MLS-C01 Practice Exam 55 — 20 Questions

Question 1

Refer to the exhibit. An IAM policy is attached to a data engineering role. The role is used by an AWS Glue ETL job that reads from 'raw/' and writes to 'processed/'. The job fails with an access denied error when trying to write to 'processed/'. What is the likely cause?

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

Accepted Answer

The Deny statement on s3:DeleteObject prevents overwriting objects.. The Deny statement on s3:DeleteObject explicitly denies the permission required to overwrite an existing object in S3. When an AWS Glue job writes to 'processed/' and attempts to overwrite an existing object, S3 requires both s3:PutObject and s3:DeleteObject permissions (since overwrite involves delete then put). The Deny on DeleteObject causes the access denied error. Option B is incorrect because the role is presumed to be attached correctly per the scenario. Option C is incorrect because the policy allows both GetObject and PutObject on the same resource, as is typical. Option D is incorrect because the ARN for the 'processed' folder is correctly specified; the error is due to the Deny, not incorrect ARN.

Answer

The role is not correctly attached to the Glue job.

Answer

The policy does not allow both s3:GetObject and s3:PutObject on the same resource.

Answer

The policy specifies incorrect ARN for the 'processed' folder.

Question 2

A large e-commerce company is using Amazon DynamoDB as the source for real-time analytics. The data is streamed to Amazon Kinesis Data Streams using DynamoDB Streams and then processed by an AWS Lambda function. The Lambda function writes the data to an Amazon Elasticsearch Service cluster for search and visualization. Recently, the Lambda function has been failing with throttling errors from the Elasticsearch cluster. What is the MOST effective way to handle this?

Accepted Answer

Configure a Dead Letter Queue (DLQ) on the Lambda function to capture failed records and implement retry logic.. Using a Dead Letter Queue (DLQ) allows the Lambda function to capture records that fail due to Elasticsearch throttling, so they can be retried later without blocking the function's processing of other records. This prevents data loss and handles backpressure effectively. Option A is incorrect because increasing Lambda concurrency would increase the rate of writes to the Elasticsearch cluster, worsening the throttling. Option B is incorrect because increasing Kinesis shards would increase the throughput of data arriving at the Lambda function, again exacerbating the throttling. Option C is incorrect because decreasing the Kinesis retention period does not reduce the data volume; it only changes how long data is stored in the stream, and it would not solve the throttling issue.

Answer

Increase the Lambda function's reserved concurrency to handle more invocations.

Answer

Increase the number of shards in the Kinesis data stream.

Answer

Decrease the Kinesis stream's retention period to reduce the data volume.

Question 3

A data scientist is using Amazon SageMaker to train a linear regression model. The training job fails with the error: 'AlgorithmError: Input data has NaN values'. Which step should the data scientist take to resolve this issue?

Accepted Answer

Impute missing values or remove rows with NaN values. The error 'AlgorithmError: Input data has NaN values' indicates missing values in the dataset. Linear regression cannot handle NaN values. The appropriate action is to either impute missing values (e.g., using mean/median) or remove rows with NaN values. Option A (convert to sparse format) is used for handling zero values, not missing values, and will not resolve NaN errors. Option B (switch to a different algorithm) is unnecessary because data preprocessing can fix the issue; moreover, many algorithms also cannot handle NaN. Option C is correct. Option D (increase training instances) only adds more compute resources and does not fix data quality issues.

Answer

Convert the data to a sparse format

Answer

Switch to a different algorithm that handles missing values

Answer

Increase the number of training instances

Question 4

A machine learning engineer is training a model using Amazon SageMaker. The training data is stored in S3 and is 10 TB. The engineer wants to use Pipe input mode to stream data from S3. Which algorithms support Pipe mode? (Select all that apply)

Accepted Answer

Amazon SageMaker Linear Learner. Amazon SageMaker's built-in algorithms, including Linear Learner, K-Means, XGBoost, and PCA, all support Pipe mode for streaming training data from S3. Therefore, all the listed options (A, B, C, D) are correct.

Question 5

A data scientist has a dataset with 500 features and wants to reduce dimensionality for visualization. Which technique is most appropriate for identifying the two components that capture the most variance?

Accepted Answer

Principal Component Analysis (PCA). Principal Component Analysis (PCA) is a linear dimensionality reduction technique that finds the directions (principal components) of maximum variance in the data, making it ideal for identifying the two components that capture the most variance for visualization. Option A is incorrect because t-SNE is a non-linear technique focused on preserving local neighborhood structure, not on maximizing global variance. Option B is incorrect because Linear Discriminant Analysis (LDA) is a supervised method that requires class labels to separate classes, not to maximize variance. Option D is incorrect because K-means clustering is an unsupervised algorithm for grouping data points, not a dimensionality reduction method.

