MLS-C01 Mock Exam 81 — 25 Questions

Question 1

A data scientist is examining a dataset for a binary classification problem. The target variable has a 1:1000 imbalance. Which technique should be used to assess model performance during exploratory data analysis?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Area under the Precision-Recall curve. With a 1:1000 class imbalance, the positive class is extremely rare. The Area Under the Precision-Recall curve (AUPRC) focuses on the performance of the positive class and is sensitive to changes in precision and recall, making it a robust metric for imbalanced datasets. Unlike ROC AUC, which can be overly optimistic when negatives dominate, AUPRC provides a realistic assessment of model performance on the minority class.

Answer

F1 score

Answer

Area under the ROC curve

Answer

Cohen's kappa

Question 2

A machine learning team is using SageMaker to train a model. The training data is stored in an S3 bucket encrypted with AWS KMS. The training job fails with an 'AccessDenied' error. Which IAM permission is MOST likely missing from the SageMaker execution role?

Accepted Answer

kms:Decrypt. The training data is stored in an S3 bucket encrypted with AWS KMS. When SageMaker reads the encrypted data, the execution role must have permission to decrypt the KMS key. Without `kms:Decrypt`, the role cannot access the encrypted objects, resulting in an 'AccessDenied' error even if S3 read permissions are present.

Answer

s3:GetObject

Answer

s3:ListBucket

Answer

kms:GenerateDataKey

Question 3

A company is using SageMaker Autopilot to automatically build a binary classification model. After the AutoML job completes, the data scientist wants to understand which features are most important for the best candidate model. How can the scientist get feature importance?

Accepted Answer

Open the SageMaker Autopilot job details and view the 'Explainability' tab. SageMaker Autopilot automatically generates a 'Explainability' tab within the job details for the best candidate model. This tab uses SHAP (SHapley Additive exPlanations) values to provide feature importance, showing which features most influence the model's predictions. The data scientist can directly access this information without any additional configuration or re-running the model.

Answer

Re-run the best model using SageMaker built-in XGBoost with the 'feature_importance' hyperparameter

Answer

Check the CloudWatch Logs for the training job

Answer

Use SageMaker Ground Truth to label a new dataset

Question 4

A data scientist is training a deep learning model on a large dataset using Amazon SageMaker. The training job is taking too long and the scientist wants to reduce the training time by distributing the workload across multiple GPUs. Which SageMaker feature should be used to achieve this?

Accepted Answer

Use SageMaker's distributed training libraries. SageMaker's distributed training libraries provide built-in optimized implementations of data parallelism and model parallelism, enabling efficient distribution of deep learning workloads across multiple GPUs with minimal code changes. This directly addresses the need to reduce training time by leveraging multiple GPUs in a SageMaker training job.

Answer

Use Amazon EMR to distribute the training

Answer

Use SageMaker Automatic Model Tuning

Answer

Use SageMaker Hyperparameter Tuning

Question 5

A data scientist is using Amazon SageMaker Debugger to monitor training jobs. The training loss is decreasing but then suddenly spikes. What is the most likely cause and how should it be addressed?

Accepted Answer

Gradient explosion; apply gradient clipping.. A sudden spike in training loss after a period of decreasing loss is a classic symptom of gradient explosion, where gradients become excessively large during backpropagation, causing the model parameters to update erratically. Amazon SageMaker Debugger can monitor tensors and gradients in real time, and applying gradient clipping (e.g., via `max_grad_norm` in PyTorch or `clip_by_global_norm` in TensorFlow) directly addresses this by capping the gradient norm to prevent destabilizing updates.

Answer

Overfitting; apply regularization.

Answer

Learning rate too low; increase learning rate.

Answer

Vanishing gradients; use ReLU activation.

Question 6

Which TWO AWS services can be used to deploy a trained model for serverless inference? (Select TWO.)

