MLS-C01 Practice Exam 53 — 20 Questions

Question 1

Drag and drop the steps to deploy a model as a SageMaker endpoint for real-time inference in the correct order.

Accepted Answer

1. Create model, 2. Create endpoint configuration, 3. Create endpoint, 4. Test endpoint. Deployment requires model creation, endpoint configuration, endpoint creation, and testing.

Answer

1. Create endpoint configuration, 2. Create model, 3. Create endpoint, 4. Test endpoint

Answer

1. Create model, 2. Create endpoint, 3. Create endpoint configuration, 4. Test endpoint

Answer

1. Test endpoint, 2. Create model, 3. Create endpoint configuration, 4. Create endpoint

Question 2

Which TWO actions can help reduce overfitting in a neural network? (Choose 2.)

Accepted Answer

Apply L1 or L2 regularization.. Options C and E are correct because L1/L2 regularization penalizes large weights to prevent overfitting, and dropout randomly deactivates neurons to reduce co-adaptation. Option A is incorrect because adding layers increases model complexity, which can worsen overfitting. Option B is incorrect because decreasing the learning rate only affects training speed, not overfitting. Option D is incorrect because, although increasing dataset size can help reduce overfitting, it is not one of the two actions specified; L1/L2 regularization and dropout are the correct choices.

Answer

Increase the number of layers.

Answer

Decrease the learning rate.

Answer

Increase the training dataset size.

Question 3

Refer to the exhibit. A SageMaker training job using the built-in Linear Learner algorithm fails with 'Loss function returned NaN'. Which hyperparameter change is MOST likely to resolve this issue?

Accepted Answer

Reduce learning_rate to 0.01. The 'Loss function returned NaN' error in SageMaker's built-in Linear Learner algorithm typically occurs when the learning rate is too high, causing gradient updates to overshoot optimal parameters and diverge. Reducing the learning rate to 0.01 stabilizes training by ensuring smaller, more controlled weight updates, preventing numerical instability that leads to NaN loss.

Answer

Increase the learning rate to 0.5

Answer

Increase mini_batch_size to 2000

Answer

Decrease epochs to 5

Question 4

Drag and drop the steps to create a data processing job using Amazon SageMaker Processing in the correct order.

Accepted Answer

Step 1: Create a processing script, Step 2: Upload script and data to Amazon S3, Step 3: Configure the ProcessingJob, Step 4: Execute the ProcessingJob, Step 5: Verify the job output. Processing requires script creation, data upload, job configuration, execution, and verification.

Answer

Step 1: Upload script and data to Amazon S3, Step 2: Create a processing script, Step 3: Configure the ProcessingJob, Step 4: Execute the ProcessingJob, Step 5: Verify the job output

Answer

Step 1: Configure the ProcessingJob, Step 2: Create a processing script, Step 3: Upload script and data to Amazon S3, Step 4: Execute the ProcessingJob, Step 5: Verify the job output

Answer

Step 1: Create a processing script, Step 2: Configure the ProcessingJob, Step 3: Upload script and data to Amazon S3, Step 4: Execute the ProcessingJob, Step 5: Verify the job output

Question 5

Drag and drop the steps to use Amazon SageMaker Feature Store for feature engineering in the correct order.

Accepted Answer

1. Define feature group, 2. Ingest data, 3. Query features, 4. Train model, 5. Maintain feature store. Feature Store involves defining group, ingesting, querying, training, and maintaining.

Answer

1. Define feature group, 2. Query features, 3. Ingest data, 4. Train model, 5. Maintain feature store

Answer

1. Ingest data, 2. Define feature group, 3. Query features, 4. Train model, 5. Maintain feature store

Answer

1. Define feature group, 2. Ingest data, 3. Train model, 4. Query features, 5. Maintain feature store

Question 6

A data analyst is investigating a dataset where the target variable is binary (0/1). The analyst wants to check for multicollinearity among the numerical features. Which statistical measure should the analyst use?

