MLS-C01 Mock Exam 80 — 25 Questions

Question 1

A data scientist is exploring a dataset with 500 features and 10,000 samples. The data scientist computes the pairwise correlation matrix and finds that many features have correlations above 0.9. The data scientist wants to reduce the dataset to 50 features while preserving as much variance as possible. Which technique should be used?

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

Accepted Answer

Apply Principal Component Analysis (PCA) and keep the top 50 principal components.. Principal Component Analysis (PCA) is the correct technique because it performs an orthogonal linear transformation that projects the original 500 features into a new coordinate system where the axes (principal components) are ordered by the variance they capture. By keeping the top 50 principal components, the data scientist retains the maximum possible variance in the reduced 50-dimensional space, directly addressing the goal of preserving variance while handling high multicollinearity.

Answer

Remove all but one feature from each group of highly correlated features.

Answer

Use Linear Discriminant Analysis (LDA) to project to 50 dimensions.

Answer

Use t-Distributed Stochastic Neighbor Embedding (t-SNE) to reduce to 50 dimensions.

Question 2

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.. A is correct because SageMaker's distributed training framework can partition the training workload across multiple ml.p3.2xlarge instances, each with one NVIDIA V100 GPU, enabling data parallelism that scales near-linearly. With sufficient instances (e.g., 5 or more), the 10-hour job can be reduced to under 2 hours without altering the model architecture, as the framework handles gradient synchronization via AllReduce.

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 3

A company uses AWS Glue jobs with job bookmarks enabled to process incremental data. They notice that the job processes all data each time instead of only new data. What is the most likely reason?

Accepted Answer

The MaxConcurrentRuns is set to 3, which can cause bookmark conflicts.. Setting MaxConcurrentRuns to a value greater than 1 can cause job bookmark conflicts. When multiple concurrent runs of the same AWS Glue job attempt to update the bookmark state simultaneously, they can overwrite each other's progress, leading to inconsistent bookmark tracking. This results in the job reprocessing all data instead of only incremental data, as the bookmark fails to correctly record the last processed position.

Answer

The TempDir is not configured correctly.

Answer

The job bookmark option is set to 'job-bookmark-enable' but should be 'job-bookmark-disable'.

Answer

The source data does not have a column that can be used as a bookmark key.

Question 4

A company uses Amazon SageMaker to train a model using a custom Docker container. The training job fails with an error: "Unable to write to /opt/ml/output/data". The data scientist checks the container and finds that the /opt/ml directory is not writable. What is the MOST likely cause?

Accepted Answer

The container runs as a non-root user that lacks write permissions to /opt/ml.. The error 'Unable to write to /opt/ml/output/data' indicates a permission issue. By default, SageMaker training containers run as a non-root user (uid 1000) for security reasons. If the Docker image is built with /opt/ml owned by root and without world-writable permissions, the non-root user cannot write to that directory, causing the failure.

Answer

The Docker image is built from a base image that does not have the required libraries.

Answer

The SageMaker training job is configured with insufficient memory.

Answer

The training script is not copying the model to /opt/ml/model.

Question 5

A team is using SageMaker to train a model using the built-in XGBoost algorithm. The training job is taking longer than expected. The team suspects that the data is not being loaded efficiently. Which data format should they use to minimize training time?

Accepted Answer

Pipe mode with RecordIO-Protobuf. Pipe mode with RecordIO-Protobuf is correct because it streams data directly from Amazon S3 to the training container without writing to disk, reducing I/O overhead. RecordIO-Protobuf also stores data in a binary, columnar format that XGBoost can parse more efficiently than CSV, especially for large datasets, leading to faster training times.

Answer

Pipe mode with CSV

Answer

File mode with Parquet

Answer

File mode with CSV

Question 6

A data scientist is evaluating a classification model. The confusion matrix shows that the model has 50 true positives, 100 true negatives, 20 false positives, and 30 false negatives. Which TWO metrics can be calculated from this confusion matrix? (Choose two.)

Accepted Answer

Recall. Recall (also known as sensitivity) is calculated as TP / (TP + FN) = 50 / (50 + 30) = 0.625, measuring the proportion of actual positives correctly identified. Precision is calculated as TP / (TP + FP) = 50 / (50 + 20) = 0.714, measuring the proportion of positive predictions that are correct. Both metrics are directly derived from the four values in the confusion matrix.

Answer

R-squared

Answer

F1 score

Answer

Root mean squared error

Question 7

A data scientist needs to deploy a PyTorch model for real-time inference. Which AWS service is best suited for this task?

Accepted Answer

Amazon SageMaker real-time endpoint. Amazon SageMaker real-time endpoints are purpose-built for hosting ML models that require low-latency, synchronous inference. They automatically manage the underlying infrastructure, including scaling, load balancing, and health checks, and support custom PyTorch containers via the SageMaker inference toolkit. This makes them the optimal choice for deploying a PyTorch model for real-time inference.