Accepted Answer

AWS Lambda with a container image. AWS Lambda with a container image allows you to package a trained model and its dependencies into a Docker container and deploy it as a serverless function. Lambda automatically scales the inference endpoint in response to incoming requests, and you pay only for the compute time consumed during inference, with no idle infrastructure costs.

Answer

Amazon SageMaker batch transform

Answer

Amazon Elastic Container Service (ECS) with Fargate

Answer

Amazon EC2 instances

Question 7

An S3 event notification is configured to trigger a Lambda function when new objects are created. The Lambda function processes the event JSON shown. Which field should the function use to read the new object from S3?

Accepted Answer

s3.bucket.arn and s3.object.key. The Lambda function needs the bucket name and object key to retrieve the new object from S3. The `s3.bucket.arn` provides the bucket identifier, and `s3.object.key` provides the object path. Together, they allow the function to call `GetObject` on the S3 API.

Answer

s3.s3SchemaVersion

Answer

awsRegion

Answer

eventName

Question 8

A data scientist is using Amazon SageMaker to train a model. The training job is taking longer than expected. The data scientist notices that the GPU utilization is low. Which action would most likely improve GPU utilization?

Accepted Answer

Increase the batch size. Low GPU utilization during training often indicates that the GPU is waiting for data to process, a condition known as data bottleneck. Increasing the batch size allows the GPU to process more samples per forward/backward pass, keeping it busier and improving utilization. In SageMaker, this directly impacts the training loop by reducing the frequency of data loading and model update steps.

Answer

Change to a CPU-based instance

Answer

Decrease the batch size

Answer

Use a larger instance type

Answer

Enable data augmentation

Question 9

Which TWO approaches can reduce inference latency on a SageMaker real-time endpoint? (Choose 2.)

Accepted Answer

Attach an Elastic Inference accelerator. Elastic Inference (EI) accelerators attach a dedicated, low-cost FPGA-based inference accelerator to a SageMaker endpoint, offloading matrix operations from the CPU. This reduces inference latency by accelerating the compute-intensive forward pass of deep learning models without requiring a full GPU instance, making it ideal for real-time, low-latency predictions.

Answer

Increase the batch size

Answer

Enable SageMaker Model Monitor

Answer

Use a GPU instance type

Question 10

A company is using Amazon SageMaker to deploy a model for real-time inference. The model is a deep neural network that requires GPU for low latency. The endpoint currently uses a single ml.p3.2xlarge instance. Traffic is expected to increase by 5x. Which TWO actions should the company take to handle the increased traffic?

Accepted Answer

Use a larger instance type with more GPUs. The correct actions are A and C. Using a larger instance type with more GPUs (e.g., ml.p3.8xlarge) increases the compute capacity per instance, allowing the model to handle more requests without increasing latency, as GPUs are essential for low-latency inference on deep neural networks. Enabling auto-scaling on the endpoint dynamically adds or removes instances based on traffic, ensuring the endpoint can scale out to handle the 5x increase without manual intervention. Option B is incorrect because switching to CPU would significantly increase latency, as deep neural networks benefit from GPU acceleration. Option D is incorrect because multi-model endpoints are designed to host multiple models on a single instance, not to increase throughput for a single model. Option E is incorrect because decreasing batch size would reduce throughput per request, worsening performance under increased traffic.

Answer

Switch to a CPU-based instance

Answer

Use a multi-model endpoint

Answer

Decrease the batch size

Question 11

A machine learning team is using SageMaker to train a model. They want to ensure that the training data is encrypted at rest in the S3 bucket and that the data is also encrypted during transit. Which configuration should they use?

Accepted Answer

Use SSE-S3 encryption on the S3 bucket and enforce HTTPS. SSE-S3 provides server-side encryption at rest for objects in S3, and enforcing HTTPS ensures data is encrypted in transit using TLS. This combination meets the requirements for both encryption at rest and in transit without additional client-side complexity.

