:
SY0-701
London, 1 minute ago