MLS-C01 Practice Exam 70 — 20 Questions

Question 1

A data scientist wants to understand the statistical relationship between two categorical variables in a dataset. Which test is most appropriate?

Accepted Answer

Chi-squared test. The chi-squared test is used to determine if there is a significant association between two categorical variables, which is exactly what the data scientist wants to understand. Option B (Pearson correlation coefficient) is incorrect because it measures linear relationship between two continuous variables. Option C (Student's t-test) is used to compare means of two groups, typically for continuous data. Option D (ANOVA) is used to compare means across three or more groups, also for continuous data.

Answer

Pearson correlation coefficient

Answer

Student's t-test

Answer

ANOVA test

Question 2

A data scientist is using SageMaker to train a model that requires access to a private S3 bucket in another account. The scientist has set up the correct IAM roles and bucket policies. However, the training job fails with an access denied error. What is the most likely cause?

Accepted Answer

The VPC used for training does not have a route to S3 (e.g., missing VPC endpoint or NAT). When a SageMaker training job runs inside a VPC (which is common for cross-account access), the VPC must have a route to S3, either through a VPC endpoint (Gateway or Interface) or a NAT gateway. Without such a route, the training instances cannot reach the private S3 bucket in the other account, even if IAM roles and bucket policies are correctly configured, resulting in an 'access denied' error because the network path is blocked.

Answer

The SageMaker execution role does not have s3:GetObject permission

Answer

The S3 objects are encrypted with SSE-KMS and the KMS key is not accessible

Answer

The training instance type does not support S3 access

Question 3

A team is training a deep learning model on SageMaker using a custom Docker container. The training job fails with 'OutOfMemoryError'. The instance type is ml.p3.2xlarge with 61 GB memory. Which change should increase available memory?

Accepted Answer

Set the 'shm-size' parameter in the SageMaker training container to a larger value.. The 'OutOfMemoryError' in a SageMaker training container often stems from insufficient shared memory (/dev/shm) for data-loading workers, especially with PyTorch or TensorFlow dataloaders that use multiprocessing. Increasing the 'shm-size' parameter allocates more shared memory to the container, resolving the error without altering the model or instance type.

Answer

Reduce the batch size to use less memory.

Answer

Use SageMaker distributed data parallelism to distribute the model across multiple instances.

Answer

Mount an Amazon FSx for Lustre file system to offload data.

Question 4

A data analyst is examining a scatter plot of two variables and notices a strong positive correlation. Which of the following is a valid conclusion?

Accepted Answer

The two variables are related, but causation cannot be inferred. A strong positive correlation indicates that the two variables are related, but correlation alone does not imply causation. Option A is incorrect because correlation does not necessarily imply a linear relationship; it could be non-linear or monotonic. Option B is incorrect because correlation does not imply causation. Option D is incorrect because correlation does not guarantee accurate prediction; prediction requires a well-fitted model and additional validation.

Answer

The relationship is linear

Answer

One variable causes the other

Answer

The relationship can be used to accurately predict one variable from the other

Question 5

A data scientist is training a binary classification model on an imbalanced dataset (95% negative class, 5% positive class). The model currently achieves 94% accuracy but a recall of only 0.10 on the positive class. Which TWO strategies should the data scientist consider to improve recall without significantly sacrificing precision? (Choose 2.)

Accepted Answer

Assign higher class weights to the positive class in the loss function.. Assigning higher class weights to the positive class in the loss function (option C) penalizes misclassifications of the minority class more heavily, forcing the model to focus on positive examples. Oversampling the minority class using SMOTE (option E) generates synthetic positive samples, improving the model's ability to learn decision boundaries for the positive class. Both techniques directly address class imbalance without discarding data. Option A (undersampling) may remove useful negative samples, harming overall performance. Option B (increasing regularization) reduces overfitting but does not specifically improve recall. Option D (using a deeper network) may increase overfitting and does not target recall directly.

Answer

Undersample the majority class to match the minority class size.

Answer

Increase the regularization strength to reduce overfitting.

Answer

Use a deeper neural network with more layers.

Question 6

A company uses Amazon Kinesis Data Firehose to deliver streaming data to Amazon S3. The data is in JSON format, and the company wants to convert it to Parquet for efficient querying. Which configuration should be used?

