MLS-C01 Practice Exam 60 — 20 Questions

Question 1

A company is building a data pipeline that ingests data from multiple sources into a centralized data lake on Amazon S3. The data must be transformed before it is available for analysis. The pipeline should be event-driven, automatically triggering transformation jobs when new data arrives. Which combination of AWS services should be used?

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

Accepted Answer

Amazon S3 event notifications to invoke AWS Lambda, which triggers an AWS Glue job. Amazon S3 event notifications can be configured to invoke an AWS Lambda function when new objects are created in an S3 bucket. The Lambda function can then trigger an AWS Glue job to perform the necessary data transformations. This creates an event-driven, serverless pipeline that automatically processes data as it arrives, meeting the requirements for a centralized data lake on S3.

Answer

Amazon Kinesis Data Analytics for transformation

Answer

Amazon EMR with automatic scaling

Answer

AWS Step Functions to orchestrate the pipeline

Question 2

A machine learning engineer needs to store training data in Amazon S3 for a SageMaker training job. The data is currently in Amazon Redshift and is about 2 TB. The engineer wants to minimize the time to transfer the data and ensure the training job can access it efficiently. Which method should the engineer use to move the data from Amazon Redshift to Amazon S3?

Accepted Answer

Use the UNLOAD command in Amazon Redshift to export the data directly to Amazon S3 in Parquet format.. The UNLOAD command is the native and most efficient way to export large datasets from Amazon Redshift to Amazon S3. It parallelizes the export across slices, supports columnar formats like Parquet, and can compress data, reducing transfer time and storage costs. Other methods like DMS or Glue add overhead and are not optimized for this specific bulk export scenario. Therefore, UNLOAD is the best choice.

Answer

Use the Amazon Redshift COPY command to copy the data from Redshift to Amazon S3.

Answer

Use the AWS Glue crawler to catalog the Redshift data and then use AWS Glue ETL to write to Amazon S3.

Answer

Use AWS Database Migration Service (AWS DMS) to replicate the data from Amazon Redshift to Amazon S3.

Question 3

A media company ingests live video telemetry into Amazon Kinesis Data Streams. A consumer application reads the stream and must process each record exactly once before writing enriched results to Amazon S3. The team observes duplicate records in S3 after consumer restarts. Which two actions should the engineer take to eliminate duplicates? (Choose two.)

Accepted Answer

Make the S3 write idempotent by including a deterministic record identifier and using conditional writes or deduplication before storing.. Eliminating duplicates requires both reliable progress tracking and safe re-writes. Checkpointing with the Kinesis Client Library lets a restarted consumer resume from the last processed sequence number, while idempotent, deduplicated S3 writes absorb any records reprocessed during the window between processing and checkpointing. Together they deliver effectively-once results; scaling shards, enhanced fan-out, or encryption do not affect duplicate semantics.

Answer

Enable server-side encryption with AWS KMS on the stream and the S3 bucket.

Answer

Switch the consumer to use enhanced fan-out with a dedicated throughput of 2 MB per second per shard.

Answer

Increase the number of shards in the stream so each consumer processes fewer records.

Question 4

A machine learning engineer is deploying a real-time inference endpoint on Amazon SageMaker. The model artifacts are stored in an Amazon S3 bucket that is encrypted with AWS Key Management Service (KMS) using a customer managed key. The SageMaker execution role has permissions to access the S3 bucket but does not have any KMS permissions. When the engineer attempts to create the endpoint, the deployment fails with an error indicating that the model data cannot be downloaded. Which action should the engineer take to resolve this issue?

Accepted Answer

Add a policy to the SageMaker execution role granting kms:Decrypt and kms:GenerateDataKey permissions for the customer managed key.. The failure occurs because the SageMaker execution role lacks permissions to decrypt the model artifacts encrypted with a customer managed KMS key. Although the role has S3 access, KMS decryption is a separate authorization step. Adding kms:Decrypt and kms:GenerateDataKey to the execution role allows SageMaker to access the encrypted objects and deploy the endpoint successfully.

