MLS-C01 Practice Exam 56 — 20 Questions

Question 1

A company runs an e-commerce platform that generates clickstream data in real-time. The data is ingested into Amazon Kinesis Data Streams (100 shards) and processed by AWS Lambda functions, which aggregate data in 1-minute windows and write the results to Amazon S3. The Lambda functions are triggered by the Kinesis stream using the event source mapping. Recently, the company noticed that some records are being processed multiple times, leading to duplicate data in S3. The Lambda function is idempotent, but the duplicates are causing downstream issues. The Lambda function's concurrency limit is 1000, and the batch size is 100. The average processing time per record is 200 ms. What is the most likely cause of the duplicates, and how should it be fixed?

Accepted Answer

Ensure the Lambda function is idempotent and uses the sequence number to deduplicate records.. Option B is correct. Lambda functions process records from Kinesis in batches. If the function fails (e.g., due to timeout or error), the entire batch is retried, causing duplicates if some records were already partially processed. To avoid duplicates, the function should be idempotent and should not commit partial results. Option A is wrong because the concurrency is sufficient. Option C is wrong because increasing batch size increases the risk of partial failure. Option D is wrong because a FIFO queue does not integrate with Kinesis.

Answer

Increase the Lambda concurrency limit to 2000 to handle the load.

Answer

Decrease the batch size to 10 to reduce the impact of failures.

Answer

Use Amazon SQS FIFO queue as a buffer between Kinesis and Lambda to guarantee exactly-once processing.

Question 2

A company uses AWS Glue to run ETL jobs that transform data from Amazon S3 to Amazon Redshift. The Glue job writes data to Redshift using the JDBC connection. Recently, the job has been failing with connection timeout errors when writing to Redshift. The Redshift cluster is a 2-node dc2.large cluster. The Glue job processes about 50 GB of data per run. The errors occur sporadically, and the job succeeds after a few retries. The data engineer needs to resolve the issue to prevent job failures. What should the engineer do?

Accepted Answer

Modify the Glue job to write data to S3 first, then use the Redshift COPY command to load data.. Option C is correct. The Glue JDBC driver may not handle large data volumes efficiently; using the COPY command via S3 is optimized for bulk loads and is more reliable. Option A is wrong because increasing timeout may mask the issue but not resolve it. Option B is wrong because the Redshift cluster may be undersized, but the issue is likely the JDBC driver. Option D is wrong because AWS DMS is for database migration, not ETL jobs.

Answer

Increase the Redshift cluster size to 4 nodes.

Answer

Increase the Glue job timeout to 24 hours.

Answer

Use AWS Database Migration Service (DMS) to load data into Redshift.

Question 3

A data engineer is building a data pipeline that ingests streaming data from Amazon Kinesis Data Streams, transforms the data using AWS Lambda, and stores the results in Amazon S3. The engineer needs to ensure that each record is processed exactly once and in order. Which TWO approaches should the engineer consider? (Choose TWO.)

Accepted Answer

Configure the Lambda function with a reserved concurrency of 1 and a batch size of 1 to process records sequentially.. Option A is correct because Kinesis Data Streams supports exactly-once processing within a shard using the sequence number. Option E is correct because AWS Lambda can be configured with a reserved concurrency of 1 and a batch size of 1 to process records in order. Option B is incorrect because S3 does not provide ordering guarantees. Option C is incorrect because Kinesis Data Firehose does not guarantee exactly-once delivery. Option D is incorrect because SQS FIFO does not integrate directly with Kinesis.

Answer

Use Amazon SQS FIFO queues to decouple Kinesis and Lambda, ensuring ordering and exactly-once delivery.

Answer

Enable S3 Event Notifications to trigger Lambda for each object.

Answer

Use Kinesis Data Firehose to buffer and deliver data to S3, then use Lambda to process.

Question 4

An ML team is deploying a model to a SageMaker endpoint for real-time inference. The model is large (2 GB) and requires GPU for low-latency inference. The team wants to minimize cost while maintaining a response time of under 200 ms. Which instance configuration and SageMaker feature would be best?