Accepted Answer

Enable data transformation in Firehose using an AWS Lambda function to convert JSON to Parquet, and set the output format to Parquet.. Amazon Kinesis Data Firehose supports data transformation via AWS Lambda, allowing you to convert incoming JSON records to Parquet format before delivery to S3. By enabling a Lambda function to perform the conversion and setting the output format to Parquet, Firehose handles the transformation in-stream, ensuring the data lands in S3 already in the optimized columnar format for efficient querying with services like Amazon Athena or Amazon Redshift Spectrum.

Answer

Use an AWS Glue job to convert the JSON files in S3 to Parquet after delivery.

Answer

Use Amazon Kinesis Data Analytics to convert the stream to Parquet before sending to Firehose.

Answer

Configure Firehose to deliver data directly to Amazon Redshift, which automatically converts to Parquet.

Question 7

A company is using Amazon SageMaker to train a deep learning model for image classification. The training job is using a single p3.2xlarge instance and takes 10 hours. The data scientist wants to reduce training time using distributed training. Which SageMaker feature should be used?

Accepted Answer

Use the SageMaker distributed data parallelism library with multiple p3.2xlarge instances.. The goal is to reduce training time, and the SageMaker distributed data parallelism library is designed to split the mini-batch across multiple GPU instances, enabling synchronous or asynchronous gradient updates that scale near-linearly with the number of instances. By adding more p3.2xlarge instances, the effective throughput increases, directly reducing wall-clock training time for the image classification model.

Answer

Use SageMaker Managed Spot Training to reduce cost, but training time remains the same.

Answer

Use SageMaker Hyperparameter Tuning to find optimal hyperparameters faster.

Answer

Use the SageMaker distributed model parallelism library with a single p3dn.24xlarge instance.

Question 8

A data scientist is deploying a model using Amazon SageMaker. The model endpoint needs to handle real-time inference requests with low latency. The model is a large ensemble of 10 deep learning models, each approximately 500 MB. What is the most cost-effective deployment strategy that meets the low-latency requirement?

Accepted Answer

Use a SageMaker multi-model endpoint to host all models on one or more instances.. A SageMaker multi-model endpoint (MME) allows hosting multiple models on a single or few instances, dynamically loading them from Amazon S3 into memory as needed. This is the most cost-effective option for a large ensemble of 500 MB models because it avoids the expense of separate endpoints or multiple instances per model, while still supporting low-latency real-time inference by keeping frequently used models cached.

Answer

Deploy each model to a separate endpoint and use a load balancer.

Answer

Use a single endpoint with multiple instances behind it.

Answer

Use a SageMaker batch transform job to process inference requests in batches.

Question 9

A company uses AWS Glue to run ETL jobs on a daily schedule. The jobs are failing intermittently with 'OutOfMemory' errors. The data volume has grown 5x over the past month. Which is the MOST cost-effective fix?

Accepted Answer

Increase the number of DPUs for the Glue job. The 'OutOfMemory' errors in AWS Glue are caused by insufficient compute resources (DPUs) to process the 5x increased data volume. Increasing the number of DPUs allocates more memory and processing capacity to the job, directly addressing the memory shortage without changing the data or architecture. This is the most cost-effective fix because it scales resources incrementally rather than switching to a more expensive service like EMR.

Answer

Increase the number of partitions in the source S3 data

Answer

Reduce the data volume by sampling

Answer

Switch from AWS Glue to Amazon EMR

Question 10

A data scientist is using Amazon SageMaker to train a linear regression model. The training data contains missing values. Which TWO techniques are appropriate for handling missing values in the dataset?

Accepted Answer

Remove rows with missing values if the proportion is small. Removing rows with missing values is a straightforward and effective technique when the proportion of missing data is small (e.g., less than 5% of the total dataset). This avoids introducing bias or distorting the distribution, which is critical for linear regression models that assume complete and normally distributed data. In Amazon SageMaker, this can be done during data preprocessing using built-in transformations or custom scripts before training.

Answer

Use a decision tree model that can handle missing values internally

Answer

Set missing values to zero

Answer

Create a separate category for missing values

Question 11

A data scientist is analyzing a dataset and finds that two features have a Pearson correlation coefficient of 0.95. Which TWO actions should the data scientist consider? (Choose two.)

