MLS-C01 Mock Exam 75 — 25 Questions

Question 1

Which TWO options are best practices for training machine learning models using SageMaker? (Choose TWO.)

Accepted Answer

Use incremental training when you have new data that is similar to the original training data. SageMaker's incremental training allows you to continue training an existing model with new data that shares the same schema and feature space, without retraining from scratch. This is a best practice when you have a steady stream of similar data, as it saves time and compute resources while preserving previously learned patterns.

Answer

Train the final model on the combined training and test sets to maximize data usage

Answer

Always use the largest possible instance type to minimize training time

Answer

Always enable checkpointing to save the model after every epoch

Question 2

A data engineer needs to design a data pipeline that ingests CSV files from an SFTP server daily, transforms them, and loads them into Amazon Redshift. The files are typically 2-3 GB. Which combination of AWS services is MOST appropriate?

Accepted Answer

Use AWS Transfer Family to automate SFTP file retrieval to S3, then use Redshift COPY to load data.. The most appropriate because AWS Transfer Family provides a fully managed, serverless solution for automating SFTP file retrieval directly into Amazon S3. Once the CSV files are in S3, the Redshift COPY command can efficiently load the 2-3 GB files using parallel processing, which is far more performant and cost-effective than alternatives like Lambda or Glue for large file sizes.

Answer

Use AWS Glue ETL with a JDBC connection to the SFTP server to read files directly.

Answer

Use AWS Lambda to download the files from SFTP, transform them in memory, and write to Redshift using the Data API.

Answer

Use Amazon Kinesis Data Firehose with an HTTP endpoint source to receive files from SFTP.

Question 3

A company is deploying a real-time inference endpoint using Amazon SageMaker. The model is a large deep learning model that requires low latency. The team is concerned about cost. Which SageMaker hosting option should the team use?

Accepted Answer

Use a SageMaker multi-model endpoint.. A SageMaker multi-model endpoint allows you to host multiple models on a single endpoint behind the same serving container, sharing resources and reducing costs while still providing low-latency real-time inference. This is ideal for a large deep learning model that needs low latency but must be cost-effective, as it avoids the expense of dedicated instances for each model.

Answer

Use a SageMaker batch transform job.

Answer

Use a SageMaker Serverless Inference endpoint.

Answer

Use a single-instance endpoint with a large instance type.

Question 4

Which TWO of the following are valid Amazon SageMaker built-in algorithms for regression tasks? (Select TWO.)

Accepted Answer

XGBoost. XGBoost is a valid Amazon SageMaker built-in algorithm for regression tasks because it supports regression objectives such as 'reg:squarederror' and 'reg:logistic'. It is a gradient boosting framework that builds an ensemble of decision trees, making it suitable for both regression and classification problems.

Answer

BlazingText

Answer

Image Classification

Answer

Object Detection

Question 5

An ML team wants to perform batch inference on a large dataset stored in Amazon S3 using a pre-trained model. The team needs to process the data in parallel across multiple instances to reduce processing time. Which approach should they use?

Accepted Answer

Use SageMaker Batch Transform with multiple instances.. SageMaker Batch Transform is designed specifically for batch inference on large datasets stored in Amazon S3. It automatically distributes the data across multiple instances, processes them in parallel, and writes the results back to S3, making it the optimal choice for reducing processing time.

Answer

Use SageMaker Processing to run a custom inference script.

Answer

Use SageMaker Training to run inference as a training job.

Answer

Use SageMaker Ground Truth to process the data.

Question 6

A data scientist needs to query a dataset stored as Parquet files in Amazon S3 using standard SQL without managing any infrastructure. Which service should they use?

Accepted Answer

Amazon Athena. Amazon Athena is a serverless interactive query service that allows you to query data stored in Amazon S3 using standard SQL without any infrastructure to manage. It directly reads Parquet files from S3 and executes queries using Presto under the hood, making it the ideal choice for this use case.

Answer

Amazon QuickSight

Answer

AWS Glue

Answer

Amazon Redshift

Question 7

A data scientist is using SageMaker to train a deep learning model for image classification. The training job is taking too long. Which approach can reduce training time?

Accepted Answer

Use SageMaker's distributed data parallelism. SageMaker's distributed data parallelism splits the training data across multiple GPUs or instances, allowing each worker to process a different subset of the data simultaneously. This reduces the wall-clock time per epoch by parallelizing the computation, which directly addresses the 'taking too long' issue for deep learning image classification models.

Answer

Use SageMaker Neo to compile the model

Answer

Increase the number of epochs

Answer

Use a smaller image size

Question 8

A data scientist is working with a dataset containing text reviews. The goal is to classify sentiment. During EDA, they compute the word frequency distribution. They notice that the most frequent words are common stop words like 'the', 'and', 'a'. Which action should they take to improve the feature representation for modeling?

