MLS-C01 Practice Test 45 — 15 Questions

Question 1

A data scientist is training a deep learning model for image classification using TensorFlow on Amazon SageMaker. The model trains slowly, and the GPU utilization is below 20%. Which action will MOST effectively increase GPU utilization and reduce training time?

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

Accepted Answer

Increase the batch size to better saturate the GPU.. Increasing batch size provides more work per GPU step, improving utilization. Option A is wrong because reducing dataset size does not directly improve GPU utilization and may lead to underfitting. Option C is wrong because switching to CPU would be slower. Option D is wrong because decreasing batch size reduces the work per step, lowering GPU utilization and increasing training time.

Answer

Reduce the training dataset size.

Answer

Switch to a CPU-only instance.

Answer

Decrease the batch size to reduce memory pressure.

Question 2

A company is deploying a machine learning model using Amazon SageMaker. The model needs to be updated frequently with new data. Which TWO approaches can be used to update the model without downtime? (Choose TWO.)

Accepted Answer

Use SageMaker A/B testing to gradually shift traffic to the new model variant.. Option C is correct because SageMaker A/B testing (production variants on a single endpoint) lets you deploy a new model variant alongside the existing one and gradually shift traffic to it, so users continue to be served without downtime. Option E is correct because a blue/green deployment runs the new model on a separate endpoint and then switches traffic (e.g., via DNS/Route 53 weighted records or an endpoint update), allowing a safe cutover with no service interruption. Option A is wrong because deleting the existing endpoint removes the serving capacity and causes downtime before the new endpoint is available. Option B is wrong because you cannot directly modify a model artifact in a live endpoint configuration; SageMaker endpoints are immutable and require creating a new endpoint configuration and updating the endpoint. Option D is wrong because stopping the endpoint takes the model offline, producing downtime during the update and restart.

Answer

Delete the existing endpoint and create a new one with the updated model.

Answer

Directly update the model artifact in the existing endpoint configuration.

Answer

Stop the endpoint, update the model, and restart the endpoint.

Question 3

A company is building a fraud detection model that must achieve low false positive rates. The dataset is highly imbalanced (0.1% positive class). Which metric is most appropriate for model evaluation?

Accepted Answer

Area under the Precision-Recall curve. In highly imbalanced datasets (0.1% positive class), the Precision-Recall curve focuses on the performance of the positive class, which is the minority class of interest. Area under the Precision-Recall curve (AUPRC) is insensitive to the large number of true negatives, making it a robust metric for evaluating models where false positives must be minimized. Unlike ROC-AUC, which can be overly optimistic in severe imbalance, AUPRC directly reflects the trade-off between precision and recall for the rare positive class.

Answer

RMSE

Answer

Accuracy

Answer

R-squared

Question 4

A data scientist is using Amazon SageMaker to train a linear regression model. After training, the scientist notices that the model has a high bias. What is the most likely cause?

Accepted Answer

The model is too simple and underfits the data. High bias means the model consistently makes large errors because it is too simple to capture the underlying patterns in the data — this is underfitting (D). A linear regression model with high bias typically lacks the complexity or features needed to represent the true relationship, so it performs poorly on both training and validation data. The fix is to increase model complexity, add relevant features, or reduce regularization strength.

Answer

The training dataset has too many features

Answer

The model is too complex and overfits the data

Answer

The regularization parameter is too high

Question 5

A data scientist is training a deep learning model for image classification using TensorFlow on Amazon SageMaker. The model trains slowly, and the GPU utilization is below 20%. Which action will MOST effectively increase GPU utilization and reduce training time?

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

Accepted Answer

The account has reached the limit for the number of GPU instances in the current AWS Region.. The 'ResourceLimitExceeded' error in SageMaker specifically indicates that the training job requested more instances (or a specific instance type) than the account's service quota allows in that AWS Region. GPU instances like ml.p3.2xlarge have default quotas that are often low for new accounts, and launching multiple instances can exceed the limit. The fix is to request a quota increase via Service Quotas.

Answer

The training script has a syntax error.

Answer

The dataset is too large for the selected instance type.

Answer

The S3 bucket containing the training data has insufficient permissions.

Question 6

A data scientist uses SageMaker Studio to run EDA on a dataset with 500 features. The goal is to reduce dimensionality before modeling. Which EDA technique should the data scientist use to understand the variance explained by each feature?