Answer

Configure the S3 bucket to use server-side encryption with Amazon S3 managed keys (SSE-S3) instead of the customer managed key.

Answer

Add a bucket policy to the S3 bucket that allows the SageMaker service principal to perform s3:GetObject on the model artifacts.

Answer

Modify the SageMaker notebook instance's IAM role to include kms:Decrypt permissions for the customer managed key.

Question 5

A data scientist is analyzing a dataset with missing values in several columns. The dataset contains customer demographic information and purchase history. Which approach should the data scientist take to handle missing values without introducing bias into the dataset?

Accepted Answer

Use multiple imputation to estimate missing values.. Multiple imputation produces multiple estimates of missing values, accounting for the uncertainty in the imputation and reducing bias compared to simpler methods. Option A is wrong because dropping all rows with missing values can lead to loss of data and potential bias if missingness is not completely random. Option B is wrong because mean imputation can underestimate variance and distort relationships between variables. Option C is wrong because replacing missing values with a constant (e.g., 0) introduces arbitrary values that can skew the data distribution.

Answer

Drop all rows with any missing values.

Answer

Impute missing values with the mean of each column.

Answer

Replace missing values with a constant, such as 0.

Question 6

A data engineer is building a feature pipeline that must replay the last 7 days of events from an Amazon Kinesis Data Stream into a new consumer application. The stream currently retains records for 24 hours, and the engineer must not change the retention period or affect existing consumers. Which approach allows the new consumer to read records from the past 7 days?

Accepted Answer

Point the new consumer at an Amazon S3 destination where the events were archived, such as a Firehose delivery stream or Kinesis Data Analytics output, and replay from there.. Kinesis Data Streams only permits reads within the configured retention window, so a 24-hour stream cannot serve seven-day-old records no matter which starting position or consumer type is used. Because retention must remain unchanged, the historical events must come from a durable store. Replaying from an S3 archive created by a delivery or analytics consumer provides the missing six days without affecting current readers.

Answer

Increase the stream's retention period to 168 hours, then read from TRIM_HORIZON, and leave it at 168 hours permanently.

Answer

Enable enhanced fan-out on the stream and register the new consumer with a starting timestamp 7 days in the past.

Answer

Use the Kinesis Client Library with a starting position of TRIM_HORIZON on the existing stream.

Question 7

A company runs an AWS Glue ETL job that reads JSON from Amazon S3, transforms records, and writes Parquet to another S3 prefix. The job must run every hour, and the team wants to minimize cost and manual scheduling effort. The transformation logic is already defined. What should the engineer configure?

Accepted Answer

Create a Glue trigger of type SCHEDULED with a cron expression that fires hourly and starts the existing job.. AWS Glue scheduled triggers are the native, serverless way to run a job on a recurring cron schedule. They require no external orchestration, keep cost low, and start the existing job definition automatically. Step Functions, EventBridge with Lambda, and bookmarks each address different concerns and either add overhead or fail to schedule the job at all.

Answer

Use AWS Step Functions with a Wait state to invoke the Glue job every hour.

Answer

Configure an Amazon EventBridge rule that runs on a schedule and starts an AWS Lambda function to submit the job.

Answer

Enable job bookmarks and set the job to run continuously.

Question 8

An ML engineer needs to give a SageMaker training job access to training data in an Amazon S3 bucket in the same account. Security policy requires that the job assume a dedicated IAM role and that the role be restricted to only the specific S3 prefix used for training. Which configuration should the engineer use?

Accepted Answer

Create an IAM role with an S3 read policy scoped to the training prefix and a trust policy allowing sagemaker.amazonaws.com to assume it, then pass the role ARN as the execution role of the training job.. Training jobs run under an execution role, and that role must both trust sagemaker.amazonaws.com and carry an identity-based policy granting read access to the training prefix. Scoping the policy resource to the specific prefix satisfies least privilege, and supplying the role ARN when configuring the job connects the container's temporary credentials to those permissions. Broad managed policies or user-level permissions do not meet the stated restrictions.

