MLS-C01 Practice Test 38 — 15 Questions

Question 1

A data scientist uses Amazon SageMaker to train a model. The training dataset is 10 GB and stored in S3. The training job uses a ml.m5.large instance. The data must be available on the local file system during training. Which input mode should be used?

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

Accepted Answer

File input mode. File input mode is correct because it downloads the entire training dataset from S3 to the local file system of the ml.m5.large instance before training begins, ensuring the data is available locally as required. This mode is suitable for datasets up to 10 GB, as the instance's local storage (typically 8 GB for ml.m5.large) may be insufficient, but SageMaker uses the instance's Amazon EBS volume (up to 512 GB) for file input mode, making it viable.

Answer

Local input mode

Answer

Batch input mode

Answer

Pipe input mode

Question 2

A team is training a large language model using PyTorch on multiple GPUs. The training is taking too long due to inefficient data loading. Which AWS service can help accelerate data loading by caching data close to the GPU instances?

Accepted Answer

Amazon FSx for Lustre. Amazon FSx for Lustre is a high-performance file system optimized for machine learning workloads. It provides sub-millisecond latencies and high throughput by caching training data on local NVMe SSDs attached to the Lustre servers, which are co-located with GPU instances in the same AWS Availability Zone. This eliminates the I/O bottleneck from remote object storage, directly accelerating data loading for PyTorch DataLoader workers.

Answer

Amazon EBS Snapshots for fast restore

Answer

Amazon S3 Transfer Acceleration

Answer

Amazon CloudFront

Question 3

A company is deploying a machine learning model to production on Amazon SageMaker. The model requires low-latency inference (under 10 ms) for real-time predictions. The data scientist has trained a model using XGBoost and wants to minimize cost while meeting latency requirements. Which SageMaker hosting option should be used?

Accepted Answer

Use a real-time endpoint with a single model. A real-time endpoint with a single model is the correct choice because it provides dedicated, always-on compute resources that can consistently achieve sub-10 ms inference latency for XGBoost models. SageMaker real-time endpoints keep instances warm and route requests directly to the model container, minimizing cold-start delays and network overhead, which is essential for low-latency requirements.

Answer

Use a serverless inference endpoint

Answer

Use a real-time endpoint with multi-model hosting

Answer

Use a batch transform job

Answer

Use an asynchronous inference endpoint

Question 4

A data scientist is troubleshooting access to an S3 bucket. The following IAM policy is attached to their role. What is the likely result when they try to list objects in the 'confidential' folder?

```json
{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Effect": "Allow",
      "Action": "s3:ListBucket",
      "Resource": "arn:aws:s3:::example-bucket"
    },
    {
      "Effect": "Deny",
      "Action": "s3:*",
      "Resource": "arn:aws:s3:::example-bucket/confidential/*",
      "Condition": {
        "StringNotEquals": {
          "aws:SourceVpce": "vpce-12345678"
        }
      }
    }
  ]
}
```

Accepted Answer

Access is denied if the request does not originate from the specified VPC endpoint.. The Deny statement explicitly denies s3:* actions on the `confidential` folder unless the request originates from the specified VPC endpoint (using the `aws:SourceVpce` condition). If the request does not come from that VPC endpoint, it will be denied. Option A is wrong because the Deny overrides the Allow. Option B is wrong because the Deny is conditional, not unconditional. Option C is wrong because the condition is about the VPC endpoint, not the use of HTTPS.

Answer

Access is allowed because the Allow statement grants s3:ListBucket.

Answer

Access is denied unconditionally.

Answer

Access is allowed only if the request uses HTTPS.

Question 5

A data scientist is using SageMaker to train a model. The training job is failing with a 'ResourceLimitExceeded' error. Which action should be taken to resolve this issue?

Accepted Answer

Request a service limit increase for the instance type.. The 'ResourceLimitExceeded' error in SageMaker indicates that the AWS account has reached the maximum number of allowed resources (e.g., instances, vCPUs, or storage) for a given instance type in the current region. Requesting a service limit increase via the AWS Service Quotas console or API directly resolves this by raising the cap for that specific instance type, allowing the training job to proceed.

Answer

Use a different AWS Region.

Answer

Reduce the training dataset size.

Answer

Switch to a different instance type with lower resource requirements.

Question 6

A company is using Amazon Kinesis Data Analytics for Apache Flink to process real-time sensor data. The application reads from a Kinesis data stream, performs windowed aggregations, and writes results to an S3 bucket. Recently, the application has been experiencing high latency and checkpoint failures. What is the MOST likely cause?

