MLS-C01 Mock Exam 74 — 25 Questions

Question 1

A data scientist is performing exploratory data analysis on a dataset stored in Amazon S3 using Amazon SageMaker Studio. The dataset has missing values in several columns. Which approach is the MOST efficient way to handle missing values within SageMaker Studio?

Accepted Answer

Use SageMaker Data Wrangler to impute missing values with mean, median, or mode.. SageMaker Data Wrangler provides a visual interface to handle missing values. Option B is wrong because writing a custom script is less efficient. Option C is wrong because Glue is external. Option D is wrong because running a notebook from the local machine is not efficient.

Answer

Run a Jupyter notebook on a local machine to clean the data and upload back to S3.

Answer

Use AWS Glue to run a find-and-replace operation.

Answer

Write a custom Python script using pandas to drop rows with missing values.

Question 2

Refer to the exhibit. A data scientist is unable to read a CSV file from the S3 bucket 'my-bucket' using SageMaker. The IAM policy attached to the SageMaker execution role is shown. What is the most likely cause of the failure?

Accepted Answer

The bucket uses server-side encryption with AWS KMS (SSE-KMS) and the policy lacks kms:Decrypt permission. The policy grants GetObject and ListBucket, but ListBucket is not sufficient for reading objects; GetObject is needed and is present. However, the error might be due to missing s3:GetObject on the specific object path. But the policy looks correct. Actually, the issue could be that the bucket is in a different region or encryption mismatch. However, the most common cause is that the SageMaker notebook instance's IAM role does not have the policy attached, or the policy is missing permissions like KMS if encrypted. But given the options, the policy appears correct. Wait, the question states 'unable to read'. A plausible cause is that the bucket uses SSE-KMS and the policy does not include kms:Decrypt. Option B is correct because if the bucket uses KMS encryption, the role needs KMS permissions. Option A is wrong because GetObject is present. Option C is wrong because ListBucket is present. Option D is wrong because the policy allows read access.

Answer

The policy does not allow the s3:GetObject action

Answer

The policy does not grant read access to the bucket

Answer

The policy does not include s3:ListBucket action

Question 3

A data scientist is analyzing a dataset with a timestamp column and several numeric measurements. The goal is to detect seasonality and trends. Which AWS service can be used directly from SageMaker Studio to perform this analysis without writing code?

Accepted Answer

Amazon SageMaker Data Wrangler. SageMaker Data Wrangler includes built-in time series analysis capabilities such as seasonality detection. Option A is wrong because QuickSight ML Insights requires data to be in QuickSight. Option B is wrong because Glue DataBrew is for data preparation but not specifically for time series analysis. Option D is wrong because Forecast is for forecasting, not exploratory analysis.

Answer

Amazon Forecast

Answer

Amazon QuickSight ML Insights

Answer

AWS Glue DataBrew

Question 4

A company uses SageMaker Pipelines to automate model retraining. The pipeline fails intermittently at the Preprocess step with a 'ResourceLimitExceeded' error. The team uses a ml.m5.xlarge instance. What is the most likely cause?

Accepted Answer

The account has reached the limit for concurrent ml.m5.xlarge instances. The error indicates reaching a service quota. SageMaker has a default limit of concurrent training jobs per account. Option A is correct. Option B would cause different errors. Option C is unrelated. Option D would cause a SageMaker service error, not a resource limit.

Answer

The preprocessing script has a memory leak

Answer

The S3 bucket has insufficient permissions

Answer

The pipeline execution role is missing the PassRole permission

Question 5

A data scientist is training a deep learning model on Amazon SageMaker using the built-in Object Detection algorithm. The training job is failing with a 'ResourceLimitExceeded' error when trying to launch multiple GPU instances. Which of the following is the MOST likely cause?

Accepted Answer

The account has reached the limit for the number of GPU instances in the current AWS Region.. Option D is correct because the 'ResourceLimitExceeded' error typically indicates that the requested instance type or count exceeds the account's service limit for SageMaker training instances. Option A is wrong because SageMaker does not enforce a limit on the total dataset size. Option B is wrong because S3 bucket permissions would cause a different error (e.g., AccessDenied). Option C is wrong because a corrupted training script would cause a different error (e.g., ModuleNotFoundError).

Answer

The training script has a syntax error.

Answer

The dataset is too large for the selected instance type.

Answer

The S3 bucket containing the training data has insufficient permissions.

Question 6

A data scientist is using Amazon SageMaker to deploy a model for real-time inference. The endpoint receives a large number of requests with variable traffic patterns. The team wants to minimize cost while ensuring low latency. Which THREE actions should the team take? (Choose THREE.)

Accepted Answer

Use a multi-model endpoint to host multiple models on the same instance.. Options A, C, and E are correct. Option A: Using a production variant with a smaller instance type reduces cost. Option C: Enabling auto-scaling adjusts capacity based on traffic. Option E: Using a multi-model endpoint allows sharing instances among models. Option B is wrong because higher concurrency may increase cost. Option D is wrong because a single large instance may be over-provisioned.

