MLS-C01 Practice Test 23 — 15 Questions

Question 1

A company is using Amazon SageMaker to deploy a real-time inference endpoint for a computer vision model. The endpoint receives bursts of traffic with up to 500 requests per second, but the load is unpredictable. Which scaling strategy is MOST cost-effective while maintaining low latency?

Accepted Answer

Configure automatic scaling with a target tracking policy and add a buffer to handle bursts. Option C is correct because SageMaker can add instances in response to increased load, and using a buffer helps absorb sudden spikes. Option A (provisioned concurrency) is for serverless but not SageMaker. Option B (manual scaling) is not cost-effective for unpredictable traffic. Option D (multi-model endpoints) is for serving multiple models, not for scaling.

Answer

Manually provision enough instances to handle peak load

Answer

Use provisioned concurrency on SageMaker Serverless Inference

Answer

Use a multi-model endpoint to reduce the number of instances

Question 2

A data scientist wants to use Amazon SageMaker to train a deep learning model on a large dataset stored in S3. The training job is expected to take several hours. Which storage option should be used to minimize data loading time and cost?

Accepted Answer

Use Pipe mode to stream data directly from S3 during training. Option C is correct because Pipe mode streams data directly from S3 without downloading, minimizing time and cost. Option A (File mode) downloads entire dataset, increasing time and cost. Option B (Amazon EFS) is unnecessary and adds complexity. Option D (Amazon EBS) is not directly integrated with SageMaker.

Answer

Attach an Amazon EBS volume with the dataset pre-loaded

Answer

Use File mode to copy data to the training instance's local storage

Answer

Mount an Amazon EFS file system to the training instance

Question 3

An ML team is deploying a model for real-time inference. They require A/B testing to compare a new model against the existing one. Which THREE steps should they take to set up this test?

Accepted Answer

Set up a second production variant for the existing model. Options A, B, and D are correct. A: Create a production variant with the new model. B: Set up a production variant for the existing model. D: Configure the endpoint to route traffic between variants. Option C (CloudWatch) is monitoring, not part of setup. Option E (Batch Transform) is for batch, not real-time.

Answer

Set up a SageMaker Batch Transform job for each model

Answer

Configure CloudWatch alarms to trigger variant switching

Question 4

A company uses Amazon SageMaker to train a text classification model. The training data is stored in S3 and contains sensitive personally identifiable information (PII). The company must ensure that the data is encrypted at rest in S3 and that the encryption key is managed by the company's own hardware security module (HSM). Which configuration should be used?

Accepted Answer

Use S3 server-side encryption with customer-provided keys (SSE-C) and store the keys in the HSM. Option A is correct because SSE-C allows customers to provide their own encryption keys, which can be stored in an HSM. Option B (SSE-S3) uses AWS-managed keys. Option C (SSE-KMS with a customer managed key) uses KMS, not HSM. Option D (client-side encryption) requires managing encryption in the application.

Answer

Use S3 server-side encryption with S3-managed keys (SSE-S3)

Answer

Use client-side encryption with the encryption key stored in the HSM

Answer

Use S3 server-side encryption with AWS KMS managed keys (SSE-KMS) with a customer managed key

Question 5

A data scientist is using Amazon SageMaker to train an XGBoost model on a dataset with missing values. The dataset has both numeric and categorical features. Which preprocessing step is MOST appropriate before training?

Accepted Answer

One-hot encode categorical features and let XGBoost handle missing values natively. Option D is correct because XGBoost can handle missing values natively, so imputation may not be necessary, and one-hot encoding is needed for categorical features. Option A (mean imputation) may be okay but not necessary. Option B (remove rows) loses data. Option C (label encoding) may create ordinal relationships.

Answer

Impute missing numeric values with the mean and categorical values with the mode, then train without encoding

Answer

Remove all rows with missing values and train on the remaining data

Answer

Label encode categorical features and use the built-in missing value handling of XGBoost

Question 6

Which TWO services can be used to perform hyperparameter tuning in Amazon SageMaker? (Choose two.)

Accepted Answer

Amazon SageMaker Automatic Model Tuning. Options A and B are correct. SageMaker Automatic Model Tuning is the native tuning service. SageMaker Experiments can track tuning jobs. Option C (SageMaker Ground Truth) is for labeling. Option D (AWS Glue) is for ETL. Option E (Amazon EMR) is for big data processing.

Answer

AWS Glue

Answer

Amazon SageMaker Ground Truth

Answer

Amazon EMR

Question 7

During training of a deep learning model on a GPU instance in SageMaker, the training job fails with an insufficient memory error. Which step should be taken first to resolve this issue?

Accepted Answer

Reduce the batch size. Option B is correct because reducing the batch size directly decreases GPU memory usage. Option A is wrong because it reduces training time but not memory per step. Option C is wrong because it addresses vanishing gradients, not memory. Option D is wrong because it reduces overfitting, not memory.

Answer

Add dropout layers

Answer

Use a smaller learning rate

Answer

Use gradient clipping

Question 8

Refer to the exhibit. A data scientist runs the AWS CLI command to create a SageMaker training job. The training job fails because the input data is not accessible. Which step should the data scientist take to fix the issue?