Answer

t-Distributed Stochastic Neighbor Embedding (t-SNE)

Answer

Linear Discriminant Analysis (LDA)

Answer

K-means clustering

Question 6

A data engineer is investigating why an Athena query against the my-data-lake bucket is slow. The query filters on year, month, and day. The exhibit shows the metadata of one Parquet file. What is the MOST likely cause of the slow query?

Accepted Answer

The file is too large, causing Athena to process it in a single task. The Parquet file is 1 GB in size, which is too large for efficient processing in Athena. Athena splits data into tasks for parallel execution, but a single large file cannot be split, causing the query to run slowly. Partitioning on year, month, and day is already applied and is not the issue. The other options are incorrect: version ID null is irrelevant, the query does use partition columns, and standard storage is faster than Glacier.

Answer

The version ID is null, causing data inconsistency

Answer

The partition columns are not being used in the query

Answer

The storage class is STANDARD, which is slower than GLACIER

Question 7

Refer to the exhibit. A data engineer is troubleshooting an AWS Glue job that fails with an 'AccessDenied' error when trying to write to the S3 bucket 'my-data-lake'. The IAM policy attached to the Glue service role is shown. What is the missing permission?

Accepted Answer

s3:ListBucket. The policy allows s3:GetObject and s3:PutObject on the bucket's objects, but it does not allow s3:ListBucket on the bucket itself. Many Glue operations require ListBucket to discover objects. Option A (s3:ListBucket) is the missing permission. Option B (s3:PutObjectAcl) is not needed. Option C (s3:GetBucketLocation) is not required. Option D (s3:DeleteObject) is not needed.

Answer

s3:PutObjectAcl

Answer

s3:GetBucketLocation

Answer

s3:DeleteObject

Question 8

A company uses Amazon Kinesis Data Streams to ingest clickstream data. The stream has 8 shards. A Lambda function processes each record and writes to Amazon DynamoDB. The Lambda function sometimes fails due to DynamoDB write throttling, causing duplicate processing of records after retries. The data engineering team needs to ensure exactly-once processing semantics for the DynamoDB writes. What should the team do?

Accepted Answer

Use DynamoDB conditional writes with the Kinesis sequence number as a unique attribute to make writes idempotent.. Using DynamoDB conditional writes with the Kinesis sequence number as a unique attribute ensures idempotency. When processing a record, the Lambda function can attempt a conditional write that only succeeds if an item with that sequence number does not already exist. If the write fails due to a condition check, it means the record was already processed, so the function can skip it. This achieves exactly-once semantics even if the same record is delivered multiple times due to retries. Option A is incorrect because an SQS FIFO queue between Kinesis and Lambda would add latency and complexity; Kinesis already provides ordering and at-least-once delivery, and using a FIFO queue does not guarantee that the Lambda function will not process the same record multiple times within its retry logic. Option B is incorrect because setting maximum retry count to 0 with a DLQ simply discards failed records after the first failure, which does not provide exactly-once processing; it results in at-most-once semantics and potential data loss. Option C is incorrect because increasing DynamoDB write capacity may reduce throttling but does not eliminate duplicate processing; the same record can still be retried and written multiple times if the function retries, leading to duplicate writes.

Answer

Use an Amazon SQS FIFO queue between Kinesis and Lambda to deduplicate records.

Answer

Configure the Lambda event source mapping with a maximum retry count of 0 and a DLQ.

Answer

Increase the DynamoDB write capacity units to avoid throttling.

Question 9

A data scientist is exploring a dataset with 1,000 features and only 200 samples. The goal is to build a binary classifier. Which technique should be used first during exploratory data analysis to reduce dimensionality and avoid overfitting?

Accepted Answer

Use principal component analysis (PCA) to reduce dimensions.. PCA is an unsupervised dimensionality reduction technique that is well-suited for high-dimensional datasets with few samples, as it reduces features while retaining variance and helps avoid overfitting. Option A is wrong because pairwise correlation only captures linear relationships and may miss interactions, and removing correlated features may not be sufficient for high dimensionality. Option B is wrong because L1 regularization (Lasso) is a model-based feature selection method applied during training, not during initial exploratory data analysis (EDA). Option C is wrong because t-SNE is a visualization technique for reducing dimensions to 2 or 3 for plotting, but it is not suitable for generating features for modeling and can be unstable with few samples.

Answer

Compute pairwise correlations and remove highly correlated features.

Answer

Apply L1 regularization (Lasso) to select features.

Answer

Use t-SNE to visualize clusters and reduce dimensions.

Question 10

A machine learning engineer is deploying a model using Amazon SageMaker. The model is a PyTorch model that performs real-time inference with low latency requirements. The engineer wants to use automatic scaling based on the number of concurrent requests. Which SageMaker feature should be used to achieve this?