Answer

Amazon SageMaker Batch Transform

Answer

Amazon ECS with Fargate

Answer

AWS Lambda with custom container

Question 8

A data scientist is using Amazon SageMaker to perform exploratory data analysis on a dataset with missing values and outliers. Which TWO actions should the scientist take to understand the data quality? (Choose TWO.)

Accepted Answer

Use histograms to visualize the distribution of each numerical feature. Histograms show the distribution of numerical features, helping to identify skewness and outliers. Option E is correct because summary statistics like df.describe() provide count, mean, min, max, and quartiles, which reveal missing values (via count) and outliers (via min/max). Option A is incorrect because a scatterplot matrix visualizes pairwise relationships but does not directly show missing values or outliers. Option C is incorrect because a confusion matrix is used for evaluating classification model performance, not for data exploration. Option D is incorrect because a correlation matrix shows relationships between features but does not highlight missing values or outliers.

Answer

Build a scatterplot matrix to visualize pairwise relationships

Answer

Plot a confusion matrix to assess class separation

Answer

Create a correlation matrix to identify redundant features

Question 9

A data engineer is building a data pipeline that uses AWS Lambda to process records from an SQS queue and write results to an S3 bucket. The Lambda function processes each record individually and writes a separate file to S3. The team notices high latency and wants to reduce the number of S3 PUT requests to improve performance and reduce cost. Which approach should the data engineer take?

Accepted Answer

Aggregate multiple records into a single file in a DynamoDB table, then periodically write the aggregated data to S3.. It reduces the number of S3 PUT requests by aggregating multiple records into a single file in DynamoDB and then periodically writing the aggregated data to S3. This approach directly addresses the high latency and cost issue caused by writing a separate S3 object per record, as S3 PUT requests are billed per operation and have overhead. By batching records before writing, the pipeline reduces the total number of PUT requests, improving throughput and lowering costs.

Answer

Use S3 multipart upload for each record to improve throughput.

Answer

Increase the Lambda function's memory allocation to improve processing speed.

Answer

Use S3 Batch Operations to process the records in batches.

Question 10

A company wants to deploy a machine learning model that requires GPU acceleration for inference. The model is small and can fit on a single GPU. Which SageMaker endpoint configuration is MOST cost-effective?

Accepted Answer

Use a ml.p3.2xlarge instance with 1 GPU and enable automatic scaling.. The most cost-effective because it uses a single-GPU ml.p3.2xlarge instance, which matches the requirement that the model fits on one GPU, and enables automatic scaling to handle variable traffic without over-provisioning. This avoids paying for unused GPU capacity while still providing the necessary GPU acceleration for inference.

Answer

Use a ml.p3.16xlarge instance with 8 GPUs.

Answer

Use a SageMaker Serverless Inference endpoint.

Answer

Use a Multi-Model Endpoint on a ml.g4dn.xlarge instance.

Question 11

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. The 'OutOfMemory' error indicates that the ml.m5.xlarge instance (4 vCPUs, 16 GiB memory) does not have enough RAM to hold the training data and model during processing. Upgrading to ml.m5.2xlarge (8 vCPUs, 32 GiB memory) directly increases available memory, resolving the issue without requiring code changes or architectural modifications. This is the most efficient solution because it requires no script alterations and leverages SageMaker's built-in instance scaling.

Answer

Enable managed spot training

Answer

Reduce the batch size in the training script

Answer

Increase the number of instances using distributed training

Question 12

A data scientist is training a deep learning model on Amazon SageMaker using a custom TensorFlow container. The training job fails with an OutOfMemory error. The instance type is ml.p3.2xlarge with 16 GB GPU memory and 61 GB system memory. The model uses mixed precision training. Which step should the data scientist take to resolve the issue without changing the instance type?

Accepted Answer

Reduce the batch size. Reducing the batch size directly decreases the memory footprint per training step, which is the most straightforward way to resolve an OutOfMemory error without changing the instance type. Since the model already uses mixed precision training (which reduces memory usage via FP16), the remaining memory pressure is likely from the batch size being too large for the 16 GB GPU memory on the ml.p3.2xlarge instance.

Answer

Use gradient accumulation to simulate a larger batch size

Answer

Use model parallelism across multiple GPUs

Answer

Enable automatic mixed precision (AMP)

Answer

Increase the instance type to ml.p3.8xlarge

Question 13

A data engineer needs to ingest streaming data from an on-premises Kafka cluster into Amazon S3 with minimal operational overhead. Which AWS service should be used to stream the data into S3 without managing servers?

Accepted Answer

Amazon Kinesis Data Firehose. Amazon Kinesis Data Firehose is the correct choice because it is a fully managed service that can directly ingest streaming data from an on-premises Kafka cluster (via a Kinesis Data Firehose HTTP endpoint or a custom producer) and deliver it to Amazon S3 without requiring any server management. It handles scaling, buffering, and compression automatically, minimizing operational overhead.

Answer

Amazon Kinesis Data Streams

Answer

AWS Glue

Answer

Amazon Managed Streaming for Apache Kafka (Amazon MSK)

Question 14

A company is building a binary classifier to detect fraudulent transactions. The dataset is highly imbalanced with only 0.1% positive cases. The data scientist uses logistic regression and obtains 99.9% accuracy on the test set. Which metric should the data scientist use to evaluate the model's performance?