Answer

Use client-side encryption and transfer data via HTTP

Answer

Use SSE-KMS encryption on the S3 bucket and disable HTTP

Answer

Use SSE-C encryption on the S3 bucket and HTTPS

Answer

Use no encryption on S3 but use HTTPS

Question 12

During EDA, a data scientist finds that two features have a Pearson correlation coefficient of 0.95. What is the primary concern when using these features together in a linear regression model?

Accepted Answer

Multicollinearity will make coefficient estimates unstable. A Pearson correlation coefficient of 0.95 indicates strong multicollinearity between the two features. Multicollinearity inflates the variance of coefficient estimates, making them unstable and difficult to interpret. Option A is wrong because redundant information leads to multicollinearity, not underfitting; underfitting occurs when the model is too simple. Option B is wrong because heteroscedasticity refers to non-constant variance of errors, not correlation between features. Option C is wrong because overfitting is more associated with model complexity and variance, not directly with redundant features; in fact, redundant features can cause numerical instability but not necessarily overfitting.

Answer

The model will underfit because of redundant information

Answer

Heteroscedasticity will be introduced

Answer

The model will overfit due to redundant features

Question 13

A company is migrating its on-premises Apache Hadoop cluster to AWS. The cluster processes large datasets using Spark jobs. The company wants to minimize operational overhead and use native AWS services. Which combination of services should the company use?

Accepted Answer

Amazon EMR with Spark and Amazon S3. Amazon EMR is a managed Hadoop framework that natively supports Spark jobs, and Amazon S3 provides scalable and durable object storage for the data. This combination minimizes operational overhead as EMR automatically handles cluster provisioning, scaling, and monitoring. Option B is incorrect because Amazon Redshift is a data warehouse, not a Hadoop cluster, and Spectrum is for querying data in S3, not for running Spark jobs. Option C is incorrect because Amazon Athena is a serverless query service for SQL-based analytics, not for executing Spark jobs, and AWS Glue is an ETL service, not a compute engine for Spark. Option D is incorrect because running Apache Spark on EC2 instances requires manual setup, maintenance, and scaling of the cluster, increasing operational overhead compared to using a managed service like EMR.

Answer

Amazon Redshift with Spectrum and Amazon S3

Answer

Amazon Athena and AWS Glue

Answer

Amazon EC2 instances with Apache Spark installed and Amazon S3

Question 14

An IAM policy attached to a SageMaker notebook role is shown in the exhibit. A data scientist is trying to run a training job from the notebook, but the job fails with an access denied error. The training job needs to read data from 'my-bucket' and write output to 'my-bucket'. What is the most likely cause of the failure?

Accepted Answer

The training job execution role does not have the same permissions. The IAM policy shown is attached to the SageMaker notebook role, which is used by the data scientist to interact with the notebook. However, when a training job is launched, it runs under a separate execution role (the SageMaker execution role for training jobs), not the notebook role. The training job fails because that execution role lacks the necessary S3 permissions (e.g., s3:GetObject, s3:PutObject) to read from and write to 'my-bucket'. The notebook role's permissions are irrelevant to the training job's runtime actions.

Answer

The policy does not allow s3:ListBucket

Answer

The policy does not allow sagemaker:CreateTrainingJob

Answer

The S3 bucket is not specified in the Resource

Answer

The policy does not allow s3:GetObject

Question 15

A data scientist is using Amazon SageMaker to train a large neural network on a GPU instance. The training is taking longer than expected. The scientist wants to reduce training time without changing the model architecture. Which TWO approaches should the scientist consider?

Accepted Answer

Use SageMaker's distributed training with multiple GPU instances.. SageMaker's distributed training can split the large neural network across multiple GPU instances, reducing wall-clock training time through data parallelism or model parallelism. Option D is correct because switching to a larger GPU instance type with more CUDA cores increases the computational throughput per step, directly accelerating training without altering the model architecture.

Answer

Use SageMaker Automatic Model Tuning to find optimal hyperparameters.