Accepted Answer

Use Amazon SageMaker automatic scaling with a target tracking scaling policy.. Amazon SageMaker automatic scaling with a target tracking scaling policy is the correct feature because it allows the endpoint to dynamically adjust the number of instances based on a predefined metric, such as the number of concurrent requests (e.g., using the SageMakerVariantInvocationsPerInstance metric). This directly meets the requirement for automatic scaling based on concurrent requests while maintaining low latency for real-time PyTorch inference.

Answer

Create an AWS Auto Scaling group for the SageMaker endpoint.

Answer

Enable Elastic Load Balancing for the endpoint.

Answer

Deploy the model behind Amazon API Gateway with a Lambda function.

Question 11

A data scientist wants to build a binary classifier to predict customer churn. The dataset has 10,000 records with 500 churners (5%). Which technique should the data scientist use to address class imbalance?

Accepted Answer

Use SMOTE (Synthetic Minority Over-sampling Technique) to create synthetic samples.. SMOTE (Synthetic Minority Over-sampling Technique) creates synthetic samples for the minority class, effectively balancing the dataset without losing information. Option A (Randomly undersampling the majority class) discards potentially useful data. Option C (Assigning higher class weights to the minority class) is a valid approach but not a data-level technique; it adjusts the loss function. Option D (Downsampling the majority class) also loses data and is similar to undersampling.

Answer

Randomly undersample the majority class.

Answer

Assign higher class weights to the minority class.

Answer

Downsample the majority class to match the minority class size.

Question 12

Which THREE techniques can help reduce overfitting in a neural network? (Select THREE.)

Accepted Answer

Dropout. Dropout is correct because it randomly deactivates a fraction of neurons during training, forcing the network to learn redundant representations and preventing co-adaptation of features. This reduces overfitting by acting as an ensemble method without increasing computational cost at inference time.

Answer

Increase training epochs

Answer

Increase the number of layers

Question 13

A company uses Amazon SageMaker to train a linear regression model. After training, the model shows high bias on the training set. Which action is MOST likely to reduce bias?

Accepted Answer

Add more features. High bias indicates that the model is underfitting the training data, meaning it is too simple to capture the underlying patterns. Adding more features increases the model's capacity to learn complex relationships, directly addressing underfitting by reducing bias. In SageMaker, this can be done by engineering additional input columns or using feature transformations before training.

Answer

Collect more training data

Answer

Apply L2 regularization

Answer

Deploy the model to a larger instance

Question 14

A company is using AWS Glue to catalog data stored in Amazon S3. The data is partitioned by year, month, day, and hour. The company runs hourly ETL jobs that add new partitions. The Glue crawler is scheduled to run every hour to update the Data Catalog. However, the crawler is taking longer than expected and is not completing before the next crawler run starts. Which action could the company take to resolve this issue?

Accepted Answer

Use multiple crawlers, each configured to crawl a different path (e.g., one for year=2023, one for year=2024). Using multiple crawlers to crawl different paths allows parallel processing of partitions, reducing crawler time. Option A is incorrect because the 'Schema updates' option does not increase throughput. Option B is incorrect because partition indexing speeds up queries, not the crawler itself. Option C is incorrect because reducing frequency does not speed up the crawler. Option E is incorrect because AWS Glue does not have a 'Crawler queue' feature; to increase parallelism, you would increase DPUs.

Answer

Increase the throughput of the crawler by configuring the 'Schema updates' option

Answer

Enable partition indexing on the table to speed up the crawler

Answer

Decrease the crawler schedule frequency to every 2 hours to avoid overlapping runs

Answer

Increase the number of crawler instances by configuring the 'Crawler queue' to process multiple partitions in parallel

Question 15

A company uses Amazon Kinesis Data Streams to collect IoT sensor data. The stream has 4 shards. A consumer application reads from the stream using the Kinesis Client Library (KCL). The application processes records and stores them in Amazon DynamoDB. Recently, the data volume has increased, and the consumer is falling behind. Which action should the team take to increase the processing throughput?

Accepted Answer

Increase the number of shards in the Kinesis stream.. Increase the number of shards in the Kinesis stream. Kinesis Data Streams throughput is determined by the number of shards; each shard provides 1 MB/s or 1000 records/s for reading. Since the consumer is falling behind, increasing shards directly increases the read throughput. Option A is incorrect because adding more consumer instances without increasing shards will not improve throughput; KCL ensures each shard is processed by one worker, so extra workers are idle. Option B is incorrect because increasing DynamoDB write capacity may reduce throttling but does not address the root cause of low read throughput from Kinesis. Option C is incorrect because increasing the data retention period does not affect the rate at which data can be read.