Answer

Set the initial variant weight to 1 and increase the number of instances.

Answer

Use a single large instance to handle all traffic.

Question 7

A company is using SageMaker to deploy a model for real-time inference. The model requires low latency, and the company wants to test the endpoint before production. Which approach should be used to validate endpoint performance?

Accepted Answer

Use SageMaker's built-in shadow testing or load testing features.. Option D is correct because SageMaker provides a built-in load testing tool that simulates traffic to test endpoint performance. Option A is wrong because waiting for production traffic does not allow pre-production validation. Option B is wrong because CloudWatch does not generate traffic. Option C is wrong because offline evaluation does not test real-time inference.

Answer

Use CloudWatch Synthetics to create a canary.

Answer

Perform offline batch evaluation on a test dataset.

Answer

Deploy to production and monitor using CloudWatch.

Question 8

A data scientist needs to store and version machine learning models, along with metadata such as hyperparameters and metrics. Which AWS service is designed for this purpose?

Accepted Answer

Amazon SageMaker Model Registry. Option D is correct: SageMaker Model Registry is for cataloging and versioning models. Option A (S3) is object storage but not specialized. Option B (ECR) stores container images. Option C (DynamoDB) is a NoSQL database, not purpose-built for ML models.

Answer

Amazon S3 with versioning enabled

Answer

Amazon DynamoDB

Answer

Amazon Elastic Container Registry (ECR)

Question 9

A data scientist is analyzing a dataset with a target variable that is highly imbalanced (99% negative class, 1% positive class). The dataset has 10 million rows. The goal is to train a binary classifier. Which technique should be applied during exploratory data analysis to best address the imbalance?

Accepted Answer

Random undersampling of the majority class. For large datasets, undersampling the majority class is feasible and can be effective. Option A is wrong because SMOTE generates synthetic samples but may be computationally expensive for 10M rows. Option B is wrong because class weights are set during training, not EDA. Option D is wrong because collecting more data is not guaranteed to fix imbalance.

Answer

Assign higher class weights to the minority class

Answer

Synthetic Minority Oversampling Technique (SMOTE)

Answer

Collect more data for the minority class

Question 10

Refer to the exhibit. A data scientist is using an IAM role with this policy to run a SageMaker processing job that reads data from S3. The job fails with an access error. What is the most likely cause?

Accepted Answer

The policy does not allow s3:ListBucket. The processing job needs both s3:GetObject and s3:ListBucket to read objects. The policy lacks s3:ListBucket. Option A is wrong because sagemaker:CreateProcessingJob is allowed. Option B is wrong because the policy allows s3:GetObject. Option D is wrong because s3:PutObject is not needed for reading.

Answer

The policy does not allow sagemaker:CreateProcessingJob

Answer

The policy does not allow s3:PutObject

Answer

The policy does not allow s3:GetObject

Question 11

A data scientist uses SageMaker to train a model. The training job takes 10 hours, but the team needs to reduce costs. Which approach is MOST cost-effective?

Accepted Answer

Enable Managed Spot Training. Spot instances can reduce costs up to 90%. Managed Spot Training is the most cost-effective. Option C is correct. Option A increases cost. Option B may reduce time but not necessarily cost. Option D is for hyperparameter tuning.

Answer

Use SageMaker Automatic Model Tuning

Answer

Use a larger instance type to finish faster

Answer

Use SageMaker Distributed Training with more instances

Question 12

A data scientist is working with a dataset that contains both numerical and categorical features. During EDA, they want to understand the relationship between a categorical feature with 10 unique values and the target variable. Which visualization is most appropriate?

Accepted Answer

Box plot. A box plot shows the distribution of the target across categories. Option A is wrong because scatter plots are for two numerical features. Option B is wrong because histogram shows distribution of a single numerical feature. Option D is wrong because heatmaps typically show correlation between numerical features.

Answer

Heatmap

Answer

Histogram

Answer

Scatter plot

Question 13

A data engineer is analyzing a large dataset stored in Amazon S3 using AWS Glue and Amazon Athena. They notice that queries against a table with many small files are slow. Which TWO actions can improve query performance?

Accepted Answer

Convert files to Apache Parquet format. Compacting small files into larger ones reduces overhead. Partitioning the data limits the amount of data scanned. Using Parquet or ORC improves performance, but the question asks for two actions; converting to columnar format is also valid but not listed as a correct option here. The correct pair is A and B.

Answer

Use Athena's automatic compression

Answer

Increase the number of Glue DPUs

Answer

Decrease the number of partitions

Question 14

A data scientist is performing exploratory data analysis on a dataset with 100 features. They want to identify which features are most correlated with the target variable. Which THREE methods are appropriate for this task?