Accepted Answer

The S3 destination bucket is located in a different AWS Region than the Kinesis application. The S3 destination bucket is located in a different AWS Region than the Kinesis application. Cross-region data transfer introduces network latency and increases the likelihood of checkpoint failures because Apache Flink checkpoints require writes to complete within a timeout. Option A (insufficient shards) would cause throttling (ProvisionedThroughputExceededException) but not directly checkpoint failures. Option C (record size > 1 MB) is impossible because Kinesis Data Streams enforces a 1 MB maximum record size. Option D (low parallelism) could cause backpressure but not typically checkpoint failures unless resources are severely constrained. Therefore, the most likely cause is the cross-region S3 bucket.

Answer

The number of shards in the Kinesis stream is insufficient for the data volume

Answer

The record size in the Kinesis stream exceeds the 1 MB limit

Answer

The parallelism of the Flink application is set too low for the number of shards

Question 7

A data scientist is working with a dataset containing 10,000 observations and 100 features. The scientist wants to detect outliers in the dataset. Which method is most appropriate for outlier detection in a high-dimensional space?

Accepted Answer

Use Isolation Forest. Isolation Forest is the most appropriate method for outlier detection in high-dimensional space because it isolates anomalies by randomly splitting features, making it effective for high-dimensional data without assuming any underlying distribution. Option A is wrong because Z-score assumes normality and is univariate, unsuitable for high-dimensional data. Option C is wrong because Mahalanobis distance assumes multivariate normality and can be computationally expensive and sensitive to high dimensionality. Option D is wrong because IQR is univariate and does not capture interactions between features in high-dimensional spaces.

Answer

Use Z-score to identify points beyond 3 standard deviations

Answer

Use Mahalanobis distance

Answer

Use interquartile range (IQR) for each feature

Question 8

A company is using Amazon Kinesis Data Firehose to load streaming data into an S3 bucket. The data schema evolves over time, with new columns added. The data must be queryable using Amazon Athena. What is the BEST way to handle schema changes?

Accepted Answer

Use AWS Glue Crawlers to automatically detect schema changes and update the table metadata. AWS Glue Crawlers can automatically detect schema changes in the data stored in S3 and update the AWS Glue Data Catalog metadata used by Athena. This allows Athena to query the evolving schema without manual intervention. Option A (manual update) is not the best because it requires manual effort and is error-prone. Option B (converting to JSON) is not necessary; Athena can handle various formats including Parquet, ORC, etc., and schema evolution is better handled by Glue Crawlers. Option D (recreating the table daily) is disruptive and not the best practice.

Answer

Manually update the Athena table definition each time a new column is added

Answer

Configure Firehose to convert the data to Apache JSON format

Answer

Recreate the Athena table daily to pick up new columns

Question 9

A company is using Amazon Kinesis Data Streams with 10 shards to ingest clickstream data. Each record is approximately 50 KB. The data is consumed by a Lambda function that writes to DynamoDB. The Lambda function is experiencing throttling errors. Which TWO actions should the data engineer take to resolve the issue? (Choose TWO.)

Accepted Answer

Request a limit increase for the Lambda function's concurrent execution limit. The Lambda function is experiencing throttling errors because it is being invoked too frequently. To resolve this, the data engineer should increase the Lambda function's concurrent execution limit (option C) to allow more simultaneous executions, and increase the batch size in the Lambda event source mapping (option E) to process more records per invocation, reducing the number of invocations. Option A (increase record size) is irrelevant as it would increase data volume. Option B (switch to Kinesis Data Firehose) changes the architecture and does not directly address Lambda throttling. Option D (increase the number of shards) would increase throughput but also potentially increase concurrency without solving the throttling issue. Therefore, the correct answers are C and E.

Answer

Increase the record size to 1 MB to reduce the number of records

Answer

Switch to Kinesis Data Firehose instead of Data Streams

Answer

Increase the number of shards in the Kinesis stream

Question 10

A company stores IoT sensor data in Amazon S3 and uses Amazon Athena for ad-hoc queries. The data is partitioned by date, but queries are still slow and expensive. Which TWO actions can improve query performance and reduce cost? (Choose TWO.)

Accepted Answer

Use S3 lifecycle policies to compact small files into larger ones. Compacts small files into larger ones, reducing the number of objects and minimizing metadata overhead, which improves query performance. Option B converts data from CSV to Parquet, a columnar format that reduces the amount of data scanned by Athena, lowering cost and speeding up queries. Option C (disabling encryption) does not affect performance and is not recommended. Option D (using Glue) is a different service and not a direct improvement for Athena queries. Option E (increasing partitions to hour-level) can create many small files, degrading performance.

