MLS-C01 Practice Exam 51 — 20 Questions

Question 1

A data scientist is deploying a model on Amazon SageMaker. The model requires inference on images, and the data scientist wants to use a GPU instance for low latency. However, the data scientist is unsure about the instance type to choose for the endpoint. Which TWO factors should the data scientist consider when selecting the instance type? (Choose TWO.)

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

Accepted Answer

The cost per inference for the instance type. Cost per inference directly impacts operational budget, especially with GPU instances that have higher hourly costs; data scientists must balance low latency with cost efficiency. Option E is correct because GPU memory limits the size of models and batch sizes that can be processed in a single inference call, directly affecting latency and throughput. Both factors are critical when selecting an instance type for real-time inference on SageMaker.

Answer

The time taken to train the model

Answer

The number of vCPUs on the instance

Answer

The AWS Region of the S3 bucket storing the model

Question 2

A company uses AWS Glue to run ETL jobs that transform data from Amazon RDS for MySQL to Amazon S3. The current job runs daily and takes 3 hours to process 100 GB of data. The company expects data volume to grow 10x in the next year. They need to reduce job runtime and cost. Which approach should they take?

Accepted Answer

Use parallel reads with pushdown predicates in the Glue job's source connection, and write the output in columnar format (Parquet) partitioned by date.. Using parallel reads with pushdown predicates reduces the amount of data transferred from RDS to Glue by filtering at the database level, which lowers extraction time and load on the source. Writing output in columnar format (Parquet) reduces storage size and improves query performance for downstream analytics. Partitioning by date enables efficient pruning. Option A is incorrect because S3 Select is used for server-side filtering of data already in S3, not for tuning extraction from RDS. Option C is incorrect because increasing DPUs alone does not solve the bottleneck from the source database; pushdown predicates are more effective. Option D is incorrect because Redshift Spectrum is used for querying data in S3, not for performing transformations in ETL jobs.

Answer

Use S3 Select with Glue to filter data before transformation.

Answer

Increase the number of Glue DPUs to 100 and enable job bookmarking.

Answer

Use Amazon Redshift Spectrum to perform transformations in place on S3.

Question 3

A data scientist is training a deep learning model on Amazon SageMaker for image classification. The training is taking a long time and the GPU utilization is consistently below 30%. What should the data scientist do to improve GPU utilization and reduce training time?

Accepted Answer

Increase the batch size.. Low GPU utilization (below 30%) indicates that the GPU is spending most of its time waiting for data to process, often due to small batch sizes that underutilize the GPU's parallel compute capacity. Increasing the batch size allows the GPU to process more samples per forward/backward pass, improving arithmetic intensity and hardware utilization, which directly reduces total training time on SageMaker.

Answer

Use early stopping to stop training earlier.

Answer

Switch to a CPU-only instance.

Answer

Reduce the number of layers in the model.

Question 4

A company is building a recommendation system using Amazon SageMaker Factorization Machines. The dataset includes user IDs, item IDs, and implicit feedback (clicks). The data is sparse with millions of users and items. The model needs to capture interactions between users and items. Which hyperparameter tuning strategy should be used to improve model performance?

Accepted Answer

Increase the number of factors (num_factors) to capture more latent features.. (increase number of factors) is correct because increasing num_factors increases the dimensionality of the latent feature vectors, allowing the model to capture more complex interactions between users and items. Option A (L2 regularization) helps prevent overfitting but does not increase the model's capacity to capture interactions. Option B (batch size) affects training speed and stability, not the expressiveness of the model. Option C (learning rate) influences convergence but not the complexity of interactions. Option D (activation function) is not applicable since Factorization Machines are linear models and do not use activation functions like ReLU.

Answer

Increase L2 regularization to prevent overfitting.

Answer

Increase the batch size to speed up training.

Answer

Decrease the learning rate to improve convergence.

Answer

Change the activation function to ReLU.

Question 5

A company is preparing a dataset for training a binary classification model. The dataset has a severe class imbalance (1% positive class). The data scientist wants to understand the impact of this imbalance on model performance before sampling. Which exploratory analysis step is MOST critical?

