MLS-C01 Practice Test 21 — 15 Questions

Question 1

A company is building a real-time fraud detection system using Amazon SageMaker. The model is a gradient boosting classifier trained on 500 GB of transactional data. The inference endpoint is deployed as a SageMaker real-time endpoint using an ml.c5.9xlarge instance. The model is serialized using the native format of the framework (XGBoost). The endpoint receives about 100 requests per second with an average payload size of 10 KB. The company observes that the endpoint's latency is around 200 ms, but they need under 100 ms. The data scientist profiles the endpoint and finds that the model inference time is 50 ms, but the remaining time is spent on data preprocessing and serialization/deserialization. The preprocessing involves converting JSON input to a NumPy array and then to a DMatrix. Which action is most likely to reduce latency to meet the requirement?

Accepted Answer

Use a more efficient serialization format such as Apache Arrow or Protocol Buffers for the input data. Option D is correct. By using SageMaker Batch Transform, the company can process requests in batches, reducing per-request overhead. However, the requirement is for real-time, so this may not be suitable. Option A is wrong because larger instances may not reduce preprocessing overhead. Option B is wrong because reducing model complexity could hurt accuracy. Option C is wrong, but it's a plausible approach: using a more efficient serialization format (e.g., Protocol Buffers) can reduce deserialization time. Actually, option C is correct: using a more efficient data format reduces preprocessing time. Option D is wrong because batch transform is for asynchronous, not real-time. The correct answer should be C. Let me re-evaluate: The stem says 'remaining time is spent on data preprocessing and serialization/deserialization.' Using a more efficient serialization format (e.g., Protobuf instead of JSON) can reduce overhead. Option A: upgrading instance may not help if the bottleneck is serialization. Option B: reducing model complexity may affect accuracy. Option D: batch transform is not real-time. So C is best.

Answer

Switch to SageMaker Batch Transform to process requests in batches

Answer

Use a larger instance type such as ml.c5.18xlarge

Answer

Reduce the number of trees in the model

Question 2

A data scientist is using Amazon SageMaker to train a deep learning model using a built-in algorithm. The training job uses an ml.p3.2xlarge instance and takes 10 hours to complete. The scientist wants to reduce training time without changing the algorithm or model architecture. The instance's GPU utilization is consistently at 95%, but CPU utilization is only 20%. The data input pipeline uses SageMaker Pipe mode with the 'TrainingInputMode' set to 'Pipe'. The training dataset is 200 GB in CSV format stored in S3. Which approach is most likely to reduce training time?

Accepted Answer

Use a larger instance type with more GPUs, such as ml.p3.8xlarge. Option D is correct. Since GPU utilization is high (95%), the GPU is the bottleneck. Upgrading to a more powerful GPU instance (e.g., p3.8xlarge with 4 GPUs) can reduce training time by parallelizing computation. Option A is wrong because File mode may not help and could increase I/O overhead. Option B is wrong because Pipe mode is already being used. Option C is wrong because reducing batch size could underutilize GPU further.

Answer

Switch from Pipe mode to File mode to reduce I/O overhead

Answer

Use Pipe mode with 'S3DataType' as 'AugmentedManifestFile'

Answer

Reduce the batch size to improve GPU utilization

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. SMOTE and undersampling are standard techniques for handling 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 company uses SageMaker to deploy a real-time inference endpoint for a fraud detection model. The model is an XGBoost model trained on 50 features. The endpoint receives 100 requests per second, but latency is higher than the required 200 ms. The team wants to reduce latency without retraining. What should they do?

Accepted Answer

Reduce the number of features by selecting the most important ones. Reducing features directly lowers latency. Elastic Inference does not apply to XGBoost.

Answer

Increase the number of instances behind the endpoint

Answer

Use SageMaker's batch transform instead of real-time endpoint

Question 5

A data scientist is training a model using SageMaker and wants to use spot instances to reduce costs. Which THREE considerations should the scientist evaluate? (Choose THREE.)

Accepted Answer

The training job must support checkpointing to save progress.. Option A is correct because spot instances can be interrupted, so the training job must be checkpointed to resume. Option C is correct because spot instances are typically cheaper, but they can be reclaimed, affecting cost savings if interruptions are frequent. Option D is correct because model training is often fault-tolerant and can handle interruptions. Option B is wrong because spot instances are dynamically priced, not fixed. Option E is wrong because spot instances are available for training, not just inference.

Answer

Spot instances have a fixed, lower price than on-demand.

Answer

Spot instances are only available for inference, not training.

Question 6

A machine learning engineer is training a deep learning model on Amazon SageMaker. The training job is taking a long time. Which THREE actions can reduce training time? (Choose 3.)

Accepted Answer

Use SageMaker managed spot training. Warm pools, distributed training, and spot training can reduce training time.

Answer

Use a smaller batch size

Answer

Use SageMaker hyperparameter tuning jobs

Question 7

A machine learning team is building a fraud detection system using Amazon SageMaker. The training data is highly imbalanced (99% legitimate, 1% fraudulent). They need to maximize the recall of the fraud class while keeping precision above 90%. Which approach should they take?

Accepted Answer

Train a model using the original data, then adjust the decision threshold on the validation set to maximize recall while precision > 90%. Option D is correct because adjusting the model threshold after training to favor recall while monitoring precision is the most direct way to meet the business requirement. Option A (SMOTE) can help but may not guarantee precision. Option B (weighted loss) is good but less direct than threshold tuning. Option C (random undersampling) may discard too much data.

Answer

Undersample the majority class to create a balanced dataset and train a Random Forest

Answer

Train an XGBoost model with scale_pos_weight parameter set to 99

Answer

Use SMOTE to oversample the fraud class and then train a logistic regression

Question 8

An ML team is using Amazon SageMaker to train a model. They notice that the training job is taking longer than expected and the CloudWatch metrics show high GPU utilization but low CPU utilization. Which action is MOST likely to improve training speed?