Accepted Answer

Pearson correlation coefficient. Pearson correlation captures linear relationships. Mutual information captures non-linear dependencies. Feature importance from a tree-based model provides a ranking. Spearman correlation is for monotonic relationships, but the question asks for three methods among the options; the correct set includes Pearson, mutual information, and feature importance. Note: Spearman is also valid but not listed as a correct option here because we need exactly three; the options given make A, B, and D the correct choices.

Answer

Variance threshold

Answer

One-hot encoding

Question 15

A company deploys a SageMaker endpoint for real-time inference. After a week, the response latency increases from 50 ms to 500 ms. CPU utilization is at 30%. What is the most likely cause?

Accepted Answer

The inference code makes a call to a downstream service that is throttling requests. Increased latency with low CPU suggests a bottleneck elsewhere, often due to throttling by downstream services like a database. Option B is correct. Option A would show high CPU. Option C would cause errors. Option D would cause high memory usage.

Answer

The model has a memory leak

Answer

The instance type is underpowered for the inference load

Answer

The SageMaker endpoint is experiencing a network outage

Question 16

A data scientist needs to deploy a model with a custom inference container. Which THREE requirements must the container meet for SageMaker hosting?

Accepted Answer

Implement a /ping endpoint for health checks. SageMaker requires containers to implement the /invocations and /ping endpoints, and to serve on port 8080. Options A, B, and E are correct. Option C is for training, Option D is optional.

Answer

Provide a training script at /opt/ml/input/data

Answer

Use the SageMaker Python SDK to load the model

Question 17

A company is using Amazon SageMaker to train a model. The training data is stored in an S3 bucket. The data scientist wants to use the Pipe mode for training to stream data directly from S3 instead of downloading it first. Which of the following is a prerequisite for using Pipe mode?

Accepted Answer

The training data must be in RecordIO-protobuf or TFRecord format.. Option B is correct because Pipe mode requires the training data to be in a format that supports streaming, such as RecordIO or TFRecord. Option A is wrong because SageMaker can handle S3 data regardless of bucket policy. Option C is wrong because Pipe mode does not require data to be in a single file. Option D is wrong because Pipe mode does not require the data to be uncompressed.

Answer

The training data must be compressed using Gzip.

Answer

The S3 bucket must have public read access.

Answer

The training data must be stored as a single large file.

Question 18

A data scientist is performing hyperparameter tuning using Amazon SageMaker Automatic Model Tuning (AMT). The job uses a random search strategy. After 20 training jobs, the best objective metric value has plateaued. The data scientist wants to explore more of the hyperparameter space. Which action should the data scientist take?

Accepted Answer

Change the tuning strategy from Random to Bayesian.. Option C is correct because switching to Bayesian search will explore new regions based on previous results, potentially finding better hyperparameters. Option A is wrong because increasing the number of parallel jobs does not change the search strategy. Option B is wrong because decreasing the number of training jobs reduces exploration. Option D is wrong because early stopping does not change the search strategy.

Answer

Enable early stopping.

Answer

Decrease the maximum number of training jobs.

Answer

Increase the number of parallel training jobs.

Question 19

A data scientist is training a deep learning model on SageMaker using a custom Docker container. The training job fails with an error indicating that the container exited with a non-zero status. The CloudWatch logs show 'FileNotFoundError: [Errno 2] No such file or directory: '/opt/ml/input/data/training/data.csv''. What is the most likely cause?

Accepted Answer

The S3 data source path is incorrect or the data has not been uploaded.. Option C is correct because the error indicates the training data is missing at the expected path, which typically occurs when the S3 data source configuration is incorrect or the data is not uploaded. Option A is wrong because the error is about missing data, not the container entry point. Option B is wrong because the error is not related to training script syntax. Option D is wrong because the error does not mention model artifacts.

Answer

The container's Docker entry point is misconfigured.

Answer

The training script has a syntax error.

Answer

The model output path in the training job configuration is wrong.

Question 20

A data scientist is tuning a gradient boosting model using SageMaker automatic model tuning. The hyperparameter 'num_round' ranges from 50 to 500. The tuning job uses 'ObjectiveMetric' = 'validation:auc'. After 50 training jobs, the best objective value is 0.95. The data scientist suspects overfitting. What should the data scientist do?

Accepted Answer

Add an early stopping round and increase the range for regularization hyperparameters like 'gamma' and 'lambda'.. Increasing early stopping rounds and adding regularization (like gamma or lambda) helps reduce overfitting. Lowering learning rate with more rounds can also help. Option A (decreasing rounds) might underfit. Option C (increasing max_depth) worsens overfitting. Option D (increasing num_round) with no regularization may overfit more.

Answer

Increase 'max_depth' to capture more complex patterns.

Answer

Increase 'num_round' to 1000 and keep other hyperparameters unchanged.

Answer

Decrease the range of 'num_round' to 10-100.