MLS-C01 Mock Exam 79 — 25 Questions

Question 1

Which THREE factors should be considered when choosing between SageMaker built-in algorithms and custom algorithms? (Choose THREE.)

Accepted Answer

Custom algorithms allow you to implement any architecture, including proprietary ones. Custom algorithms in SageMaker allow you to implement any architecture, including proprietary or novel models that are not available as built-in algorithms. This flexibility is essential when you need to use a custom neural network, a unique loss function, or a model from a research paper that SageMaker does not natively support.

Answer

Built-in algorithms can only be used with CSV and JSON formats

Answer

Custom algorithms require you to bring your own Docker container, but SageMaker built-in algorithms do not support frameworks like PyTorch

Question 2

A company is deploying a machine learning model to a SageMaker endpoint and wants to ensure that the endpoint is resilient to instance failures. Which THREE steps should the company take to achieve high availability? (Choose THREE.)

Accepted Answer

Deploy the endpoint in a VPC with subnets in at least two Availability Zones.. Deploying the endpoint in a VPC with subnets in at least two Availability Zones ensures that if one Availability Zone fails, the endpoint can still serve traffic from the other zone. SageMaker endpoints distribute instances across the specified subnets, so multi-AZ deployment provides fault isolation and high availability at the infrastructure level.

Answer

Use a single instance type with the largest size to handle capacity.

Answer

Use a single Availability Zone for simplicity.

Question 3

A data scientist is building a recommendation system for an e-commerce platform. The dataset includes user-item interactions (clicks, purchases, ratings). The scientist wants to use matrix factorization. Which approach is most appropriate for handling implicit feedback (e.g., clicks) rather than explicit ratings?

Accepted Answer

Use weighted alternating least squares (WALS) with confidence weights. Weighted Alternating Least Squares (WALS) is specifically designed for implicit feedback scenarios because it treats unobserved interactions as negative signals with low confidence, rather than missing values. By assigning confidence weights (e.g., based on click frequency or dwell time), WALS can factorize the implicit feedback matrix effectively, avoiding the bias introduced by treating all zeros as true negatives.

Answer

Use k-means clustering to segment users and then use item popularity within clusters

Answer

Use singular value decomposition (SVD) on the interaction matrix with missing values filled with 0

Answer

Use a deep neural network with a softmax output to predict item probabilities

Question 4

A data scientist is using Amazon SageMaker to deploy a model for real-time inference. The model is a TensorFlow neural network. The scientist wants to use automatic scaling based on the number of incoming requests. Which service integration is required?

Accepted Answer

Amazon SageMaker endpoint configured with Application Auto Scaling. Amazon SageMaker endpoints natively integrate with Application Auto Scaling to adjust the number of instances based on a target metric, such as the number of incoming requests per instance. This allows the TensorFlow model to scale automatically in response to traffic, without needing additional orchestration services.

Answer

Amazon ECS with service auto scaling

Answer

AWS Lambda with provisioned concurrency

Answer

AWS Auto Scaling plans

Question 5

A company is building a real-time fraud detection system using Amazon SageMaker. The model must have low latency (under 10ms) and high throughput (thousands of predictions per second). The team has trained a gradient boosting model using XGBoost. Which SageMaker inference option is MOST suitable?

Accepted Answer

Deploy the model on a SageMaker real-time endpoint with a multi-model endpoint.. A multi-model endpoint (MME) on SageMaker is the most suitable option because it allows you to host multiple XGBoost models on a single endpoint, sharing the underlying instance to maximize throughput and minimize latency. MMEs keep models loaded in memory and route requests to the correct model with sub-10ms overhead, meeting the low-latency and high-throughput requirements for real-time fraud detection.

Answer

Use SageMaker asynchronous inference.

Answer

Deploy the model on a SageMaker serverless endpoint.

Answer

Use a batch transform job.

Question 6

A company uses Amazon SageMaker to train a deep learning model for image classification. The training job is taking longer than expected. The data scientist observes that GPU utilization is low (around 30%) and CPU utilization is high. Which action is most likely to reduce training time?

Accepted Answer

Increase the number of data loading workers. Low GPU utilization with high CPU utilization indicates a data loading bottleneck where the CPU cannot prepare batches fast enough to keep the GPU busy. Increasing the number of data loading workers (e.g., SageMaker's `sagemaker.session.Session` or PyTorch `DataLoader` `num_workers`) allows parallel data preprocessing and I/O, reducing idle GPU time and overall training duration.

Answer

Reduce the batch size

Answer

Increase the batch size

Answer

Increase the learning rate

Question 7

A company is deploying a machine learning model for fraud detection. The model outputs a probability score. The cost of false negatives is very high. Which TWO metrics should the company focus on optimizing?