Accepted Answer

Use SageMaker Pipe mode to stream data from S3 to reduce I/O bottleneck. Option B is correct because high GPU utilization indicates the GPU is busy, but low CPU may indicate a bottleneck in data loading; using Pipe mode can reduce I/O wait. Option A (increase instance count) may help if the job is parallelizable but not if the bottleneck is data loading. Option C (increase GPU memory) does not address data loading. Option D (use CPU instance) would slow down training.

Answer

Switch to a CPU-only instance to avoid GPU overhead

Answer

Increase the number of training instances

Answer

Use a larger GPU instance with more GPU memory

Question 9

A data scientist wants to deploy a PyTorch model for real-time inference with latency under 100 ms. Which AWS service is most suitable?

Accepted Answer

Amazon SageMaker real-time endpoint. Option B is correct because Amazon SageMaker real-time endpoints provide low-latency inference. Option A (SageMaker Batch Transform) is for batch predictions, not real-time. Option C (Lambda) has limited runtime and scalability for large models. Option D (SageMaker Processing) is for data processing, not inference.

Answer

Amazon SageMaker Processing

Answer

AWS Lambda with container image

Answer

Amazon SageMaker Batch Transform

Question 10

A healthcare company is building a model to predict patient readmission within 30 days. They have structured electronic health records (EHR) data with 200 features. The data includes missing values, categorical variables with high cardinality (e.g., diagnosis codes), and a severe class imbalance (5% readmission). They need to deploy a model on SageMaker that is interpretable and achieves high recall for the positive class. Which combination of techniques should they use?

Accepted Answer

Use XGBoost with SMOTE, feature selection via SHAP, and deploy as a SageMaker endpoint. XGBoost with SMOTE and SHAP balances interpretability and performance.

Answer

Use logistic regression with one-hot encoding and random undersampling

Answer

Use PCA for dimensionality reduction, then train a linear SVM with class weights

Answer

Use a deep neural network with embeddings for categorical variables and oversample the minority class

Question 11

A data scientist is training a binary classification model on an imbalanced dataset (95% negative class, 5% positive class). The model currently achieves 94% accuracy but a recall of only 0.10 on the positive class. Which TWO strategies should the data scientist consider to improve recall without significantly sacrificing precision? (Choose 2.)

Accepted Answer

Assign higher class weights to the positive class in the loss function.. Oversampling the minority class (option A) increases the number of positive examples, which helps the model learn better decision boundaries for the positive class. Using class weights (option B) penalizes misclassifications of the minority class more heavily, encouraging the model to focus on positive examples. Both techniques directly address class imbalance. Option C (undersampling) may discard useful negative samples and harm performance. Option D (increasing regularization) typically reduces overfitting but does not specifically improve recall. Option E (using a deeper network) may increase overfitting and does not target recall directly.

Answer

Undersample the majority class to match the minority class size.

Answer

Increase the regularization strength to reduce overfitting.

Answer

Use a deeper neural network with more layers.

Question 12

A company is using SageMaker's built-in image classification algorithm to classify product images into 100 categories. The training takes 3 hours on a single p3.2xlarge instance. They need to reduce training time to under 1 hour. They have access to a cluster of 4 p3.2xlarge instances. Which approach should they take?

Accepted Answer

Use SageMaker's distributed training with data parallelism using Horovod. Distributed training with data parallelism effectively reduces training time.

Answer

Use SageMaker's hyperparameter tuning to find faster convergence

Answer

Use a smaller batch size on each instance

Answer

Use SageMaker's managed spot training with checkpointing

Question 13

A company deploys a SageMaker model for inference. After a few days, response times increase significantly. CloudWatch metrics show high CPU utilization and memory usage. The model is a large ensemble. What is the most cost-effective solution?

Accepted Answer

Configure SageMaker automatic scaling based on CPU utilization. Option C is correct: automatic scaling adds instances based on demand, handling spikes cost-effectively. Option A (ad hoc monitoring) does not automatically adjust. Option B (migrate to Lambda) may not support large models. Option D (increase instance size) is less cost-effective than scaling out.

Answer

Use CloudWatch alarms to notify the team, who manually launch additional endpoints

Answer

Migrate the model to AWS Lambda with provisioned concurrency

Answer

Replace the current instance type with a larger one

Question 14

A data scientist has this IAM policy attached to their IAM role. They are trying to run a SageMaker training job that reads data from 'my-bucket' and writes output to 'my-bucket'. The job fails. What is the most likely reason?

Accepted Answer

Missing iam:PassRole permission. Option B is correct: the policy does not grant permission to pass the execution role to SageMaker (iam:PassRole). Option A is incorrect because s3:GetObject and s3:PutObject are present. Option C is incorrect because the actions are allowed. Option D is irrelevant.

Answer

The sagemaker:CreateTrainingJob action is not allowed on specific resources

Answer

Missing s3:ListBucket permission on the bucket

Answer

The training job requires permissions to write to CloudWatch Logs

Question 15

A data scientist uses SageMaker to train a model and wants to automatically stop the training job if the loss is not improving after a certain number of steps. Which feature should be used?

Accepted Answer

SageMaker Debugger. SageMaker Debugger can monitor loss and trigger actions like stopping the job. Option D is correct. Option A is wrong because automatic tuning is for hyperparameter optimization. Option B is wrong because Experiments is for tracking. Option C is wrong because Ground Truth is for labeling.

Answer

SageMaker Experiments

Answer

SageMaker Automatic Model Tuning

Answer

SageMaker Ground Truth