MLS-C01 Machine Learning Implementation and Operations Practice Test 8 — 15 Questions

Question 1

An ML team wants to perform batch inference on a large dataset stored in Amazon S3 using a pre-trained model. The team needs to process the data in parallel across multiple instances to reduce processing time. Which approach should they use?

Accepted Answer

Use SageMaker Batch Transform with multiple instances.. SageMaker Batch Transform is designed for batch inference, automatically distributing the dataset across instances for parallel processing. SageMaker Processing (B) is for data preprocessing, not inference. SageMaker Training (C) is for training models. SageMaker Ground Truth (D) is for labeling.

Answer

Use SageMaker Processing to run a custom inference script.

Answer

Use SageMaker Training to run inference as a training job.

Answer

Use SageMaker Ground Truth to process the data.

Question 2

Refer to the exhibit. An ML engineer attaches this IAM policy to a user. The user wants to invoke the SageMaker endpoint my-endpoint from an EC2 instance with public IP 52.1.1.1. What will happen?

Accepted Answer

The invocation is allowed because the source IP is not in the denied ranges.. The policy has an Allow for InvokeEndpoint on the specific endpoint, but also a Deny with a condition that denies InvokeEndpoint if the source IP is within private IP ranges (10.0.0.0/8, 172.16.0.0/12, 192.168.0.0/16). The user's IP is 52.1.1.1, which is a public IP, not in the deny condition. Therefore, the Allow takes effect, and the invocation is permitted. Note: Deny always overrides Allow, but the condition does not match, so Deny is not applied.

Answer

The invocation fails because the user does not have permission to create an endpoint.

Answer

The invocation is denied because the Deny statement applies to all resources.

Answer

The invocation is denied because the user is not in a VPC.

Question 3

Refer to the exhibit. A data scientist is deploying a PyTorch model on a SageMaker endpoint. When the endpoint is invoked, the above error appears in CloudWatch logs. What is the MOST likely cause?

Accepted Answer

The model artifact was not properly saved or is missing from the S3 location.. The error occurs in the model_fn function, which loads the model. The error 'NoneType' object has no attribute 'shape' suggests that the model object is None, meaning the model was not loaded correctly. The most likely cause is that the model file (model.tar.gz) does not contain the expected model artifact, or the model file is missing. Incorrect input tensor shape (B) would cause errors during inference, not loading. Insufficient memory (C) would cause out-of-memory errors. Wrong endpoint instance type (D) would not cause a NoneType error.

Answer

The endpoint instance type does not support the required CUDA version.

Answer

The endpoint instance does not have enough memory to load the model.

Answer

The input tensor shape does not match the model's expected input shape.

Question 4

Refer to the exhibit. An ML engineer creates a CloudFormation stack with this template. The stack creation succeeds, but when the engineer tries to invoke the endpoint, it returns a ModelError. The CloudWatch logs show that the container exited with error. What is the MOST likely cause?

Accepted Answer

The execution role does not have permissions to pull the Docker image from ECR.. The template does not specify a VPC configuration for the endpoint. By default, SageMaker endpoints are not in a VPC and cannot access resources in a VPC unless configured. However, the model artifact is in S3 (s3://my-bucket/model.tar.gz), which is accessible without VPC. The most common cause of ModelError is that the container image is not compatible with the instance type or the model file is missing. But given the template, a likely issue is that the execution role (SageMakerRole) does not have permissions to access the ECR image or S3 bucket. The error is not about VPC (A) or instance count (B) or endpoint config (D).

Answer

The initial instance count is set to 2, which is insufficient for the model size.

Answer

The endpoint is not deployed in a VPC and cannot access the S3 bucket.

Answer

The EndpointConfig references the model but the model is not yet created.

Question 5

A financial services company is deploying a machine learning model for credit risk assessment. The model must have an inference latency under 200ms and must be able to handle up to 1000 transactions per second (TPS). The company wants to minimize costs. The model is a gradient boosting model implemented in XGBoost. Which SageMaker deployment option should the team choose?