Answer

Attach an S3 read policy to the user account running the training job and rely on the user's credentials being passed to the training container.

Answer

Create an S3 bucket policy that allows the SageMaker service principal to read the prefix, and use the default SageMaker execution role for the job.

Answer

Create an IAM role with the AmazonS3FullAccess managed policy and a trust policy for sagemaker.amazonaws.com, then use it as the execution role.

Question 9

A machine learning engineer has trained a model using Amazon SageMaker and wants to deploy it for real-time inference. The model artifacts are stored in Amazon S3. The engineer needs to create a SageMaker endpoint that can serve predictions with low latency. Which step is required to deploy the model?

Accepted Answer

Create a SageMaker model, create an endpoint configuration, and create an endpoint.. The correct deployment process involves creating a SageMaker model that points to the model artifacts and inference image, then creating an endpoint configuration that specifies the instance type, and finally creating an endpoint that provisions the resources. This managed approach ensures low-latency, scalable real-time inference with minimal operational effort.

Answer

Use AWS CloudFormation to create an Amazon EC2 instance with the model and an Application Load Balancer.

Answer

Create a SageMaker notebook instance and run the model directly from the notebook.

Answer

Upload the model artifacts to Amazon ECR and create an AWS Lambda function.

Question 10

A company is using SageMaker to train a model with a large dataset that is stored in S3. The training job is taking a long time due to high I/O latency. The team has already converted the data to RecordIO format. What should they do next to reduce I/O latency?

Accepted Answer

Use Pipe mode to stream the RecordIO data. Pipe mode streams data directly from S3 to the training algorithm in a sequential manner, eliminating the need to download files to the local disk. Since the data is already in RecordIO format, Pipe mode can efficiently read the serialized records, significantly reducing I/O latency compared to File mode.

Answer

Use SageMaker fast file mode

Answer

Use multiple training instances

Answer

Use Amazon FSx for Lustre as the training data source

Answer

Shuffle the data before training

Question 11

A data scientist is exploring a dataset with mixed data types (numeric, categorical, text). The dataset has 5 million rows. The scientist wants to understand the relationships between variables and identify potential data quality issues. Which THREE tools are suitable for this analysis?

Accepted Answer

AWS Glue DataBrew. AWS Glue DataBrew (A) is correct because it is a visual data preparation tool that provides over 250 pre-built transformations and profiling features to detect data quality issues like missing values, duplicates, and outliers across mixed data types without writing code. Amazon SageMaker Data Wrangler (C) is correct because it offers a visual interface for data exploration, with built-in analysis templates (e.g., scatter plots, histograms, correlation matrices) and a Data Quality and Insights report that surfaces anomalies and target leakage on large datasets. Amazon Athena (D) is correct because it lets the scientist run ad-hoc SQL queries directly against data in Amazon S3, enabling aggregation, joins, and statistical summaries to explore relationships among numeric, categorical, and text columns at scale. AWS Data Pipeline (B) is not suitable because it is a workflow orchestration service for moving and transforming data on schedules, not an interactive exploration or profiling tool. Amazon Kinesis Data Analytics (E) is not suitable because it is designed for real-time stream processing with SQL or Apache Flink, not for exploratory analysis of a static 5-million-row dataset.

Answer

AWS Data Pipeline

Answer

Amazon Kinesis Data Analytics

Question 12

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. Option A, AWS Lambda with a container image, is correct because Lambda is a fully serverless compute service that can run inference code packaged as a container image (up to 10 GB) without managing servers, scaling automatically per request. Option B, Amazon SageMaker Serverless Inference, is correct because it is purpose-built to host trained models with automatic scaling and scale-to-zero, charging only for compute used during inference without provisioning instances. Option C, SageMaker batch transform, is not serverless inference for real-time requests; it is a batch job that provisions resources to process an entire dataset offline. Option D, ECS with Fargate, is serverless for containers but is not a model-serving inference service and requires managing task definitions and services. Option E, EC2 instances, requires provisioning and managing servers, so it is not serverless.