Accepted Answer

Variance Inflation Factor (VIF).. Variance Inflation Factor (VIF) is the correct measure to check for multicollinearity among numerical features. VIF quantifies how much a feature is correlated with other features by calculating the ratio of variance of a model with multiple features to variance of a model with one feature. Option B (Mutual information) measures dependence between features and target, not among features. Option C (Chi-square test) is for categorical variables. Option D (Pearson correlation) only measures pairwise linear relationships, not multicollinearity involving multiple features.

Answer

Mutual information between features and target.

Answer

Chi-square test of independence.

Answer

Pearson correlation coefficient between each pair of features.

Question 7

A data scientist is performing EDA on a dataset with many features. They suspect some features are redundant due to high pairwise correlations. Which technique can help identify groups of correlated features?

Accepted Answer

Create a correlation matrix and visualize with a heatmap. Create a correlation matrix and visualize with a heatmap. This technique directly shows pairwise correlations between features, making it easy to identify groups of highly correlated (redundant) features. Option A is incorrect: t-SNE is a dimensionality reduction technique for visualization of high-dimensional data, but it does not quantify pairwise correlations between features. Option B is incorrect: PCA reduces dimensionality by creating principal components that are linear combinations of original features; while loadings indicate feature contributions, they do not directly show pairwise correlations between original features. Option C is incorrect: Mutual information measures dependency between features and target, not between features themselves. Option D is incorrect: The chi-square test is used for testing association between categorical variables, not for continuous features or pairwise correlation analysis.

Answer

Use t-SNE to visualize feature relationships

Answer

Apply PCA and examine the loadings

Answer

Compute mutual information between each feature and the target

Answer

Use chi-square test for each pair

Question 8

A data engineering team needs to ingest streaming data from thousands of IoT devices into Amazon S3 for near-real-time analytics. The solution must handle data that arrives in bursts and must be able to reprocess failed records automatically. Which combination of AWS services should the team use?

Accepted Answer

Amazon Kinesis Data Streams with AWS Lambda. Amazon Kinesis Data Streams is designed for real-time ingestion of large volumes of streaming data, such as from thousands of IoT devices, and can handle bursty traffic by scaling shards. AWS Lambda can be used as a consumer to process records in near-real-time, and Kinesis Data Streams supports automatic retries and checkpointing, enabling reprocessing of failed records without data loss.

Answer

AWS Glue with Amazon S3

Answer

Amazon SQS with AWS Lambda

Answer

Amazon DynamoDB Streams with AWS Lambda

Question 9

Drag and drop the steps to train a model using Amazon SageMaker built-in algorithm in the correct order.

Accepted Answer

Prepare training data and upload to S3 → Choose built-in algorithm → Create training job specifying algorithm, input/output S3 paths, and compute resources → Execute training job. Training involves data preparation, job creation, algorithm selection, input/output paths, and execution.

Answer

Choose built-in algorithm → Prepare training data and upload to S3 → Create training job specifying algorithm, input/output S3 paths, and compute resources → Execute training job

Answer

Prepare training data and upload to S3 → Create training job specifying input/output S3 paths and compute resources → Choose built-in algorithm → Execute training job

Answer

Create training job specifying algorithm, input/output S3 paths, and compute resources → Prepare training data and upload to S3 → Execute training job → Choose built-in algorithm

Question 10

A company is using SageMaker Autopilot to automatically build ML models. They want to ensure that the generated models are reproducible. Which TWO settings should they configure?

Accepted Answer

Set a random seed.. Setting a random seed (Option A) ensures that the stochastic processes in model training (e.g., weight initialization, data shuffling, and hyperparameter sampling) produce identical results across runs. SageMaker Autopilot uses algorithms like XGBoost and linear learners that rely on randomness; fixing the seed guarantees reproducibility of the final model.

Answer

Use multiple trials.

Answer

Enable early stopping.

Answer

Enable automatic feature engineering.