Accepted Answer

Deploy the model on a SageMaker real-time endpoint with multiple instances behind a load balancer.. SageMaker real-time endpoints are designed for low-latency, high-throughput inference. They can scale horizontally to handle TPS requirements. SageMaker Batch Transform (B) is for offline processing. SageMaker Serverless Inference (C) has cold starts and may not meet latency requirements under high load. SageMaker asynchronous inference (D) is for near-real-time but has higher latency.

Answer

Use SageMaker Batch Transform to process transactions in batches.

Answer

Use SageMaker asynchronous inference for queued requests.

Answer

Use SageMaker Serverless Inference for automatic scaling.

Question 6

An ML team uses Amazon SageMaker to train a deep learning model. The training job runs on a single ml.p3.2xlarge instance and is taking 10 hours. The team wants to reduce the training time to under 2 hours without changing the model architecture. Which approach is MOST effective?

Accepted Answer

Use SageMaker distributed training with multiple ml.p3.2xlarge instances.. Using SageMaker's distributed training with multiple GPU instances (A) can significantly reduce training time by parallelizing the workload. Changing to a larger instance (B) may help but not as much as multiple instances. Using SageMaker Debugger (C) does not speed up training. Using Spot Instances (D) saves cost but not time.

Answer

Use SageMaker Managed Spot Training to reduce cost.

Answer

Switch to a single ml.p3.16xlarge instance with more GPUs.

Answer

Enable SageMaker Debugger to identify bottlenecks.

Question 7

A company wants to use Amazon SageMaker to host a model that was trained using a custom algorithm. The model artifact is stored in Amazon S3. The company wants to ensure that the endpoint can automatically scale based on the number of incoming requests. Which configuration should the company use?

Accepted Answer

Create a SageMaker real-time endpoint and configure automatic scaling using a target tracking policy.. SageMaker real-time endpoints support automatic scaling using Application Auto Scaling, which can adjust the number of instances based on metrics like request count. Multi-model endpoints (A) are for serving multiple models. Batch Transform (B) is for offline inference. Serverless Inference (D) scales automatically but has limitations; the question asks for endpoint scaling, and real-time endpoints with auto-scaling is the standard approach.

Answer

Create a SageMaker multi-model endpoint with automatic scaling.

Answer

Use SageMaker Serverless Inference which scales automatically.

Answer

Use SageMaker Batch Transform with a scheduled job.

Question 8

A company uses Amazon SageMaker to train a model. The training job fails with an 'OutOfMemory' error. The training data is stored in S3 and the instance type is ml.m5.xlarge. What is the most efficient way to resolve this issue?

Accepted Answer

Use a larger instance type, such as ml.m5.2xlarge. Option C is correct: Increasing the instance type provides more memory. Option A (increasing instance count) does not increase memory per instance. Option B (reducing batch size) may help but is less efficient. Option D (enabling spot instances) does not address memory.

Answer

Enable managed spot training

Answer

Reduce the batch size in the training script

Answer

Increase the number of instances using distributed training

Question 9

A data scientist is deploying a real-time inference endpoint using SageMaker. The model is a large NLP model requiring GPU for low latency. The endpoint must be highly available across two Availability Zones. Which deployment configuration meets these requirements?

Accepted Answer

Deploy a multi-model endpoint on an ml.p3.2xlarge instance with auto-scaling and at least two instances in different AZs. Option B is correct: A multi-model endpoint on a GPU instance with auto-scaling across AZs ensures high availability. Option A uses CPU. Option C (single instance) lacks HA. Option D (batch transform) is not real-time.

Answer

Deploy a single model endpoint on an ml.c5.xlarge instance with auto-scaling

Answer

Use SageMaker batch transform on GPU instances

Answer

Deploy a single model endpoint on an ml.p3.2xlarge instance with one instance

Question 10

A team uses AWS Glue ETL jobs to preprocess data for SageMaker training. The job runs successfully but the output data is empty. What is the most likely cause?