Accepted Answer

Precision-recall curve. With only 0.1% positive cases, accuracy is misleading because a model that always predicts 'not fraudulent' achieves 99.9% accuracy. The precision-recall curve focuses on the positive class and is robust to extreme class imbalance, showing the trade-off between precision and recall across thresholds. This makes it the best choice for evaluating a binary classifier on highly imbalanced fraud detection data.

Answer

ROC AUC

Answer

Precision

Answer

F1 score

Question 15

A data engineer is building a data pipeline that ingests streaming data from IoT devices. The data must be processed in near real-time and stored in Amazon S3 for further analysis. Which AWS service should be used to capture and process the streaming data before storing it in S3?

Accepted Answer

Use Amazon Kinesis Data Streams to capture the data and Amazon Kinesis Data Firehose to deliver it to S3.. Amazon Kinesis Data Streams is designed for real-time data ingestion and can capture streaming data from IoT devices with low latency. Amazon Kinesis Data Firehose then reliably loads that streaming data into Amazon S3, handling buffering, compression, and partitioning automatically. This combination provides the near real-time processing and durable storage required for the pipeline.

Answer

Use Amazon S3 with S3 Event Notifications to trigger AWS Lambda for processing.

Answer

Use AWS Glue to perform ETL on the streaming data.

Answer

Use Amazon Simple Queue Service (SQS) to buffer the data and then process it with AWS Lambda.

Question 16

A company is deploying a machine learning model using Amazon SageMaker. The model needs to be updated frequently. Which THREE practices should the company implement for model versioning and deployment?

Accepted Answer

Use AWS CodePipeline to automate the training and deployment pipeline.. AWS CodePipeline is correct because it enables continuous integration and continuous delivery (CI/CD) for machine learning models, automating the build, train, test, and deploy stages. By integrating with SageMaker, CodePipeline can trigger retraining on new data, run evaluation steps, and automatically update the endpoint, ensuring frequent model updates are reliable and repeatable.

Answer

Manually update the endpoint configuration each time.

Answer

Store all training datasets in a single S3 bucket without versioning.

Question 17

An ML engineer needs to store and version training datasets and model artifacts. Which AWS service should they use?

Accepted Answer

Amazon Simple Storage Service (S3). Amazon S3 is the correct choice because it provides scalable, durable, and cost-effective object storage with built-in versioning capabilities, making it ideal for storing and versioning large training datasets and model artifacts. S3's versioning feature allows you to preserve, retrieve, and restore every version of an object, which is essential for reproducibility in ML workflows.

Answer

Amazon DynamoDB

Answer

Amazon Elastic File System (EFS)

Answer

Amazon Elastic Block Store (EBS)

Question 18

An ML engineer needs to run a hyperparameter tuning job on Amazon SageMaker. The training algorithm supports distributed training across multiple GPUs. The engineer wants to minimize the total time to find the best hyperparameters. Which strategy should be used?

Accepted Answer

Use Bayesian optimization as the tuning strategy.. Bayesian optimization is the correct choice because it builds a probabilistic model of the objective function and uses an acquisition function to select the most promising hyperparameters to evaluate next. This approach converges to optimal hyperparameters in far fewer trials than random or grid search, minimizing total tuning time. SageMaker's built-in hyperparameter tuning jobs natively support Bayesian optimization and can leverage distributed training across multiple GPUs without any additional configuration.

Answer

Use random search to explore a wide range.

Answer

Use grid search to cover all combinations.

Answer

Use Hyperband which is designed for distributed training.

Question 19

A SageMaker endpoint configuration is shown in the exhibit. The company wants to deploy the model to a real-time endpoint. What is missing from this configuration to successfully create the endpoint?

Accepted Answer

The endpoint name is not specified in the configuration. The endpoint configuration must include an EndpointName parameter to uniquely identify the endpoint within the AWS account and region. Without it, the CreateEndpoint API call fails because the service cannot route traffic or manage the deployment. The exhibit shows a valid EndpointConfigName, but the endpoint itself is not named, which is a required field for real-time inference endpoints.

Answer

The model name is missing

Answer

The initial instance count is missing

Answer

The accelerator type is missing

Answer

The data capture configuration is missing

Question 20

A data scientist creates the above IAM policy and attaches it to a role used by an Amazon SageMaker notebook instance. When trying to save a file to the S3 bucket, the operation fails. What is the missing permission?

Accepted Answer

kms:GenerateDataKey. (kms:GenerateDataKey) because the S3 bucket is likely encrypted with a KMS key. When SageMaker writes an object to an encrypted bucket, it needs permission to call kms:GenerateDataKey to generate a data key for encryption. Option A (kms:Decrypt) is for decryption, not encryption. Option B (s3:ListBucket) allows listing objects, not writing. Option D (s3:GetObject) allows reading objects, not writing. The error when saving indicates missing encryption permissions.

Answer

kms:Decrypt

Answer

s3:ListBucket

Answer

s3:GetObject