Accepted Answer

Plot the distribution of each feature separately for the positive and negative classes.. The most critical step because plotting the distribution of each feature separately for the positive and negative classes allows the data scientist to visually assess class separability, overlap, and feature behavior under severe imbalance. This insight directly informs the impact of imbalance on model performance before any sampling. Options A, B, and C are less critical at this stage: correlation with the target (A) does not reveal class-level distributions; missing values and outliers (B) are important but not specific to understanding imbalance impact; PCA (C) is a dimensionality reduction technique that may obscure per-feature patterns and is not necessary for initial exploratory analysis of class distributions.

Answer

Compute the correlation matrix of all features with the target variable.

Answer

Check for missing values and outliers in the dataset.

Answer

Perform PCA and visualize the first two principal components colored by class.

Question 6

A data scientist is analyzing a dataset stored in Amazon S3 (100 GB, CSV format) using Amazon SageMaker Studio. The dataset contains 500 columns and 10 million rows. The data scientist wants to understand the distribution of each column, detect missing values, and identify outliers. However, the SageMaker Studio notebook instance runs out of memory when loading the entire dataset into a pandas DataFrame. The data scientist needs to complete the EDA efficiently without modifying the source data. What should the data scientist do?

Accepted Answer

Use Amazon SageMaker Data Wrangler to create a data flow that samples and profiles the data.. SageMaker Data Wrangler is purpose-built for EDA on large datasets; it automatically samples data and profiles columns without requiring the entire dataset to be loaded into memory. Option A (sampling 10% of rows) could work but risks missing critical patterns or outliers, and is less integrated than Data Wrangler. Option B (converting to Parquet with AWS Glue) adds complexity and still requires memory to load into pandas. Option C (larger instance) may still be insufficient and is more expensive. Data Wrangler provides a seamless, integrated experience within SageMaker Studio for efficient EDA.

Answer

Write a script that loads only a random 10% sample of rows to reduce memory usage.

Answer

Use AWS Glue ETL to transform the data into Parquet format and then load into pandas.

Answer

Launch a larger notebook instance with more memory (e.g., ml.r5.24xlarge) and reload the data.

Question 7

A data scientist needs to run a hyperparameter tuning job for a deep learning model. Which SageMaker feature should they use?

Accepted Answer

SageMaker Hyperparameter Tuning Job. SageMaker Hyperparameter Tuning Job (option A) is the correct feature because it is the native SageMaker capability designed specifically to automate the search for optimal hyperparameters for a machine learning model. It launches multiple training jobs with different hyperparameter combinations, evaluates them against a specified objective metric, and uses strategies like Bayesian optimization or random search to converge on the best configuration. This directly matches the requirement to run a hyperparameter tuning job for a deep learning model.

Answer

SageMaker Experiments

Answer

SageMaker Automatic Model Tuning

Answer

SageMaker Processing

Question 8

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. SSE-C allows you to provide your own encryption key, which can be stored in your own HSM, and Amazon S3 manages the encryption/decryption process using that key. This satisfies the requirement for server-side encryption with a key managed by the company's HSM, ensuring data at rest is encrypted without exposing the key to AWS.

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 9

A company is using Amazon SageMaker to train a model. The training job is taking too long. The data scientist notices that the GPU utilization is low. Which action should be taken to improve training performance?

Accepted Answer

Increase the batch size in the training script.. Low GPU utilization during training typically indicates that the GPU is waiting for data, often due to a small batch size that underutilizes the GPU's parallel processing capacity. Increasing the batch size allows the GPU to process more samples per step, improving computational efficiency and throughput, which directly addresses the low utilization issue.

Answer

Increase the number of training instances.

Answer

Use spot instances to reduce cost.

Answer

Decrease the batch size to reduce memory usage.

Question 10

A machine learning engineer is performing exploratory data analysis on a dataset containing customer transaction records. The dataset includes a column 'transaction_date' with timestamps. The engineer wants to derive features such as day of the week, hour, and month for modeling. Which AWS service can be used directly to extract these features without writing custom code?