Accepted Answer

Remove the stop words from the text before creating the bag-of-words representation.. The correct action is to remove stop words (option C) because stop words like 'the', 'and', 'a' are common across all documents and do not carry sentiment information. Removing them allows the model to focus on content words that are more indicative of sentiment. Option A (n-grams) captures phrase patterns but still includes stop words, so it does not address the issue. Option B (adding more stop words) would remove even more words, potentially including some useful for sentiment, making it less effective than using a standard stop word list. Option D (stemming) reduces words to root forms but does not remove stop words, so it does not solve the problem of high-frequency stop words dominating the feature space.

Answer

Use n-grams instead of unigrams to capture phrase patterns.

Answer

Add more stop words to the default list to remove even more common words.

Answer

Apply stemming to reduce words to their root forms.

Question 9

A data scientist is using SageMaker to train an XGBoost model for regression. The training data contains categorical features with high cardinality (e.g., zip code with over 10,000 unique values). Which feature engineering approach is MOST appropriate to avoid overfitting while preserving predictive power?

Accepted Answer

Use target encoding with smoothing. Target encoding with smoothing is the most appropriate approach because it replaces each high-cardinality category with the mean of the target variable for that category, regularized by a smoothing factor that pulls estimates toward the global mean. This preserves predictive power by capturing the relationship between the category and the target while preventing overfitting on rare categories that have few samples. In SageMaker XGBoost, this avoids the curse of dimensionality from one-hot encoding and the arbitrary ordering from label encoding.

Answer

One-hot encode the categorical features

Answer

Apply frequency encoding based on category occurrence

Answer

Label encode the categorical features

Question 10

A data scientist is training a random forest model. During hyperparameter tuning, which parameter is MOST effective at reducing overfitting?

Accepted Answer

Decrease the maximum depth of each tree. Decreasing the maximum depth of each tree limits the complexity of individual trees, preventing them from memorizing noise and outliers in the training data. This directly reduces overfitting by enforcing simpler decision boundaries, which is a core regularization technique for ensemble methods like Random Forest.

Answer

Increase the number of trees

Answer

Increase the number of features considered per split

Answer

Increase the maximum depth of each tree

Question 11

A company is using AWS Glue to run ETL jobs that process data from Amazon RDS to Amazon S3. The ETL jobs are failing intermittently with write timeout errors when writing to S3. The company wants to implement a retry mechanism for transient errors. What should the company do?

Accepted Answer

Configure the AWS Glue job to retry on failure by setting the 'Max retries' parameter. AWS Glue provides a built-in retry mechanism via the 'Max retries' parameter, which automatically retries the job when transient errors like write timeouts to S3 occur. Option A directly addresses the need for a retry mechanism. Option B is incorrect because increasing EBS volume size does not fix S3 write timeout errors, which are network-related. Option C is incorrect because manual restart via CloudWatch is not an automated retry mechanism. Option D is incorrect because AWS Glue does not natively integrate with SQS for job retries; the built-in retry parameter is the proper solution.

Answer

Increase the size of the Amazon EBS volumes attached to the Glue job

Answer

Use Amazon CloudWatch to monitor the job and manually restart on failure

Answer

Place the failed job messages in an Amazon SQS queue and reprocess them

Question 12

A team is analyzing a dataset with many categorical features that have high cardinality (e.g., ZIP code, user ID). They want to explore relationships between these features and a continuous target variable. Which approach is most appropriate for visualizing these relationships without overwhelming the viewer?

Accepted Answer

Group categories into top K levels and use a box plot for each group.. When dealing with high-cardinality categorical features, grouping the most frequent categories into a manageable number (e.g., top 10) and using box plots per group allows for clear visualization of the relationship with a continuous target. This approach reduces clutter and highlights differences in distributions. Option B is incorrect because Pearson correlation is designed for continuous variables, not categorical ones. Option C is incorrect: a scatter plot with color-coded categories becomes unreadable with many categories and does not effectively show distributional differences. Option D is incorrect because chi-square statistics assess association between two categorical variables, not between a categorical and a continuous variable.

Answer

Compute a correlation matrix using Pearson correlation.

Answer

Create a scatter plot with each category as a different color.

Answer

Use a heatmap to show pairwise chi-square statistics.

Question 13

A data scientist is exploring a dataset of customer transactions. The dataset has 1 million rows and 50 columns. The target variable is a binary flag indicating whether a customer churned. The data scientist runs a correlation matrix on all numerical features and finds that two features have a correlation coefficient of 0.98. Which action should be taken to improve model performance?

Accepted Answer

Remove one of the two highly correlated features from the dataset.. Two features with a correlation coefficient of 0.98 are nearly perfectly multicollinear. This inflates the variance of coefficient estimates in linear models, making them unstable and reducing interpretability. Removing one of the highly correlated features is a standard dimensionality reduction technique that mitigates multicollinearity without significant information loss, as the remaining feature captures almost the same variance.

Answer

Create an interaction term between the two features.

Answer

Increase the regularization parameter (e.g., lambda) in the model.