Accepted Answer

The filter transformation condition is too restrictive, removing all rows. Option A is correct: If the filter condition excludes all records, output is empty. Option B (partition pruning) would not cause empty output if data exists. Option C (data type mismatch) causes errors, not empty output. Option D (insufficient memory) causes job failure, not empty output.

Answer

There is a data type mismatch between source and target

Answer

The source data is partitioned and only a subset of partitions is read

Answer

The Glue job runs out of memory and fails silently

Question 11

A company uses SageMaker to host a model for real-time predictions. The model is updated weekly. To minimize downtime during model updates, what should the company do?

Accepted Answer

Create a new endpoint configuration with the new model and update the endpoint to use the new configuration. Option D is correct: Creating a new endpoint configuration with the new model and updating the endpoint with a blue/green deployment minimizes downtime. Option A (delete and recreate) causes downtime. Option B (update endpoint directly) causes brief downtime. Option C (multiple endpoints with load balancer) works but is more complex than SageMaker's built-in blue/green.

Answer

Create a second endpoint with the new model and use an Application Load Balancer to route traffic

Answer

Update the existing endpoint configuration with the new model URL

Answer

Delete the existing endpoint and create a new one with the updated model

Question 12

A machine learning team is using SageMaker Processing jobs to run feature engineering on large datasets. The job takes a long time to complete. Which change would most likely reduce the processing time?

Accepted Answer

Increase the number of instances in the processing cluster. Option B is correct: Increasing the instance count allows distributed processing, reducing time. Option A (larger instance) helps but is less scalable. Option C (local mode) is for testing, not production. Option D (changing framework) may not improve performance.

Answer

Switch to local mode to avoid network overhead

Answer

Change the processing script from Python to PySpark

Answer

Use a larger instance type, e.g., from r5.xlarge to r5.24xlarge

Question 13

A company is using SageMaker to train a model. The training data includes personally identifiable information (PII). The company must ensure that the data is encrypted at rest and in transit. Which combination of actions meets these requirements?

Accepted Answer

Use S3 server-side encryption and enable SageMaker inter-container traffic encryption. Option C is correct: S3 SSE-S3 or SSE-KMS encrypts data at rest, and SageMaker uses HTTPS for in-transit encryption. Option A (only SSL) lacks at-rest encryption. Option B (only S3 SSE) lacks in-transit. Option D (VPC only) does not encrypt.

Answer

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

Answer

Enable SSL for data in transit and use VPC endpoints

Answer

Place all resources in a private VPC subnets with no internet access

Question 14

A data scientist wants to use AWS Step Functions to orchestrate a machine learning workflow including data preprocessing, training, and evaluation. Which SageMaker integration is best suited for this purpose?

Accepted Answer

Use the SageMaker SDK with Step Functions service integrations. Option B is correct: SageMaker SDK with Step Functions integration allows direct orchestration. Option A (SageMaker Pipelines) is a different orchestration tool. Option C (Lambda) adds complexity. Option D (Batch) is for non-interactive jobs.

Answer

Implement each step as an AWS Lambda function and call Step Functions

Answer

Use SageMaker Pipelines to define the workflow

Answer

Use AWS Batch to run the steps sequentially

Question 15

A company is using SageMaker to host a model that makes predictions on streaming data from Amazon Kinesis. The model must provide predictions with sub-second latency. Which approach should the company use?

Accepted Answer

Use a SageMaker real-time endpoint and invoke it from an AWS Lambda function that is triggered by Kinesis. Option C is correct: SageMaker real-time endpoint provides sub-second latency with Kinesis via Lambda. Option A (batch transform) is not real-time. Option B (async inference) has higher latency. Option D (Kinesis Analytics) does not use SageMaker.

Answer

Use SageMaker asynchronous inference with a Kinesis trigger

Answer

Use Amazon Kinesis Data Analytics with a built-in ML model

Answer

Use SageMaker batch transform to process batches of records from Kinesis