Accepted Answer

F1 score. Recall (true positive rate) measures ability to find positives; minimizing false negatives is optimizing recall. AUC-ROC summarizes overall performance but not specific to false negatives. Precision focuses on false positives. FPR is about false positives. F1 balances precision and recall, but recall directly addresses false negatives.

Answer

Precision

Answer

False positive rate (FPR)

Answer

Area under the ROC curve (AUC-ROC)

Question 8

A company is training a deep learning model for object detection using Amazon SageMaker. The training job is taking too long. Which TWO actions can reduce training time?

Accepted Answer

Use distributed training with multiple GPUs. Distributed training (A) reduces wall-clock time by splitting the workload across multiple GPUs. Using a smaller batch size initially and increasing gradually (warm-up) (D) can help stabilize training and speed convergence by allowing the model to adjust more smoothly early on. Managed spot training (C) reduces cost, not training time, and may increase time due to interruptions. A larger instance (B) does not necessarily reduce training time if the bottleneck is GPU-related, and increasing the number of epochs (E) increases training time.

Answer

Use a larger instance type with more vCPUs

Answer

Use SageMaker managed spot training

Answer

Increase the number of epochs

Question 9

A data scientist is using Amazon SageMaker to train an XGBoost model for a regression problem. The training data contains missing values in some features. Which approach should the data scientist use to handle missing values in XGBoost?

Accepted Answer

Leave missing values as-is; XGBoost handles them natively. XGBoost has a built-in mechanism to handle missing values natively by learning the best direction to split on missing values during training. For each split, XGBoost assigns missing values to the left or right child node based on which direction minimizes the loss function, making explicit imputation unnecessary for this algorithm.

Answer

Use K-nearest neighbors imputation

Answer

Remove all rows with missing values

Answer

Impute missing values with the mean of the column

Question 10

A data scientist is using Amazon SageMaker to train a random forest model for a binary classification task. The dataset has 50 features and 10,000 samples. The model achieves high training accuracy but poor test accuracy. Which TWO actions should the scientist take to improve generalization?

Accepted Answer

Reduce the max_depth of the trees.. The model is overfitting, as indicated by high training accuracy but poor test accuracy. To improve generalization, reduce model complexity. Reducing max_depth (B) limits the depth of each tree, preventing overly specific splits. Increasing min_samples_leaf (E) requires a minimum number of samples per leaf, which smooths the model and reduces variance. These two actions directly combat overfitting in random forests.

Answer

Increase the max_samples parameter.

Answer

Increase the max_features parameter.

Answer

Increase the number of trees (n_estimators).

Question 11

Refer to the exhibit. A developer has this IAM policy attached to an IAM role used by SageMaker. When attempting to create an endpoint, the operation fails with an access denied error. What is the MOST likely cause?

Accepted Answer

The policy is missing s3:ListBucket on the model bucket.. The error occurs because SageMaker needs to list objects in the S3 bucket where the model artifacts are stored before it can download them to create the endpoint. The attached policy grants s3:GetObject but not s3:ListBucket, which is required for the initial validation and listing of model artifacts in the bucket. Without s3:ListBucket, the CreateEndpoint API call fails with an access denied error.

Answer

The policy is missing ecr:DescribeRepositories.

Answer

The policy is missing sagemaker:DescribeEndpoint.

Answer

The policy is missing sagemaker:InvokeEndpoint.

Question 12

Which TWO factors should be considered when choosing between Amazon SageMaker's real-time endpoints and serverless inference? (Select TWO.)

Accepted Answer

GPU requirement. GPU requirement is a key factor because SageMaker real-time endpoints support GPU-based instances (e.g., ml.p3, ml.g4dn) for low-latency inference on deep learning models, while serverless inference only supports CPU instances. If your model requires GPU acceleration for acceptable latency, you must choose a real-time endpoint.

Answer

Integration with AWS Lambda

Answer

Availability of built-in algorithms

Answer

Model size in GB

Question 13

A data scientist is training a binary classification model on a dataset with 100 features and 10,000 rows. The model overfits significantly: training accuracy is 99%, but validation accuracy is 80%. The data scientist has tried L1 and L2 regularization without improvement. The dataset is clean and representative. Which approach is MOST likely to reduce overfitting? A. Increase the number of training epochs. B. Add more training data by generating synthetic samples using SMOTE. C. Reduce the number of features using PCA. D. Use a simpler model like logistic regression instead of a decision tree ensemble. The data scientist needs to maintain a validation accuracy above 85%, but the current model is too complex. The company has limited budget for data labeling. Which option is BEST?

Accepted Answer

Use a simpler model like logistic regression. The current model (likely a decision tree ensemble like Random Forest or XGBoost) is too complex for the dataset, causing overfitting. Switching to a simpler model like logistic regression reduces variance by limiting the hypothesis space, which directly addresses overfitting without requiring additional data or feature engineering. Given the limited labeling budget, this approach is cost-effective and can improve generalization, potentially achieving the required >85% validation accuracy.