Question 11

A company captures streaming data from IoT devices using Amazon Kinesis Data Streams. The data is consumed by a custom application that processes records in near real-time. Recently, the application has been falling behind, and the stream is showing increased 'iterator age' metrics in CloudWatch. Which action is MOST likely to reduce the iterator age?

Accepted Answer

Increase the number of shards in the stream. The 'iterator age' metric in Amazon Kinesis Data Streams measures the time between the oldest unread record in a shard and the current time. An increasing iterator age indicates that consumers are reading data slower than it is being produced. Increasing the number of shards increases the stream's total read capacity, allowing the custom application to process records in parallel and reduce the backlog.

Answer

Increase the data retention period of the stream

Answer

Decrease the number of shards in the stream

Answer

Reduce the data retention period of the stream

Question 12

A company uses Amazon Kinesis Data Streams to ingest real-time clickstream data from a website. The data is consumed by a Lambda function that writes records to an S3 bucket. Recently, the number of shards was increased from 2 to 4 to handle higher throughput. After the change, the Lambda function started processing records with increased latency and some records were being written out of order. What is the MOST likely cause?

Accepted Answer

The partition key used by the producer does not ensure that related records go to the same shard after resharding.. After resharding from 2 to 4 shards, the mapping of partition keys to shards changes. If the producer does not use a partition key that ensures related records (e.g., same user session) are routed to the same shard, records that were previously ordered within a shard may now be split across multiple shards. Since the Lambda consumer processes shards independently, records from the same logical sequence can arrive out of order, and the increased shard count can also cause higher latency if the consumer is not properly parallelized.

Answer

The S3 bucket is not configured with versioning, causing overwrites.

Answer

The Lambda function is reading from the oldest sequence number, causing high IteratorAgeSeconds.

Answer

The Lambda function’s reserved concurrency is too low for the increased shard count.

Question 13

A company runs a daily ETL job that reads data from Amazon RDS, transforms it using AWS Glue, and writes the results to Amazon S3. The job started failing yesterday with the error: 'Rate exceeded'. What is the most likely cause and solution?

Accepted Answer

The RDS database is overwhelmed by the number of connections; reduce the Glue job's parallelism or increase RDS instance size. The 'Rate exceeded' error in an AWS Glue job reading from Amazon RDS typically indicates that the database is being overwhelmed by too many concurrent connections or queries. AWS Glue jobs can spawn multiple executors, each opening connections to RDS, and if the database's max_connections or IOPS limit is exceeded, RDS throttles requests. Reducing the Glue job's parallelism (e.g., setting the number of executors or DPUs lower) or scaling up the RDS instance (e.g., increasing instance size or provisioned IOPS) resolves the issue.

Answer

The Glue job is using too many DPUs; reduce the number of DPUs

Answer

The S3 bucket has reached its request rate limit; request a limit increase

Answer

Enable job bookmarks in the Glue job to process only new data

Question 14

A data scientist is using Amazon SageMaker to train a model. The training job is using a large dataset stored in S3. Which data input mode provides the FASTEST data loading for training?

Accepted Answer

Pipe mode. Pipe mode is the fastest data loading mode for SageMaker training because it streams data directly from S3 to the training algorithm via a FIFO pipe, bypassing disk writes. This eliminates the I/O overhead of downloading files to the local storage, enabling near-zero latency data ingestion for large datasets.

Answer

FastFile mode

Answer

Augmented manifest file

Answer

File mode

Question 15

A data scientist is training a binary classification model using SageMaker XGBoost and notices that training loss decreases but validation loss increases after a few epochs. Which action should the data scientist take to address this issue?

Accepted Answer

Set early stopping based on validation loss. The increasing validation loss while training loss decreases is a classic sign of overfitting. Setting early stopping based on validation loss halts training when the validation loss stops improving, preventing the model from memorizing noise in the training data. SageMaker XGBoost's `early_stopping_rounds` parameter monitors the evaluation metric on the validation set and stops training if no improvement is seen for a specified number of rounds.