Answer

Amazon SageMaker batch transform

Answer

Amazon Elastic Container Service (ECS) with Fargate

Answer

Amazon EC2 instances

Question 13

A machine learning engineer is deploying a scikit-learn model to a SageMaker endpoint. The model requires a Python preprocessing function that transforms raw JSON input into a NumPy array before prediction. The engineer wants to minimize inference latency and avoid writing a custom Docker container. Which SageMaker feature should be used?

Accepted Answer

SageMaker Inference Pipeline. Inference Pipeline is the correct choice because it lets you deploy multiple containers behind a single endpoint, with the preprocessing container handling raw input and passing transformed data to the model container. This eliminates the need for a custom container while keeping latency low, as both steps execute within the same endpoint.

Answer

SageMaker Model Monitor

Answer

SageMaker Batch Transform

Answer

SageMaker Neo

Question 14

A company has deployed a real-time inference endpoint on Amazon SageMaker using a custom container. The endpoint receives a steady stream of requests but occasionally experiences spikes in traffic. The company wants to automatically scale the endpoint based on the number of invocations per instance to handle the load efficiently while minimizing costs. Which scaling policy should the company configure?

Accepted Answer

Target tracking scaling policy with a predefined metric of SageMakerVariantInvocationsPerInstance. The SageMakerVariantInvocationsPerInstance metric measures the average number of invocations per instance, directly indicating the load. A target tracking policy using this metric automatically adjusts instance count to maintain a specified target, handling traffic spikes efficiently. Other options either rely on less direct metrics or are not responsive to dynamic changes, making them less suitable for this use case.

Answer

Target tracking scaling policy with a custom metric of MemoryUtilization

Answer

Scheduled scaling policy to increase instances during peak hours

Answer

Step scaling policy based on the CPUUtilization metric

Question 15

A company operates a SageMaker real-time endpoint that serves a fraud-detection model. Compliance requires that predictions be explainable for individual transactions, and the data science team wants to detect when incoming feature distributions shift away from the training baseline. The team wants to use SageMaker built-in capabilities rather than custom code. Which two capabilities should they enable? (Choose two.)

Accepted Answer

SageMaker Clarify online explainability on the endpoint, configured with a baseline and a SHAP explainer, so each invocation can return feature attributions alongside the prediction.. Clarify online explainability produces SHAP-based attributions for individual real-time requests, meeting the explainability mandate, while Model Monitor data quality monitoring compares live request features to a training baseline and raises violations when distributions drift. Both are native SageMaker features configured through the SDK, so the team avoids writing custom drift or explanation code.

Answer

SageMaker Debugger with a built-in rule such as VanishingGradient, attached to the endpoint to capture tensors during inference and flag anomalous activation patterns.

Answer

SageMaker Batch Transform with a data capture configuration that stores every request and response in S3 for later offline analysis by the compliance team.

Answer

SageMaker Automatic Model Tuning with a hyperparameter tuning job that periodically retrains the model on recent transactions to keep the fraud-detection model aligned with current behavior.

Question 16

Which THREE factors should be considered when choosing between SageMaker built-in algorithms and custom algorithms? (Choose THREE.)

Accepted Answer

Custom algorithms allow you to implement any architecture, including proprietary ones. Option A is correct because custom algorithms in SageMaker give you full flexibility to implement any model architecture, including proprietary or novel designs, by packaging your own training and inference code in a Docker container. Option B is correct because SageMaker built-in algorithms are engineered and tuned by AWS for scalable, distributed training on large datasets, often leveraging GPU instances and parallelization out of the box. Option E is correct because built-in algorithms expose a fixed set of predefined hyperparameters, which may not cover every tuning need or match a specialized use case, making custom algorithms preferable when finer control is required. Option C is incorrect because built-in algorithms support multiple input formats beyond CSV and JSON, such as RecordIO-Protobuf and Parquet, depending on the algorithm. Option D is incorrect because SageMaker built-in algorithms do support popular frameworks like PyTorch and TensorFlow through separate framework containers, and custom algorithms do require bringing your own container, but the claim about built-in algorithms not supporting PyTorch is false.