Accepted Answer

Combine the two features into a single feature using PCA or averaging. A Pearson correlation coefficient of 0.95 indicates strong multicollinearity between the two features. Multicollinearity can inflate coefficient variances and reduce model interpretability. Two standard remedies are to remove one of the correlated features (Option D) or to combine them into a single feature using techniques like PCA, averaging, or summing (Option A). Option B (adding interaction terms) would introduce additional correlated terms and exacerbate multicollinearity. Option C (increasing regularization) can help stabilize coefficients but does not directly address the high pairwise correlation; it is often used as a secondary technique after feature selection or combination. Option E (standard scaling) does not change the correlation coefficient and therefore does not mitigate multicollinearity.

Answer

Add interaction terms between the features

Answer

Increase regularization strength in the model

Answer

Apply standard scaling to both features

Question 12

Refer to the exhibit. A data scientist creates a SageMaker notebook instance using this Terraform configuration. The notebook fails to start. The logs indicate 'The IAM role does not have the necessary permissions'. Which addition to the IAM role policy is MOST likely needed?

Accepted Answer

sagemaker:CreatePresignedNotebookInstanceUrl. The SageMaker notebook instance requires the `sagemaker:CreatePresignedNotebookInstanceUrl` permission to generate a presigned URL, which is used to access the notebook's Jupyter interface. Without this permission, the notebook fails to start because the IAM role cannot create the necessary URL for the user to connect, as indicated by the 'The IAM role does not have the necessary permissions' log error.

Answer

cloudwatch:PutMetricData

Answer

s3:GetObject on the notebook bucket

Answer

sagemaker:CreateTrainingJob

Question 13

A data scientist is training a model using SageMaker and wants to use spot instances to reduce costs. Which THREE considerations should the scientist evaluate? (Choose THREE.)

Accepted Answer

The training job must support checkpointing to save progress.. SageMaker managed spot training requires checkpointing to save model state at regular intervals. If a spot instance is interrupted, the training job can resume from the last checkpoint rather than starting from scratch, which is essential for long-running or expensive training jobs.

Answer

Spot instances have a fixed, lower price than on-demand.

Answer

Spot instances are only available for inference, not training.

Question 14

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

Accepted Answer

Amazon SageMaker Pipelines. Amazon SageMaker Pipelines is a purpose-built service for creating, automating, and managing end-to-end machine learning workflows. It provides direct integration with SageMaker's training, tuning, and deployment steps, allowing you to define a directed acyclic graph (DAG) of ML steps that can be triggered on a schedule or by events. AWS Step Functions is a serverless orchestration service that lets you coordinate multiple AWS services into flexible workflows. It can orchestrate ML pipelines by integrating with SageMaker, Lambda, and other services, making it a viable alternative for complex, multi-step workflows that may span beyond SageMaker's native capabilities. Both services are capable of orchestrating ML pipelines.

Answer

Amazon SageMaker Ground Truth

Answer

Amazon Redshift

Answer

AWS Glue

Question 15

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. Enabling HTTPS for the SageMaker endpoint encrypts data in transit using TLS/SSL. SageMaker endpoints support HTTPS by default when using the InvokeEndpoint API, and you can enforce HTTPS by configuring a custom VPC and security group to only allow HTTPS traffic. Option D is correct because encryption at rest for the endpoint's ML storage volume can be enabled by specifying an AWS KMS key when creating the endpoint configuration. This encrypts the temporary storage used during inference. Option E is correct by attaching a resource-based IAM policy to the endpoint to control which IAM principals (users, roles) can invoke the endpoint, meeting access control requirements. Option B is incorrect because using a VPC is not required for encryption or access control; it provides network isolation but does not directly enforce HTTPS or IAM access. Option C is incorrect because SSE-S3 encrypts model artifacts in S3, not the endpoint's ML storage volume; encryption at rest for the endpoint must be configured at the endpoint level.

Answer

Configure the endpoint to use a VPC

Answer

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

Question 16

A company is designing a data pipeline to ingest data from multiple sources into an Amazon S3 data lake. The data must be encrypted at rest and in transit. Which TWO actions should be taken to meet these requirements?