Accepted Answer

Use a GPU instance (ml.p3.2xlarge) with SageMaker Elastic Inference.. Option B is correct because using a GPU instance (ml.p3.2xlarge) with SageMaker's Elastic Inference attaches a fraction of GPU acceleration to a CPU instance, balancing cost and performance. Option A is wrong because serverless inference may not support GPU and has cold starts. Option C is wrong because multi-model endpoints are for hosting multiple models on the same instance, not primarily for latency. Option D is wrong because batch transforms are for offline inference.

Answer

Use a batch transform job on GPU instances.

Answer

Use a serverless inference endpoint with a CPU instance.

Answer

Use a multi-model endpoint on a GPU instance.

Question 5

A data scientist is training a model using Amazon SageMaker and wants to track hyperparameter tuning jobs, training jobs, and model metrics. The team also needs to compare experiments visually. Which AWS service should be used?

Accepted Answer

Amazon SageMaker Experiments. Option C is correct because SageMaker Experiments is purpose-built for tracking and comparing ML experiments. Option A is wrong because AWS Glue is for ETL, not experiment tracking. Option B is wrong because CloudWatch Logs stores logs but does not provide experiment comparison. Option D is wrong because Step Functions is for workflow orchestration.

Answer

Amazon CloudWatch Logs

Answer

AWS Glue DataBrew

Answer

AWS Step Functions

Question 6

A company is using Amazon SageMaker to train a model. The training data is stored in an S3 bucket in a different AWS account. Which IAM policy configuration is required to allow SageMaker to access the data?

Accepted Answer

Add a bucket policy allowing access from the SageMaker execution role ARN, and ensure the SageMaker execution role has an IAM policy allowing s3:GetObject on the bucket.. Option B is correct because cross-account access requires the SageMaker execution role to have an IAM policy allowing access to the S3 bucket, and the S3 bucket policy must grant access to that role. Option A is wrong because SageMaker cannot assume a role in another account without proper trust policy. Option C is wrong because the data owner's role cannot be used directly. Option D is wrong because SageMaker does not use the data owner's IAM user credentials.

Answer

Add a bucket policy that allows s3:GetObject for the SageMaker execution role's ARN.

Answer

Create an IAM user in the data owner's account and use its credentials in SageMaker.

Answer

Use the data owner's IAM role as the SageMaker execution role.

Question 7

A data scientist is using Amazon SageMaker to train a model. The training job uses a custom Docker image stored in Amazon ECR. The training job fails with an error 'CannotPullContainerError'. Which TWO actions should the data scientist take to resolve this issue? (Choose TWO.)

Accepted Answer

Confirm that the image tag exists in the ECR repository. Options B and D are correct because checking ECR permissions and verifying the image tag are common causes. Option A is unrelated to pulling. Option C might be needed but not directly. Option E is irrelevant to the error.

Answer

Use a public Docker image instead of a custom one

Answer

Increase the training job timeout

Answer

Ensure the training instance has internet access

Question 8

A data scientist is analyzing a dataset with 500 features and 10,000 samples. After running a correlation matrix, they find that many feature pairs have correlation >0.95. What is the most appropriate next step to improve model performance?

Accepted Answer

Apply principal component analysis (PCA) to reduce dimensionality.. Option A is correct because high correlation indicates multicollinearity, which can be addressed by dimensionality reduction techniques like PCA. Option B is wrong because adding more data does not fix multicollinearity. Option C is wrong because removing all correlated features may discard useful information. Option D is wrong because increasing regularization can help but is not the most appropriate first step for a large number of correlated features.

Answer

Collect more training data to reduce the impact of correlated features.

Answer

Increase the regularization parameter in the model.

Answer

Remove all features with correlation above 0.95.

Question 9

A machine learning engineer is performing exploratory data analysis on a dataset containing customer transactions. They notice that the target variable is highly imbalanced: 99% of samples belong to class 0 and 1% to class 1. Which technique should they use to address this imbalance before training a classification model?