Answer

Use SageMaker Managed Spot Training to reduce cost.

Answer

Enable SageMaker Debugger to capture training metrics.

Question 16

A company uses Amazon SageMaker to train a model. The training job uses a custom Docker container. The job fails with the error 'CannotStartContainerError: API error (500).' Which of the following is the most likely cause?

Accepted Answer

The Docker image is built for a different CPU architecture.. The error 'CannotStartContainerError: API error (500)' occurs when the Docker daemon on the SageMaker training instance fails to start the container. The most common cause is a CPU architecture mismatch: if the Docker image is built for a different architecture (e.g., ARM64) than the SageMaker training instance (which uses x86_64), the container cannot execute. SageMaker training instances are x86_64-based, so an image built for ARM64 will trigger this error at container launch time.

Answer

The training script has a syntax error.

Answer

The S3 input data is missing.

Answer

The output path is not writable.

Question 17

Which TWO of the following are appropriate techniques for detecting outliers in a univariate continuous dataset? (Select TWO.)

Accepted Answer

Z-score method. Options A and B are correct. Z-score method flags points beyond a threshold (e.g., 3 standard deviations) from the mean. IQR-based outlier detection identifies points beyond 1.5*IQR from the quartiles. Option C is wrong because box plots visualize outliers but are not a detection technique per se; they rely on IQR. Option D is wrong because Pearson correlation is bivariate and not used for univariate outlier detection. Option E is wrong because K-means clustering is typically used for multivariate data and not a standard univariate outlier detection method.

Answer

Box plot visualization

Answer

Pearson correlation coefficient

Answer

K-means clustering

Question 18

A machine learning engineer is deploying a PyTorch model on SageMaker for real-time inference. The model requires GPU for low latency. Which instance type and configuration should the engineer choose?

Accepted Answer

Deploy to an ml.p3.2xlarge instance with a SageMaker endpoint.. SageMaker real-time endpoints support GPU instances like ml.p3.2xlarge. Option A (ml.c5.4xlarge with batch transform) is a CPU instance and batch transform is for offline inference, not real-time. Option B (ml.m5.large with endpoint) is a CPU instance and not suitable for GPU-accelerated inference. Option D (ml.p3.2xlarge with batch transform) uses a GPU instance but batch transform is not real-time; a SageMaker endpoint is required for real-time inference.

Answer

Deploy to an ml.c5.4xlarge instance with SageMaker batch transform.

Answer

Deploy to an ml.m5.large instance with a SageMaker model endpoint.

Answer

Deploy to an ml.p3.2xlarge instance with SageMaker batch transform.

Question 19

A machine learning team is using Amazon SageMaker to train a model using a custom Docker container. The training job fails with an error: 'Unable to write to /opt/ml/model'. The container does not have root access. What is the most likely cause?

Accepted Answer

The container process does not have write permission to /opt/ml/model. SageMaker expects training containers to write the model artifact to /opt/ml/model. The container process must have write permissions to that directory. Root access is not required; the container runs with the 'sagemaker' user. The directory may not exist or permissions are wrong. The error indicates a write issue, likely permissions.

Answer

The /opt/ml/model directory does not exist in the container

Answer

The container is using an unsupported operating system

Answer

The container does not have internet access

Question 20

A company uses Amazon Redshift for its data warehouse. The data engineering team notices that queries are slow and wants to improve performance without changing the schema. Which action is most likely to improve query performance?

Accepted Answer

Increase the number of nodes in the cluster.. Increasing the number of nodes in an Amazon Redshift cluster distributes data and query processing across more compute resources, which directly improves parallel execution and reduces query execution time. This is the most effective way to boost performance without altering the schema, as it scales the cluster's CPU, memory, and I/O capacity.

Answer

Decrease the number of nodes to reduce network overhead.

Answer

Disable compression on all tables to reduce CPU overhead.

Answer

Change the distribution style from AUTO to EVEN.