Answer

Add more training data by generating synthetic samples using SMOTE

Answer

Reduce the number of features using PCA

Answer

Increase the number of training epochs

Question 14

A data scientist is trying to upload a CSV file to an S3 bucket using the AWS CLI without specifying server-side encryption. The upload fails with an AccessDenied error. Based on the bucket policy exhibit, what is the most likely cause?

Accepted Answer

The upload request did not specify the required server-side encryption.. The bucket policy requires that all PutObject requests include the x-amz-server-side-encryption header with value 'AES256'. Since the data scientist did not specify any encryption, the request was denied with AccessDenied. Option B is wrong because the error is AccessDenied, not NoSuchBucket. Option C is wrong because the data scientist may have permissions but the condition on encryption is not met. Option D is wrong because region mismatch would give a different error.

Answer

The bucket does not exist.

Answer

The data scientist does not have any permissions to the bucket.

Answer

The data scientist used the wrong AWS region.

Question 15

A data scientist is training a linear regression model on a dataset with 100 features. The model shows high variance on the test set. Which action is MOST likely to reduce overfitting?

Accepted Answer

Apply L2 regularization (Ridge regression). High variance (overfitting) means the model is too complex and fits noise in the training data. L2 regularization (Ridge regression) adds a penalty proportional to the square of the coefficients, shrinking them toward zero and reducing model complexity. This directly counteracts overfitting by preventing the model from relying too heavily on any single feature.

Answer

Use a more complex model like XGBoost

Answer

Increase the number of training iterations

Answer

Add more feature engineering to increase model complexity

Question 16

A company is using SageMaker to train a linear learner algorithm. The training log shows that the algorithm converges but the final loss is still high. Which change is most likely to improve the model?

Accepted Answer

Add feature crosses or polynomial features. A high final loss despite convergence indicates that the model is underfitting — the linear decision boundary is too simple to capture the underlying patterns in the data. Adding feature crosses or polynomial features increases the model's expressiveness by introducing non-linear interactions, allowing the linear learner to fit more complex relationships and reduce the loss.

Answer

Reduce the early stopping tolerance

Answer

Increase the maximum runtime

Answer

Increase the number of training instances

Question 17

A data scientist has this IAM policy attached to an IAM role used by SageMaker. When trying to create a training job, the scientist gets an access denied error. The training data is in 's3://my-bucket/training-data/'. What is the most likely cause?

Accepted Answer

Missing s3:ListBucket permission. The error occurs because the IAM policy grants s3:GetObject permission on the training data objects but lacks s3:ListBucket permission on the bucket itself. SageMaker's CreateTrainingJob API first performs a ListBucket call to verify the bucket exists and to enumerate objects, even if the exact object key is known. Without s3:ListBucket, the ListBucket call fails, resulting in an access denied error.

Answer

The bucket name is misspelled

Answer

The S3 resource ARN is incorrect

Answer

The sagemaker:CreateTrainingJob action is not allowed

Question 18

A data scientist is deploying a model to a SageMaker endpoint and needs to optimize for cost while maintaining low latency. Which TWO actions should the data scientist take?

Accepted Answer

Use SageMaker Serverless Inference. SageMaker Serverless Inference (Option D) automatically scales compute resources based on request volume, charging only for the compute time used during inference. This eliminates the cost of idle provisioned instances, making it ideal for optimizing cost while maintaining low latency for variable or intermittent traffic patterns.

Answer

Use a larger instance type

Answer

Deploy to a single instance

Answer

Switch to batch transform

Question 19

Which TWO statements about handling categorical variables in exploratory data analysis are correct? (Select TWO.)

Accepted Answer

When a categorical feature has high cardinality, consider grouping rare categories.. High-cardinality categorical features can lead to overfitting and sparse representations. Grouping rare categories into a single 'Other' bucket reduces dimensionality and noise, improving model generalization without losing significant predictive signal.

Answer

Target encoding always avoids data leakage.

Answer

Label encoding is suitable for nominal categorical variables.

Answer

Categorical variables should always be dropped if they have many unique values.

Question 20

A data scientist is performing feature selection for a classification problem with 100 features. The data scientist wants to reduce overfitting and improve model interpretability. Which THREE methods are appropriate for feature selection? (Choose THREE.)

Accepted Answer

Recursive Feature Elimination (RFE). Recursive Feature Elimination (RFE) is a wrapper method that recursively removes the least important features based on a model's feature weights or coefficients, training the model multiple times to identify the optimal subset. This directly reduces overfitting by eliminating irrelevant or redundant features and improves interpretability by keeping only the most predictive features.

Answer

Principal Component Analysis (PCA)

Answer

Adding random noise to the features