Accepted Answer

Apply SMOTE to generate synthetic samples for the minority class.. Option C is correct because SMOTE generates synthetic samples for the minority class, which is effective for imbalanced datasets. Option A is wrong because accuracy is not a good metric for imbalanced data. Option B is wrong because under-sampling discards majority class data. Option D is wrong because using raw data without handling imbalance typically leads to poor minority class performance.

Answer

Train the model on the raw data without any modification.

Answer

Use accuracy as the evaluation metric and train on the raw data.

Answer

Under-sample the majority class to match the minority class size.

Question 10

A data scientist is analyzing a dataset with missing values. The missing data mechanism is missing at random (MAR). Which imputation method is most appropriate to preserve relationships between variables?

Accepted Answer

Use multiple imputation by chained equations (MICE).. Option D is correct because multiple imputation by chained equations (MICE) handles MAR well by modeling each variable with missing values conditional on others. Option A is wrong because mean imputation underestimates variance. Option B is wrong because dropping rows with missing data reduces sample size and can introduce bias. Option C is wrong because KNN imputation assumes data are MCAR and may not be optimal for MAR.

Answer

Remove all rows with any missing values.

Answer

Use k-nearest neighbors imputation.

Answer

Replace missing values with the mean of the column.

Question 11

A data scientist runs the above AWS CLI command on a file in S3. What can be concluded from the output?

Accepted Answer

The ETag can be used for integrity checking.. Option B is correct because the ETag can be used to verify file integrity. Option A is wrong because ContentLength shows size in bytes, ContentLength 1048576 is 1 MB. Option C is wrong because ETag is not a version ID; S3 versioning uses VersionId. Option D is wrong because preprocessed metadata indicates the file has been processed.

Answer

The file is 1 GB in size.

Answer

The object has S3 versioning enabled.

Answer

The file has not been preprocessed.

Question 12

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

Accepted Answer

Access is denied if the request does not originate from the specified VPC endpoint.. Option C is correct because the Deny statement explicitly denies s3:* actions on the confidential folder unless the request comes from a specific VPC endpoint. If the request is from outside that endpoint or from a different VPC, it will be denied. Option A is wrong because the Deny overrides the Allow. Option B is wrong because the Deny is conditional. Option D is wrong because the condition restricts access.

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 13

A data scientist is using Amazon Athena to query a CSV file stored in S3. The above error occurs. What is the most likely cause?

Accepted Answer

The CSV file has inconsistent number of columns in some rows.. Option A is correct because the error clearly states that a row has more fields than the header. Option B is wrong because the error is about field count mismatch, not encoding. Option C is wrong because the error mentions row number, but the issue is field count. Option D is wrong because the header is present and read correctly.

Answer

The CSV file uses a different delimiter than comma.

Answer

The CSV file is missing a header row.

Answer

The CSV file is too large for Athena to process.

Question 14

A data scientist is reviewing a dataset and notices that the distribution of a numerical feature is heavily right-skewed with a long tail. Which visualization is most appropriate to assess the distribution?

Accepted Answer

Histogram with a logarithmic scale on the x-axis. Option B is correct because a histogram with a log scale can handle skewed data. Option A is wrong because a box plot shows quartiles but not the full distribution shape. Option C is wrong because a scatter plot is for two variables. Option D is wrong because a line chart is for time series.

Answer

Box plot

Answer

Line chart

Answer

Scatter plot

Question 15

A data scientist is working with a dataset that includes a 'timestamp' column. They want to create features that capture seasonality. Which feature engineering approach is most appropriate?

Accepted Answer

Extract hour of day and apply sine/cosine transformation.. Option D is correct because sine and cosine transformations capture cyclic patterns like time of day or day of year. Option A is wrong because one-hot encoding creates many sparse features. Option B is wrong because converting to Unix timestamp loses cyclic nature. Option C is wrong because binning loses granularity.

Answer

Bin timestamps into fixed intervals.

Answer

Convert timestamp to Unix epoch seconds.

Answer

One-hot encode the timestamp column.

Question 16

A data scientist is performing exploratory data analysis on text data. They want to identify the most common terms and their frequencies. Which approach should they use?