Answer

Increase the number of rounds

Answer

Increase the learning rate

Answer

Increase the maximum tree depth

Question 16

A machine learning engineer is exploring a dataset with 50 features. Some features are highly correlated. Which technique should the engineer use to reduce dimensionality while preserving variance?

Accepted Answer

Principal Component Analysis (PCA). PCA (Principal Component Analysis) is the standard technique for dimensionality reduction by projecting data onto principal components that capture maximum variance. LDA is supervised and aims to separate classes. t-SNE is for visualization. Autoencoders can reduce dimensionality but are more complex. Factor analysis assumes latent factors.

Answer

Factor Analysis

Answer

t-Distributed Stochastic Neighbor Embedding (t-SNE)

Answer

Linear Discriminant Analysis (LDA)

Question 17

A data engineer is performing exploratory data analysis on a dataset stored in Amazon S3 using AWS Glue DataBrew. The dataset contains a column 'age' with missing values. DataBrew's profile shows that the column has 5% missing values, a mean of 45, and a standard deviation of 15. Which imputation strategy should the engineer recommend to minimize bias if the missing data is Missing at Random (MAR)?

Accepted Answer

Use multiple imputation to generate several plausible values and combine results. Multiple imputation provides unbiased estimates under MAR by accounting for uncertainty and preserving relationships between variables. Option A is wrong because mean imputation reduces variance, distorts distributions, and can bias estimates. Option B is wrong because listwise deletion reduces sample size and can introduce bias if missingness is related to other variables. Option C is wrong because median imputation is a single imputation method that does not account for the uncertainty due to missing data and may still introduce bias.

Answer

Replace missing values with the mean (45)

Answer

Remove rows with missing 'age' values

Answer

Replace missing values with the median

Question 18

A data scientist is working with a dataset that contains both numerical and categorical features. The target variable is continuous. Which TWO EDA techniques should the scientist use to understand relationships between features and the target?

Accepted Answer

Create scatter plots of numerical features against the target variable.. Scatter plots (C) are appropriate for visualizing relationships between numerical features and a continuous target. Box plots (D) are appropriate for comparing target distribution across categories of categorical features. Option A (confusion matrix) is used for classification, not regression. Option B (silhouette score) is for evaluating clustering. Option E (histogram of target) is univariate and does not show feature-target relationships.

Answer

Generate a confusion matrix for the target variable.

Answer

Compute the silhouette score for each feature.

Answer

Plot a histogram of the target variable.

Question 19

A company uses AWS Glue to catalog data in S3. Data is partitioned by year, month, day. The Glue crawler runs daily but sometimes misses new partitions. What should be done to ensure all partitions are cataloged?

Accepted Answer

Configure the crawler to update all partitions on each run.. Configuring the Glue crawler to 'update all partitions on each run' forces the crawler to scan the entire S3 path and register any new partitions it finds, even if the partition structure hasn't changed. This ensures all missed partitions are cataloged. Partition indexing (D) improves query performance by creating an index over existing partitions, but does not automatically discover new partitions.

Answer

Use a custom classifier to detect partition patterns.

Answer

Increase the crawler schedule to run every hour.

Answer

Enable partition indexing in the Glue table properties.

Question 20

A company is using Amazon SageMaker to train a large language model. The training job is taking too long. The data scientist wants to reduce training time without sacrificing model accuracy. Which THREE strategies are MOST appropriate?

Accepted Answer

Use mixed precision training (float16). Mixed precision training (float16) reduces memory usage and accelerates computation by using half-precision floating-point numbers for most operations, while maintaining a single-precision copy of critical parameters to preserve accuracy. This directly reduces training time on compatible GPUs (e.g., NVIDIA V100, A100) without sacrificing model quality, as the loss scaling technique prevents underflow in gradients.

Answer

Switch from GPU instance to CPU instance

Answer

Increase the maximum sequence length