Accepted Answer

Attach an IAM policy to SageMakerRole that grants s3:GetObject on the bucket. Option B is correct because the IAM role must have s3:GetObject permission for the S3 bucket. Option A is wrong because the bucket policy is separate. Option C is wrong because VolumeSizeInGB is for local storage, not S3. Option D is wrong because VPC configuration is not the issue.

Answer

Add a VpcConfig to the training job

Answer

Modify the bucket policy to allow s3:GetObject for any principal

Answer

Increase VolumeSizeInGB to 50

Question 9

A data scientist needs to create a SageMaker notebook instance with access to a private S3 bucket. The bucket uses SSE-KMS encryption. Which additional configuration is required?

Accepted Answer

Attach a policy to the notebook's IAM role that allows kms:Decrypt. Option D is correct because the notebook instance needs permission to use the KMS key. Option A is wrong because VPC is optional. Option B is wrong because lifecycle configuration does not handle encryption. Option C is wrong because bucket policy is separate.

Answer

Add a lifecycle configuration script

Answer

Modify the bucket policy to allow s3:GetObject

Answer

Place the notebook instance in a VPC

Question 10

A company uses SageMaker to train a model, but the training job fails due to insufficient memory. What is the most cost-effective way to resolve this?

Accepted Answer

Use a larger instance type with more memory. Option A is correct because increasing instance memory addresses the issue directly. Option B is wrong because reducing batch size may not solve memory issues if the model itself is large. Option C is wrong because Spot Instances have no memory advantage. Option D is wrong because distributed training adds complexity and cost.

Answer

Use Spot Instances to reduce cost

Answer

Reduce the batch size in the training script

Answer

Switch to distributed training across multiple instances

Question 11

A team notices that a SageMaker training job using TensorFlow is running slower than expected. The training data is in S3 in TFRecord format. Which action is most likely to improve training throughput?

Accepted Answer

Use Pipe mode for data ingestion. Option D is correct because SageMaker Pipe mode streams data directly from S3, eliminating download latency. Option A is wrong because using 'File' mode is default but slower. Option B is wrong because increasing batch size may cause memory issues. Option C is wrong because increasing instances adds complexity but not per-instance throughput.

Answer

Use distributed training with more instances

Answer

Increase the batch size in the training script

Answer

Switch from Pipe mode to File mode

Question 12

Which TWO services can be used to orchestrate a machine learning pipeline?

Accepted Answer

Amazon SageMaker Pipelines. Options A and D are correct. Option B is wrong because it's for labeling. Option C is wrong because it's for data transformation. Option E is wrong because it's for data warehousing.

Answer

Amazon SageMaker Ground Truth

Answer

Amazon Redshift

Answer

AWS Glue

Question 13

A data scientist is training a deep learning model on a large dataset using SageMaker. The training job is taking too long. Upon reviewing the CloudWatch logs, the scientist notices that the GPU utilization is below 10% most of the time. Which change is MOST likely to improve GPU utilization and reduce training time?

Accepted Answer

Increase the batch size in the training script.. Low GPU utilization often indicates a data loading bottleneck. Increasing the batch size can improve GPU utilization by feeding more data at once, but it may also cause memory issues. Using a larger instance type with more GPU memory could help if the model is large. However, the most common fix is to use SageMaker Pipe Mode or Fast File Mode to stream data efficiently, reducing I/O wait. Among the options, increasing batch size is a direct way to increase GPU utilization.

Answer

Use a different optimizer that requires less computation.

Answer

Switch to a smaller instance type to reduce data transfer overhead.

Answer

Reduce the size of the training dataset.

Question 14

A company is deploying a machine learning model to an Amazon SageMaker endpoint. The model receives requests with sensitive data that must be encrypted in transit and at rest. Additionally, the company needs to control access to the endpoint using AWS IAM. Which THREE steps should the company take to meet these requirements? (Choose THREE.)

Accepted Answer

Enable HTTPS for the endpoint. Options A, B, and D are correct. Enabling encryption in transit using HTTPS, enabling encryption at rest for the endpoint's attached storage, and attaching an IAM policy to the endpoint to allow only authorized users are necessary. Option C is wrong because VPC settings do not encrypt data at rest. Option E is wrong because the model data in S3 should be encrypted with SSE-KMS, not SSE-S3, to meet stricter security requirements.

Answer

Configure the endpoint to use a VPC

Answer

Store the model artifacts in Amazon S3 with SSE-S3 encryption

Question 15

A company is using Amazon SageMaker to host a model that performs real-time inference. The model receives around 100 requests per second with occasional spikes up to 500 requests per second. The current endpoint uses 2 ml.m5.large instances. During spikes, latency increases significantly, and some requests time out. What is the MOST cost-effective solution to handle the spikes without losing requests?

Accepted Answer

Configure SageMaker managed scaling with a target tracking policy and add a buffer based on the average spike duration. Option C is correct because adding a buffer to the autoscaling policy allows the endpoint to scale proactively before the spike fully hits, while managed scaling adjusts instances based on demand. Option A (increase instance size) is less cost-effective than scaling out. Option B (SQS) adds latency. Option D (Lambda) may not be suitable for real-time inference.

Answer

Replace the instances with a single larger instance type, such as ml.m5.4xlarge

Answer

Use an Amazon SQS queue to buffer incoming requests and process them asynchronously

Answer

Use AWS Lambda with a provisioned concurrency to handle the spikes