MLS-C01 Practice Test 19 — 15 Questions

Question 1

An ML engineer is using Amazon SageMaker to train a model on a dataset that contains personal identifiable information (PII). The data must be encrypted at rest and in transit. The company uses AWS KMS for key management. How should the engineer configure the SageMaker training job to meet these encryption requirements?

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

Accepted Answer

Specify a KMS key for the training job's VolumeKmsKeyId and enable inter-container traffic encryption. It addresses both encryption at rest and in transit for the SageMaker training job. Specifying a KMS key via VolumeKmsKeyId encrypts the ML storage volume (EBS) used by the training instances at rest, while enabling inter-container traffic encryption ensures data exchanged between distributed training containers is encrypted in transit using TLS. This combination meets the PII encryption requirements using AWS KMS.

Answer

Enable S3 Server-Side Encryption (SSE-S3) on the input data bucket

Answer

Use a custom Docker image with built-in encryption and disable inter-container traffic encryption for performance

Answer

Use a VPC with an S3 VPC Endpoint and enable SSL for the endpoint

Question 2

A data engineer needs to transform large CSV files stored in Amazon S3 into Parquet format before loading into Amazon Redshift. The transformation logic is complex and requires custom Python code. Which AWS service should be used to perform this transformation with minimal operational overhead?

Accepted Answer

AWS Glue. AWS Glue is the correct answer because it is a fully managed, serverless ETL service that can handle large CSV files, convert them to Parquet, and load into Amazon Redshift with minimal operational overhead. AWS Glue provides a built-in Spark environment and supports custom Python code via Spark jobs. Option B (AWS Lambda) has a 15-minute timeout and is not designed for large-scale data transformations. Option C (Amazon EMR) requires managing clusters, increasing operational overhead. Option D (AWS Data Pipeline) is a legacy service with less flexibility and is not optimized for complex transformations like CSV to Parquet.

Answer

AWS Lambda

Answer

Amazon EMR

Answer

AWS Data Pipeline

Question 3

A data scientist is building a binary classification model to predict customer churn. The dataset has 10,000 samples with 500 churners (positive class). Which TWO techniques should be used to address the class imbalance? (Choose 2.)

Accepted Answer

Use random undersampling of the majority class. Option C is correct because random undersampling of the majority class reduces the number of non-churner samples, rebalancing the 9,500:500 ratio so the classifier is not overwhelmed by the majority class during training. Option D is correct because SMOTE generates synthetic minority-class (churner) samples by interpolating between existing minority instances in feature space, directly increasing the positive class representation and improving the model's ability to learn the churn pattern. Option A is incorrect because a higher learning rate only affects optimization step size and can cause instability or divergence; it does nothing to correct class imbalance. Option B is incorrect because L1 regularization penalizes large weights to encourage sparsity and reduce overfitting, not to rebalance class distributions. Option E is incorrect because PCA reduces dimensionality by projecting features onto principal components, which addresses multicollinearity or high dimensionality, not class imbalance.

Answer

Use a higher learning rate during training

Answer

Use L1 regularization on the model

Answer

Use principal component analysis (PCA) to reduce dimensionality

Question 4

A data scientist is training a recurrent neural network (RNN) for time series forecasting. The training loss decreases steadily for the first 10 epochs, then plateaus. The validation loss starts increasing after epoch 10. What is the most appropriate action?

Accepted Answer

Stop training early and use the model from epoch 10. The described pattern — training loss still decreasing while validation loss begins rising after epoch 10 — is textbook overfitting. The model is memorizing training data rather than generalizing. Early stopping at epoch 10 (or restoring the checkpoint with the lowest validation loss) is the standard, low-cost remedy and prevents further degradation of validation performance.

Answer

Continue training for more epochs

Answer

Add more layers to the network

Answer

Increase the batch size

Question 5

A company's ML model training on Amazon SageMaker is taking longer than expected. The training job uses a single ml.p3.2xlarge instance. Which change is most likely to reduce training time?

Accepted Answer

Use distributed training with multiple GPU instances. The training job is bottlenecked by compute capacity, as a single ml.p3.2xlarge instance provides only one NVIDIA V100 GPU. Distributed training with multiple GPU instances (e.g., multiple ml.p3.2xlarge instances) enables data parallelism, splitting the workload across GPUs and significantly reducing wall-clock training time for large models or datasets.

Answer

Increase the instance's EBS volume size

Answer

Enable Managed Spot Training

Answer

Switch to a compute-optimized instance with more vCPUs

Question 6

A team is using Amazon SageMaker to train a model. The training job repeatedly fails with a 'ResourceLimitExceeded' error. Which action should the team take to resolve this issue?

Accepted Answer

Request a service limit increase for SageMaker resources.. The 'ResourceLimitExceeded' error in Amazon SageMaker indicates that the AWS account has reached a service quota for SageMaker resources, such as the number of concurrent training jobs, total instance count, or specific instance types. The correct action is to request a service limit increase via the AWS Service Quotas console or by contacting AWS Support, as this directly addresses the quota cap causing the failure.

Answer

Reduce the size of the training dataset.

Answer

Switch to using Spot Instances.

Answer

Use a different instance type with less memory.

Question 7

A data engineer is designing a data pipeline that ingests 500 GB of data daily from an on-premises Oracle database to Amazon S3. The pipeline must minimize data loss and support change data capture (CDC). Which combination of services should they use?

Accepted Answer

AWS Database Migration Service (DMS) with ongoing replication. AWS DMS with ongoing replication is the correct choice because it provides continuous change data capture (CDC) from an Oracle source database using Oracle LogMiner or binary reader technology, replicating transactions in near real-time to Amazon S3. This minimizes data loss by capturing incremental changes without requiring batch snapshots, and it supports the 500 GB daily volume efficiently with parallel tasks and task tuning.