Accepted Answer

Enable Server-Side Encryption on the S3 bucket. Enabling Server-Side Encryption (SSE-S3 or SSE-KMS) on the S3 bucket automatically encrypts data at rest when written to disk, using AES-256 encryption. This meets the requirement for encryption at rest without any client-side changes.

Answer

Enable S3 Transfer Acceleration

Answer

Use client-side encryption before uploading

Answer

Use S3 VPC Endpoint

Question 17

A data engineer needs to move 50 TB of historical data from an on-premises Hadoop cluster to Amazon S3. The network bandwidth is limited to 100 Mbps. Which AWS service should be used to transfer the data most efficiently?

Accepted Answer

AWS Snowball Edge device to physically ship the data.. Given 50 TB of data and a 100 Mbps network link, the theoretical minimum transfer time over the network is over 46 days (50 TB * 8 / 100 Mbps ≈ 4,000,000 seconds ≈ 46.3 days), not accounting for protocol overhead, retransmissions, or contention. AWS Snowball Edge is a physical appliance that bypasses the network bottleneck entirely, allowing you to copy data locally and ship it to AWS, making it the most efficient option for this volume over a constrained link.

Answer

Amazon S3 Transfer Acceleration to speed up the transfer.

Answer

AWS Direct Connect to establish a dedicated network connection.

Answer

AWS Site-to-Site VPN to connect and copy data.

Question 18

A data engineering team is designing a data lake on Amazon S3. Raw data is ingested in JSON format and must be partitioned by year, month, and day. The team expects high query performance for recent data but infrequent queries for older data. The data is immutable. Which storage tier configuration minimizes costs while meeting performance requirements?

Accepted Answer

Use S3 Intelligent-Tiering for the entire data lake. S3 Intelligent-Tiering automatically moves objects between access tiers (frequent, infrequent, and archive instant access) based on changing access patterns, without performance impact or lifecycle management overhead. This matches the workload: recent data is queried frequently (automatic frequent tier), older data is queried rarely (automatic infrequent/archive instant tiers), and data is immutable, so no write/delete penalties apply. It minimizes cost by charging only for the tiers actually used, while maintaining millisecond latency for all tiers.

Answer

Store all data in S3 Standard, then move to S3 Glacier after 30 days using a lifecycle policy

Answer

Store recent partitions in S3 Standard, older partitions in S3 One Zone-IA

Answer

Keep all data in S3 Standard because query performance is critical

Question 19

A machine learning team needs to preprocess large volumes of clickstream data stored in Amazon S3 before training a model. The preprocessing includes data cleaning, feature engineering, and normalization. The team wants to use a serverless solution that minimizes operational overhead. Which combination of services should the team use?

Accepted Answer

AWS Glue ETL jobs reading from and writing to S3.. AWS Glue ETL jobs are a serverless solution that automatically provisions and scales the underlying compute resources, making them ideal for preprocessing large volumes of clickstream data stored in S3. Glue can read directly from S3, perform data cleaning, feature engineering, and normalization using PySpark or Scala, and write the transformed data back to S3, all without managing any infrastructure. This minimizes operational overhead while handling the required preprocessing tasks at scale.

Answer

Amazon SageMaker Notebooks with custom Python scripts.

Answer

Amazon EMR with Spark clusters.

Answer

Amazon Athena with SQL queries.

Question 20

A data scientist is deploying a model on Amazon SageMaker for real-time inference. The model is a PyTorch model that requires custom inference code. The data scientist needs to handle variable-length inputs and optimize inference latency. Which TWO steps should the data scientist take? (Choose TWO.)

Accepted Answer

Use TorchScript to compile the model for optimized inference.. TorchScript compiles PyTorch models for optimized inference, reducing execution time and handling variable-length inputs efficiently. Option E is correct because a custom inference script (inference.py) is required to define preprocessing, prediction, and postprocessing logic for variable-length inputs. Option A is incorrect because SageMaker Batch Transform is designed for offline, asynchronous inference and cannot be used for real-time endpoints with sub-second latency. Options B and C are also incorrect: using the PyTorch container without modifications would not support custom inference code, and multiple variants are for A/B testing, not latency optimization.

Answer

Enable SageMaker batch transform to process requests in batches.

Answer

Use the SageMaker PyTorch container without any modifications.

Answer

Set the endpoint to use multiple variants for A/B testing.