Answer

Deploy additional consumer instances using the same application name.

Answer

Increase the write capacity of the DynamoDB table.

Answer

Increase the data retention period of the stream to 7 days.

Question 16

A Lambda function is triggered by S3 events. The event payload shown in the exhibit is received by the Lambda function. The function is supposed to process the CSV file and load it into DynamoDB. However, the function fails because it cannot read the file. What is the MOST likely cause?

Accepted Answer

The Lambda function's IAM role does not have s3:GetObject permission. The Lambda function cannot read the file from S3 because its IAM role does not have the s3:GetObject permission. Option A is wrong because the failure is not due to DynamoDB write permissions; the function fails before writing. Option C is wrong because the S3 bucket exists, as indicated by the event triggering. Option D is wrong because the event notification is correctly configured to trigger the Lambda function, as evidenced by the function receiving the event.

Answer

The Lambda function lacks DynamoDB write permissions

Answer

The S3 bucket does not exist

Answer

The S3 event notification is misconfigured

Question 17

A machine learning team is preparing a dataset for model training. The data is stored in an Amazon S3 bucket with objects that are each approximately 100 MB in size. The team wants to use Amazon SageMaker for training. To optimize training performance, which data format and storage configuration should be used?

Accepted Answer

Store data as RecordIO-Protobuf files and use SageMaker Pipe input mode. RecordIO-Protobuf is the optimal format for SageMaker because it stores data in a binary, sharded structure that allows for efficient random access and parallel I/O. Pipe input mode streams data directly from S3 to the training algorithm, eliminating disk writes and reducing startup latency, which is critical for large datasets with 100 MB objects.

Answer

Store data as RecordIO-Protobuf files and use SageMaker File input mode

Answer

Store data as CSV files and use SageMaker Pipe input mode

Answer

Store data as CSV files and use SageMaker File input mode

Question 18

A machine learning engineer is deploying a model to SageMaker for real-time inference. The model is a TensorFlow SavedModel. Which SageMaker capability should be used to create an endpoint?

Accepted Answer

SageMaker hosting with TensorFlow Serving container. SageMaker provides managed TensorFlow serving containers for deploying TensorFlow SavedModels to real-time endpoints. Option B is wrong because SageMaker Pipelines is used for building and managing ML workflows, not for deploying models to endpoints. Option C is wrong because SageMaker Model Monitor is used for monitoring model quality and drift, not for deployment. Option D is wrong because SageMaker Ground Truth is used for labeling data, not for hosting models.

Answer

SageMaker Pipelines

Answer

SageMaker Model Monitor

Answer

SageMaker Ground Truth

Question 19

A data engineer needs to load data from a MySQL database to Amazon S3 daily. The database is 500 GB and the load window is 2 hours. The data must be extracted without impacting the source database performance. Which AWS service should be used to perform the extraction?

Accepted Answer

AWS Database Migration Service (AWS DMS) with a full-load task to S3.. (AWS Database Migration Service). AWS DMS is specifically designed for migrating databases to AWS with minimal impact on the source. It can perform a full-load task to extract data from MySQL and write it to S3 efficiently within the 2-hour window. Option A (AWS Glue ETL) uses JDBC and can cause higher overhead on the source, potentially impacting performance. Option C (Amazon Athena with MySQL federated query) is a query service, not an extraction tool, and may not handle 500 GB efficiently. Option D (Amazon EMR with Spark) is for big data processing and incurs overhead for setup and coordination, making it less suitable for direct daily extraction without impact.

Answer

AWS Glue ETL job using a JDBC connection to read the full table.

Answer

Amazon Athena with the MySQL federated query connector.

Answer

Amazon EMR with a Spark job reading from MySQL via JDBC.

Question 20

Refer to the exhibit. A data engineer has deployed this CloudFormation template. The Glue job 'my-etl-job' reads from the S3 bucket 'my-data-lake-bucket' and writes transformed data to another bucket. After 30 days, the data engineer notices that the Glue job fails with 'Input data not found' errors. What is the most likely cause?

Accepted Answer

The lifecycle configuration deletes objects from the bucket after 30 days, removing the input data.. The lifecycle configuration on the S3 bucket 'my-data-lake-bucket' is set to delete objects after 30 days. Since the Glue job 'my-etl-job' reads input data from this bucket, once the 30-day period elapses, the input data is removed, causing the 'Input data not found' error. This matches the symptom of the job failing after exactly 30 days.

Answer

The temporary directory 'my-temp-dir' is being cleaned up by the lifecycle configuration.

Answer

The script location 's3://my-scripts/etl.py' is being deleted by the lifecycle rule.

Answer

The job bookmark option 'job-bookmark-enable' is causing the job to skip newly arriving data.