Accepted Answer

Create a bag-of-words matrix and compute term frequencies.. Option A is correct because a term frequency-inverse document frequency (TF-IDF) vectorizer can provide weighted frequencies, but a simple count vectorizer is also common. However, the question asks for common terms and frequencies, so a bag-of-words approach is appropriate. Option B is wrong because word2vec produces embeddings, not frequencies. Option C is wrong because LDA is a topic model. Option D is wrong because sentiment analysis is not about frequency.

Answer

Perform sentiment analysis on the text.

Answer

Apply Latent Dirichlet Allocation (LDA) to extract topics.

Answer

Use word2vec to generate word embeddings.

Question 17

During exploratory data analysis, a data scientist discovers that a feature has a variance of 0.01, while other features have variances around 1.0. Which action should be taken?

Accepted Answer

Consider removing the feature or applying variance threshold.. Option B is correct because features with near-zero variance contribute little information and may cause numerical instability. Option A is wrong because low variance does not automatically mean missing values. Option C is wrong because scaling to unit variance amplifies noise. Option D is wrong because transformation does not increase variance meaningfully.

Answer

Scale the feature to have unit variance.

Answer

Apply a log transformation to the feature.

Answer

Impute missing values in the feature.

Question 18

A data scientist is using Amazon SageMaker to train a model and wants to use a custom Docker container for training. The container requires access to a private Amazon ECR repository. Which IAM role configuration is needed?

Accepted Answer

Attach an IAM policy to the SageMaker execution role that allows ecr:GetDownloadUrlForLayer, ecr:BatchGetImage, and ecr:GetAuthorizationToken for the ECR repository.. Option C is correct because the SageMaker execution role must have an IAM policy that allows ecr:GetDownloadUrlForLayer, ecr:BatchGetImage, and ecr:GetAuthorizationToken for the ECR repository. Option A is wrong because the ECR repository does not grant permissions to the SageMaker role via bucket policies. Option B is wrong because SageMaker does not use the ECR repository owner's role. Option D is wrong because the SageMaker role is the appropriate entity to grant permissions.

Answer

Use the AWS account owner's IAM role as the SageMaker execution role.

Answer

Create a new IAM user with ECR access and store credentials in SageMaker.

Answer

Add a bucket policy to the ECR repository allowing access from the SageMaker execution role.

Question 19

A data scientist is analyzing a dataset and finds that the target variable has a bimodal distribution. Which preprocessing step is most appropriate before modeling?

Accepted Answer

Consider clustering to separate the two modes and model them separately.. Option B is correct because clustering can identify natural groups, which can be treated as separate modeling tasks. Option A is wrong because log transformation works for skewed unimodal distributions. Option C is wrong because scaling does not change distribution shape. Option D is wrong because removing outliers would not address bimodality.

Answer

Standardize the target variable to have mean 0 and variance 1.

Answer

Remove outliers from the target variable.

Answer

Apply a log transformation to the target variable.

Question 20

A data scientist is analyzing a dataset with missing values in several features. The dataset is large (10 million rows) and stored in an S3 bucket as CSV files. The scientist wants to use AWS Glue to catalog the data and then use Amazon Athena to query it. However, the missing values are causing errors in downstream machine learning models. Which approach should the scientist take to handle missing values during exploratory data analysis?

Accepted Answer

Use AWS Glue ETL jobs with a custom transformation script that uses the AWS Glue library to drop or impute missing values before writing to a new dataset.. Option C is correct because AWS Glue provides built-in transforms to handle missing values during the ETL process, and using a custom script with the AWS Glue library allows fine-grained control. Option A is wrong because Athena cannot modify data; it is only a query engine. Option B is wrong because SageMaker Data Wrangler is for interactive data preparation, not for large-scale automated ETL. Option D is wrong because Redshift Spectrum is for querying, not for cleaning missing values.

Answer

Use Amazon SageMaker Data Wrangler to create a data flow that imputes missing values and export the transformed dataset to S3.

Answer

Use Amazon Redshift Spectrum with an external table to query the data and use SQL COALESCE to handle missing values on the fly.

Answer

Use Amazon Athena to run SQL queries that impute missing values and write the results to a new table.