Answer

AWS Data Pipeline with SQL query

Answer

Amazon Kinesis Data Streams with a custom Oracle CDC connector

Answer

AWS Glue ETL jobs running on a schedule

Question 8

A research team is training a deep learning model for image classification using Amazon SageMaker. The model is a convolutional neural network (CNN) with 50 layers. The team uses a single ml.p3.2xlarge instance. After 10 hours of training, the model has not converged and the loss is decreasing very slowly. The team suspects vanishing gradients. They want to diagnose and fix the issue without significant code changes. Which action should they take?

Accepted Answer

Modify the architecture to include residual connections (skip connections). Residual connections (skip connections) are a proven architectural solution to the vanishing gradient problem in deep networks. They allow gradients to flow directly through identity mappings, mitigating the degradation problem and enabling training of very deep networks like ResNet. This requires minimal code changes—just adding shortcut connections—and directly addresses the slow convergence and vanishing gradients described.

Answer

Add more convolutional layers to increase model capacity

Answer

Use batch normalization after each convolutional layer

Answer

Increase the learning rate by a factor of 10

Question 9

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 10

A data scientist is working with a dataset containing text reviews. The goal is to build a sentiment analysis model. Which EDA step is most critical before feature extraction?

Accepted Answer

Checking the distribution of sentiment labels. Checking the distribution of sentiment labels is critical before feature extraction because it reveals class imbalance, which can bias the model towards the majority class and affect evaluation metrics. This EDA step enables informed decisions about resampling or weighting techniques. Option A (vocabulary size) is not a critical first step; option B (word cloud) is a visualization tool, not essential; option C (removing stop words) is a preprocessing step, not part of EDA.

Answer

Calculating the vocabulary size

Answer

Creating a word cloud

Answer

Removing stop words

Question 11

A company is using Amazon SageMaker to train a deep learning model. The training job uses a script that reads data from Amazon S3 using the SageMaker SDK's `s3_input` method. The training job runs on a single ml.p3.2xlarge instance. The data scientist notices that the GPU utilization is very low during training, often below 20%. The training dataset is large, approximately 50 GB, stored as TFRecord files in S3. What is the MOST likely cause of low GPU utilization?

Accepted Answer

The data loading pipeline is not optimized, causing the GPU to wait for data.. Low GPU utilization (below 20%) with a large dataset (50 GB TFRecord) on a single GPU instance almost always indicates the input pipeline cannot feed data fast enough, so the GPU idles waiting for batches. This is a classic data-loading bottleneck: insufficient prefetching, too few parallel readers, small batch sizes, or reading directly from S3 without the Fast File Mode / Pipe Mode optimizations. Optimizing the tf.data pipeline (interleave, prefetch, parallel map, larger batch) is the fix.

Answer

The training script is using a CPU-only version of TensorFlow.

Answer

The batch size is too large, causing the GPU to run out of memory.

Answer

The instance type does not have enough GPU memory for the model.

Question 12

A data scientist is training a regression model. The training loss is decreasing but the validation loss starts to increase after a few epochs. Which technique should the scientist use to address this issue?

Accepted Answer

Implement early stopping based on validation loss.. The described pattern — training loss decreasing while validation loss increases — is the textbook signature of overfitting. Early stopping monitors validation loss and halts training when it stops improving (often with a patience parameter), preventing the model from memorizing the training data. This directly addresses the divergence between training and validation performance.

Answer

Decrease the batch size.

Answer

Add more layers to the model.

Answer

Increase the learning rate.

Question 13

A data scientist is analyzing a dataset with missing values. The missing data is not random and is correlated with other features. Which imputation method is most appropriate to minimize bias?

Accepted Answer

Multiple imputation using MICE. MICE (Multiple Imputation by Chained Equations) models each variable with missing values as a function of the other variables, generating multiple plausible imputations that preserve relationships and reduce bias when missingness is correlated with other features (MAR/MNAR). It is the most appropriate choice because it leverages the correlation structure rather than ignoring it.

Answer

Last observation carried forward

Answer

Listwise deletion

Answer

Mean imputation

Question 14

A team is using Amazon SageMaker Autopilot to automatically build models. The dataset has 50 features and 1 million rows. After training, Autopilot generates multiple candidates. The team wants to deploy the model with the highest accuracy. What is the best practice to select and deploy the model?

Accepted Answer

Deploy the candidate with the highest objective metric value from the Autopilot leaderboard. Amazon SageMaker Autopilot automatically generates a leaderboard ranking candidate models by their objective metric (e.g., accuracy, F1, AUC). The highest-ranked candidate represents the best-performing model based on the validation data, and deploying it directly is the recommended best practice. Autopilot handles preprocessing, algorithm selection, and hyperparameter tuning internally, so manual intervention is unnecessary.

Answer

Deploy all candidates behind a multi-model endpoint and route traffic based on request features

Answer

Select the model with the highest validation accuracy after performing additional hyperparameter tuning

Answer

Manually review each candidate's architecture and select the one with the simplest design

Question 15

A company wants to build a real-time anomaly detection system for IoT sensor data. The data arrives as a stream of numerical values. The model should adapt to concept drift over time. Which approach is most suitable?

Accepted Answer

Train an online learning model, such as stochastic gradient descent (SGD) with a sliding window. Online learning with stochastic gradient descent (SGD) using a sliding window allows the model to continuously update its parameters as new IoT sensor data arrives, adapting to concept drift without retraining from scratch. The sliding window ensures that the model focuses on the most recent data distribution, discarding outdated patterns, which is essential for real-time anomaly detection in streaming environments.

Answer

Use a static deep learning model trained once on historical data

Answer

Use a stateful LSTM with fixed weights

Answer

Batch train a random forest model monthly