Answer

Apply mean-centering to both features to reduce correlation.

Question 14

A company uses SageMaker to train a model. The training job fails with 'ResourceLimitExceeded' error. Which TWO actions should the company take to resolve this?

Accepted Answer

Use a different instance type that is not at its limit.. The 'ResourceLimitExceeded' error indicates that the requested instance type has reached its concurrent usage limit in the current AWS region. Switching to a different instance type that is not at its limit allows the training job to proceed without exceeding the service quota. Option E is correct because requesting a service limit increase for SageMaker training job resources directly raises the cap on the number of concurrent instances or total instance count, resolving the underlying quota issue.

Answer

Launch the training job in a different AWS region.

Answer

Use SageMaker Managed Spot Training to reduce cost.

Answer

Compress the training data to reduce storage requirements.

Question 15

A company uses Amazon SageMaker to train a deep learning model using TensorFlow. The training job is failing with an 'OutOfMemory' error. The instance type is ml.p3.2xlarge with 16 GB GPU memory. The model has 10 million parameters. Which THREE actions should be taken to resolve the memory issue? (Choose THREE.)

Accepted Answer

Reduce the batch size. Reducing the batch size directly decreases the memory footprint per training step because fewer samples are loaded into GPU memory simultaneously. With 10 million parameters and 16 GB GPU memory, the default batch size may exceed available memory for activations and gradients. This is the most straightforward fix for an OutOfMemory error in TensorFlow on SageMaker.

Answer

Increase the number of epochs

Answer

Increase the batch size

Question 16

A machine learning engineer needs to deploy a real-time inference endpoint for a model that requires GPU acceleration for low latency. Which AWS service should be used?

Accepted Answer

Amazon SageMaker real-time endpoint. Amazon SageMaker provides real-time endpoints that support GPU instances for low-latency inference. AWS Lambda does not support GPU, and Batch is for asynchronous processing. EC2 would require manual management.

Answer

Amazon SageMaker batch transform

Answer

Amazon EC2 with auto scaling

Answer

AWS Lambda with GPU

Question 17

An AWS Glue ETL job failed with the error 'Insufficient memory allocated for the job'. The job run details show AllocatedCapacity: 5, WorkerType: Standard, NumberOfWorkers: 5. Which change should be made to resolve the issue?

Accepted Answer

Increase the number of workers to 10. The error indicates insufficient memory for the job. Both increasing the number of workers (Option C) and changing the worker type to G.2X (Option D) increase the total allocated memory. Option C scales out by adding more Standard workers, each with 16 GB memory and 1 DPU. Option D scales up by switching to G.2X workers, each with 32 GB memory and 2 DPUs, effectively doubling the DPU and total memory for the same number of workers. Either change can resolve the insufficient memory error. Option A is incorrect because deleting and recreating the job does not change resource allocation. Option B is incorrect because job timeout does not affect memory.

Answer

Delete and recreate the job with a different name

Answer

Increase the job timeout to 3600 minutes

Question 18

A data scientist uses SageMaker Autopilot to automatically build a binary classification model. The dataset has 50 features and 100,000 rows. After the experiment, Autopilot provides multiple candidate models. Which candidate should the data scientist select to minimize inference latency for real-time predictions?

Accepted Answer

The model that is a linear learner. SageMaker Autopilot explores various algorithms including linear models, tree-based ensembles, and neural networks. For real-time inference with low latency, simpler models like linear or logistic regression or shallow decision trees are preferred. XGBoost with many trees or deep neural networks increase latency.

Answer

The model with the smallest memory footprint

Answer

The model with the highest validation accuracy

Answer

The model with the lowest validation loss

Question 19

A data scientist is trying to launch a SageMaker training job using an IAM role with the above policy. The training job fails with an access denied error. What is the MOST likely reason?

Accepted Answer

The policy does not include s3:ListBucket permission. The policy grants s3:GetObject and s3:PutObject permissions on the S3 bucket ARN with a /* suffix, but SageMaker training jobs also require s3:ListBucket permission at the bucket level (without the /*) to enumerate objects and validate paths during job creation. Without s3:ListBucket, the training job fails with an access denied error even though read/write permissions are present.

Answer

The sagemaker:StopTrainingJob action is not required

Answer

The sagemaker:CreateTrainingJob action is not allowed for the specific instance type

Answer

The S3 bucket ARN should not include the /* suffix

Question 20

A data scientist builds a Random Forest model using SageMaker. The model performs well on training data but poorly on test data. Which step is most likely to reduce overfitting?

Accepted Answer

Reduce the maximum depth of each tree. Reducing the maximum depth of each tree limits the complexity of individual decision trees, preventing them from memorizing noise and specific patterns in the training data. This directly addresses overfitting by enforcing simpler, more generalized splits, which improves performance on unseen test data.

Answer

Increase the number of trees

Answer

Switch to a linear model

Answer

Increase the number of features considered at each split