Accepted Answer

AWS Glue ETL with built-in timestamp transforms. AWS Glue ETL provides built-in transforms like `ExtractTimestamp` that can parse timestamps and extract date/time components (e.g., day of week, hour, month) without writing custom code. Option B is wrong because Amazon Athena requires writing SQL queries to extract date parts, which constitutes custom code. Option C is wrong because Amazon QuickSight is a BI visualization tool, not designed for feature engineering. Option D is wrong because Amazon SageMaker Data Wrangler, while offering visual transformations, requires an active SageMaker Studio environment and is not a serverless ETL service like AWS Glue.

Answer

Amazon Athena with SQL date functions

Answer

Amazon QuickSight

Answer

Amazon SageMaker Data Wrangler

Question 11

A team deployed a SageMaker endpoint for real-time inference using a PyTorch model. After monitoring, they notice that the latency is highly variable, with p99 latency 10x the p50 latency. The endpoint uses a single ml.c5.2xlarge instance with auto-scaling based on average CPU utilization. Which change is most likely to reduce latency variability?

Accepted Answer

Change the auto-scaling metric to 'InvocationsPerInstance'. Scaling based on InvocationsPerInstance allows the endpoint to react more quickly to changes in request volume, reducing the queueing that causes high p99 latency. Option A (increasing batch size) would actually increase latency. Option B (pre-warming) helps with cold starts but not queueing from traffic spikes. Option C (GPU instance) is unlikely to help if the model is CPU-bound and would not address the root cause of latency variability.

Answer

Increase the batch size for inference

Answer

Pre-warm the model by sending dummy requests every minute

Answer

Switch to a GPU instance type

Question 12

Which THREE of the following are valid approaches for deploying a machine learning model to an Amazon SageMaker endpoint for real-time inference?

Accepted Answer

Use a SageMaker Inference Pipeline with multiple containers. SageMaker Inference Pipelines allow you to chain multiple containers (e.g., preprocessing, prediction, postprocessing) into a single endpoint, enabling complex workflows for real-time inference. This is achieved by defining a sequence of Docker containers in the model definition, where each container's output is passed as input to the next, all within the same SageMaker endpoint.

Answer

Use Amazon EMR to host the model

Answer

Deploy the model as an AWS Lambda function

Question 13

A machine learning team is using Amazon SageMaker to train a deep learning model on a large dataset stored in Amazon S3. The training job is taking too long. The team wants to reduce training time without modifying the model architecture. Which THREE actions should the team take? (Choose 3.)

Accepted Answer

Enable SageMaker Managed Spot Training to use cheaper spot instances.. SageMaker Managed Spot Training enables the use of spot instances at a reduced cost, allowing the team to allocate more resources (e.g., more or larger instances) within the same budget, which can directly reduce training time. Option C is correct because distributed training across multiple GPU instances parallelizes the workload, significantly reducing training duration. Option D is correct because Pipe input mode streams data from Amazon S3 directly to the training algorithm, minimizing I/O bottlenecks and reducing time spent waiting for data to load. Option B is not one of the three best choices because simply using a larger instance may not fully address I/O or parallelism bottlenecks and can be more expensive. Option E is incorrect because SageMaker Processing is designed for data preprocessing, not for accelerating training itself.

Answer

Use a larger instance type with more vCPUs and memory.

Answer

Use SageMaker Processing to preprocess the data.

Question 14

A machine learning engineer needs to deploy a TensorFlow model to a SageMaker endpoint. The model expects a specific input format. The engineer has the model artifacts stored in an S3 bucket. Which step is REQUIRED to deploy the model?

Accepted Answer

Create a SageMaker Model object using the TensorFlow serving image.. To deploy a TensorFlow model to a SageMaker endpoint, you must create a SageMaker Model object that references the model artifacts in S3 and specifies the appropriate TensorFlow Serving container image. This image handles loading the model and exposing a RESTful or gRPC inference endpoint. Without this step, SageMaker cannot associate the artifacts with a serving container to start the endpoint.

Answer

Register the model in SageMaker Model Registry.

Answer

Create a SageMaker training job to re-train the model.