Answer

Disable server-side encryption on the S3 bucket

Answer

Use AWS Glue instead of Athena for querying

Answer

Increase the number of partitions to hour-level granularity

Question 11

A data engineer is designing a data pipeline that uses Amazon Kinesis Data Streams to ingest real-time transaction data. The data must be processed in near real-time and stored in Amazon S3 for long-term analytics. The engineer wants to ensure data durability and exactly-once processing semantics. Which TWO actions should the engineer take? (Choose two.)

Accepted Answer

Use AWS Glue streaming ETL with checkpointing.. Correct options: B and D. AWS Glue streaming ETL with checkpointing provides exactly-once processing semantics when writing to S3 using a transactional format like Delta Lake. Setting RetryAttempts to 0 on a Lambda event source mapping ensures that each record is processed only once (no retries), which avoids duplicate processing, though failures may cause data loss. Options A and C do not guarantee exactly-once: KPL provides at-least-once with deduplication, and Kinesis Data Firehose provides at-least-once delivery to S3. Option E (Amazon SQS) is not part of the Kinesis pipeline and does not ensure exactly-once semantics.

Answer

Use the Kinesis Producer Library (KPL) with exactly-once delivery.

Answer

Enable exactly-once delivery on Kinesis Data Firehose.

Answer

Use Amazon SQS as the event source for downstream processing.

Question 12

A team is analyzing a dataset with many categorical features. They notice that one feature has 1,000 unique values but a long tail where most values appear only once. Which encoding method is most appropriate to avoid overfitting?

Accepted Answer

Count encoding. Count encoding uses the frequency of each category as its encoded value, which captures information for rare categories without increasing dimensionality. One-hot encoding (C) would create 1,000 columns, leading to high dimensionality and potential overfitting. Target encoding (A) uses the target variable mean, which can cause overfitting especially with rare categories. Label encoding (B) imposes an arbitrary ordinal relationship, which is inappropriate for nominal categorical features.

Answer

Target encoding

Answer

Label encoding

Answer

One-hot encoding

Question 13

A data engineer needs to design a data ingestion pipeline that ingests data from a MySQL database hosted on-premises into Amazon S3 for analytics. The pipeline must capture change data (CDC) and run continuously with low latency. Which two services should the data engineer use?

Accepted Answer

AWS Database Migration Service (DMS) with ongoing replication.. AWS Database Migration Service (DMS) with ongoing replication can continuously capture changes from on-premises MySQL using Change Data Capture (CDC). Amazon S3 can be configured as the target endpoint for DMS, allowing the CDC data to be written directly to S3 with low latency. Option C (Amazon AppFlow) is designed for SaaS applications, not on-premises databases. Option D (AWS Glue ETL) is batch-oriented and not suitable for low-latency continuous ingestion. Option E (Amazon Kinesis Data Streams) is not required because DMS can directly write to S3.

Answer

Amazon AppFlow.

Answer

AWS Glue ETL jobs scheduled at regular intervals.

Answer

Amazon Kinesis Data Streams.

Question 14

A company uses Amazon Kinesis Data Streams to ingest clickstream data from a website. The data is consumed by a custom application that runs on Amazon EC2 instances. The company notices that the consumer application is falling behind the producer, causing data to be throttled. Which action should the company take to improve the consumer's throughput?

Accepted Answer

Increase the number of shards in the Kinesis data stream. Increasing the number of shards increases the stream's read capacity, allowing more consumers to read in parallel and improving throughput. Option A is wrong because reducing the data retention period does not increase read throughput; it only affects how long data is stored. Option C is wrong because Lambda concurrency is applicable only to Lambda functions, not to the custom EC2 application consuming the stream. Option D is wrong because Amazon Kinesis Data Firehose is a different service for delivering streaming data to destinations like S3, and it does not improve the throughput of the existing EC2 consumer.

Answer

Reduce the data retention period of the stream

Answer

Increase the maximum concurrency of the AWS Lambda function that processes the stream

Answer

Use Amazon Kinesis Data Firehose to deliver data to Amazon S3

Question 15

A data scientist is performing EDA on a dataset with a timestamp column. They want to detect seasonality. Which visualization is most appropriate?

Accepted Answer

Line plot of value over time. A line plot of value over time directly visualizes the temporal trend, making seasonal patterns (e.g., repeating cycles) easily identifiable. Option A (box plot of value grouped by month) shows the distribution per month but does not reveal the sequential order or cyclical pattern. Option B (bar chart of average value per month) averages out within-month variations and may obscure seasonality that occurs at finer granularity. Option D (scatter plot of timestamp vs. value) can become cluttered with many points and does not connect observations in time, making it harder to detect seasonality.

Answer

Box plot of value grouped by month

Answer

Bar chart of average value per month

Answer

Scatter plot of timestamp vs. value