Answer

Built-in algorithms can only be used with CSV and JSON formats

Answer

Custom algorithms require you to bring your own Docker container, but SageMaker built-in algorithms do not support frameworks like PyTorch

Question 17

A company is building a recommendation system for an e-commerce platform. The system needs to suggest products to users based on past purchases and browsing history. Which approach would be most appropriate for this use case?

Accepted Answer

Collaborative filtering using past user-item interactions. Collaborative filtering is the most appropriate approach because it leverages past user-item interactions (e.g., purchases, clicks) to identify patterns and recommend items that similar users have liked. This method directly captures user behavior and preferences without requiring explicit product metadata, making it ideal for e-commerce recommendation systems where implicit feedback is abundant.

Answer

Content-based filtering using product descriptions

Answer

K-means clustering of users based on demographics

Answer

Matrix factorization on user-item ratings

Question 18

A company wants to deploy a machine learning model that predicts customer churn. The model must provide interpretable predictions to explain why a customer is likely to churn. Which algorithm is most appropriate?

Accepted Answer

Decision tree. Decision trees are inherently interpretable because they produce a clear, rule-based structure that shows exactly which features and thresholds lead to a churn prediction. This white-box nature allows stakeholders to trace the reasoning for each prediction, meeting the requirement for interpretability without needing post-hoc explanation methods.

Answer

Gradient boosting machine

Answer

Support vector machine (SVM)

Answer

Deep neural network

Question 19

A company uses Amazon SageMaker to train a recommendation model. The training dataset grows daily and is stored in Amazon S3. The data science team wants to avoid re-downloading the entire dataset for each training job, so they configure SageMaker Pipe mode with an augmented manifest file. Which statement accurately describes how Pipe mode streams data to the training algorithm?

Accepted Answer

Pipe mode streams data directly from Amazon S3 to the training container without downloading the full dataset to the training instance's Amazon EBS volume.. Pipe mode streams data directly from Amazon S3 to the training container, bypassing the need to download the full dataset to the training instance's EBS volume. This reduces startup time and disk space requirements, making it suitable for large or frequently updated datasets. The other options confuse Pipe mode with File mode or misstate its memory and compatibility characteristics.

Answer

Pipe mode streams data from Amazon S3 but requires the training algorithm to read the entire dataset into memory before processing any records.

Answer

Pipe mode downloads the entire dataset to the training instance's Amazon EBS volume before training starts, then streams from local disk.

Answer

Pipe mode streams data from Amazon S3 only when the training job uses the SageMaker built-in algorithms; custom containers must use File mode.

Question 20

A company is using Amazon SageMaker to train machine learning models. The training data is stored in Amazon S3, but the data includes personally identifiable information (PII) that must be anonymized before training. What is the most efficient way to anonymize the data?

Accepted Answer

Use an AWS Glue ETL job to read from S3, apply anonymization, and write to another S3 bucket.. AWS Glue ETL jobs are purpose-built for serverless data transformation at scale, making them the most efficient choice for anonymizing PII in S3 before training. Glue can read directly from S3, apply built-in or custom anonymization transforms (e.g., masking, hashing) using PySpark or Scala, and write the cleaned data to a separate S3 bucket without provisioning any infrastructure. This approach decouples the data preparation from SageMaker, avoids unnecessary compute costs during training, and scales automatically with data volume.

Answer

Use Amazon Athena to query the data and apply anonymization functions.

Answer

Use Amazon Redshift Spectrum to query and anonymize data in S3.

Answer

Use a SageMaker Processing job to read from S3 and apply anonymization.