Answer

Save the model as a SavedModel format.

Question 15

A data engineer needs to transform large CSV files stored in S3 into Parquet format and load them into a data warehouse for analysis. The transformation must be cost-effective and serverless. Which AWS service should be used?

Accepted Answer

AWS Glue. AWS Glue is the correct choice because it provides a fully managed, serverless ETL service that can automatically convert CSV files from S3 into Parquet format using its built-in Spark engine. It is cost-effective as you only pay for the resources consumed during the job execution, and it integrates directly with data warehouses like Amazon Redshift for loading transformed data.

Answer

Amazon Athena

Answer

Amazon EMR with Spark

Answer

AWS Data Pipeline

Question 16

A data scientist is training a binary classification model using Amazon SageMaker. The dataset is highly imbalanced (99% negative class, 1% positive class). The model currently achieves 99% accuracy but fails to detect most positive cases. Which metric should the data scientist primarily use to evaluate model performance?

Accepted Answer

F1 score. In highly imbalanced datasets (99% negative, 1% positive), accuracy is misleading because a model can achieve 99% accuracy by simply predicting the majority class for all instances, failing to detect any positive cases. The F1 score (option B) is the harmonic mean of precision and recall, providing a balanced measure that penalizes models that trade off recall for precision or vice versa. This makes it the primary metric for evaluating binary classification performance on imbalanced data, as it directly reflects the model's ability to correctly identify positive cases while minimizing false positives.

Answer

ROC AUC

Answer

Recall

Answer

Accuracy

Question 17

A data scientist is using SageMaker to train a deep learning model. The training script uses TensorFlow and runs on a single p3.2xlarge instance. The scientist wants to reduce training time by using multiple GPUs. What should the scientist do?

Accepted Answer

Modify the training script to use Horovod for distributed training.. Horovod is a distributed deep learning framework that integrates with TensorFlow to enable multi-GPU training across multiple instances. By modifying the training script to use Horovod's `hvd.DistributedOptimizer` and broadcasting initial variables, the data scientist can leverage multiple GPUs on a single p3.2xlarge instance (which has 1 GPU) or scale to multiple instances, directly reducing training time through data parallelism.

Answer

Increase the instance count to 4 without changing the script.

Answer

Switch to PyTorch framework.

Answer

Use SageMaker Managed Spot Training.

Question 18

A data scientist needs to understand the distribution of a numeric feature in a dataset stored in Amazon S3. Which AWS service can be used to run a quick exploratory query without setting up a server?

Accepted Answer

Amazon Athena. Amazon Athena allows serverless SQL queries on data in S3. Option A (Amazon Redshift) is a data warehouse; Option B (Amazon EMR) requires cluster setup; Option D (AWS Glue) is for ETL.

Answer

Amazon Redshift

Answer

Amazon EMR

Answer

AWS Glue

Question 19

A data engineering team is designing a data pipeline to process streaming data from social media feeds. The data must be deduplicated, enriched with customer information from a relational database, and stored in Amazon S3 in Parquet format. Which AWS services should the team use to build this pipeline? (Select TWO.)

Accepted Answer

AWS Glue. AWS Glue is correct because it provides a serverless ETL service that can transform streaming data stored in Amazon S3 into Parquet format. It can also connect to a relational database via JDBC to enrich the data with customer information, and its built-in deduplication capabilities (e.g., using DropDuplicates in PySpark) handle the deduplication requirement.

Answer

Amazon Kinesis Data Firehose

Answer

Amazon Athena

Answer

Amazon SageMaker

Question 20

A company has a time series forecasting problem with daily sales data. The data shows both trend and seasonality. Which Amazon SageMaker built-in algorithm is most suitable?

Accepted Answer

DeepAR. DeepAR is a supervised learning algorithm for time series forecasting that explicitly models both trend and seasonality using recurrent neural networks (RNNs). It is designed to handle multiple related time series, incorporate additional features like holidays or promotions, and produce probabilistic forecasts, making it the most suitable choice for daily sales data with trend and seasonal patterns.

Answer

K-Means

Answer

Linear Learner

Answer

XGBoost