Accepted Answer

Scree plot of principal components. A Scree plot from PCA shows the eigenvalues or variance explained by each principal component, helping decide how many components to retain. Option A is wrong because a histogram shows distribution, not variance. Option C is wrong because a heatmap of correlations shows pairwise relationships, not variance. Option D is wrong because a box plot shows summary statistics.

Answer

Histogram of the target variable

Answer

Heatmap of feature correlations

Answer

Box plot of each feature

Question 7

A data scientist needs to choose an algorithm for a regression problem with 50 features and 1 million training examples. The model must be interpretable and the training data fits in memory. Which algorithm is most appropriate?

Accepted Answer

Linear regression. Linear regression is inherently interpretable — coefficients directly show the effect of each feature on the target — and it scales efficiently to 1 million rows with 50 features when the data fits in memory. It satisfies both the interpretability requirement and the computational constraints. More complex models like XGBoost may perform better but sacrifice the transparency the question demands.

Answer

Principal Component Analysis (PCA)

Answer

XGBoost

Answer

k-Nearest Neighbors

Question 8

Which TWO SageMaker features can be used to monitor and debug training jobs? (Choose 2.)

Accepted Answer

SageMaker Debugger. SageMaker Debugger (A) is correct because it provides real-time monitoring and debugging of training jobs by capturing tensors, gradients, and other metrics during training, allowing you to detect issues like vanishing gradients or overfitting. Amazon CloudWatch Logs (D) is correct because it automatically collects and stores logs from SageMaker training jobs, including algorithm output and framework logs, which you can monitor for errors or anomalies.

Answer

SageMaker Model Monitor

Answer

SageMaker Ground Truth

Answer

SageMaker Clarify

Question 9

A company deploys a SageMaker endpoint for real-time inference. After a week, the response latency increases from 50 ms to 500 ms. CPU utilization is at 30%. What is the most likely cause?

Accepted Answer

The inference code makes a call to a downstream service that is throttling requests. CPU utilization is only 30%, which rules out compute saturation, and the latency degraded gradually over a week rather than abruptly — consistent with a downstream dependency (e.g., a feature store, database, or third-party API) beginning to throttle requests. The inference container waits on the throttled call, inflating end-to-end latency while its own CPU stays idle.

Answer

The model has a memory leak

Answer

The instance type is underpowered for the inference load

Answer

The SageMaker endpoint is experiencing a network outage

Question 10

A data scientist is analyzing a dataset with 500 features and 10,000 rows. The target variable is binary. After training a logistic regression model, the coefficients show many non-zero values but the model has low accuracy on the test set. Which EDA step should the data scientist perform next to improve model performance?

Accepted Answer

Use correlation analysis or mutual information to select the most relevant features.. With 500 features and low accuracy, the model likely suffers from overfitting due to irrelevant or redundant features. Correlation analysis or mutual information helps select the most relevant features, reducing noise and improving generalization. Option A (PCA) reduces dimensionality but creates uninterpretable components and may lose feature relationships, not directly addressing irrelevant features. Option B (collect more data) may help but does not solve the core issue of irrelevant features. Option C (normalization) only scales features, not reduce them, and logistic regression is not sensitive to scale if coefficients are interpreted carefully; overfitting is more likely due to too many features.

Answer

Apply Principal Component Analysis (PCA) to reduce dimensionality.

Answer

Collect more training data to improve generalization.

Answer

Normalize the features using StandardScaler.

Question 11

A data scientist is using Amazon SageMaker to train a model. The training data is stored in an S3 bucket encrypted with AWS KMS. During training, the job fails with an access denied error. What is the MOST likely cause?

Accepted Answer

The SageMaker execution role lacks kms:Decrypt permission for the KMS key. SageMaker needs permission to use the KMS key to decrypt the data; the execution role must have kms:Decrypt permissions.

Answer

The training instance type does not support encryption

Answer

The training data is not in the same region as the SageMaker notebook

Answer

The S3 bucket policy does not allow SageMaker to list objects

Question 12

Which THREE of the following are appropriate data visualization techniques for exploring the relationship between two numerical variables?

Accepted Answer

Scatter plot. Scatter plot, hexbin plot, and pair plot are designed for bivariate numerical relationships. Bar chart is for categorical. Box plot is for numerical vs categorical.

Answer

Box plot

Answer

Bar chart

Question 13

During exploratory data analysis, a data scientist notices that the target variable is highly imbalanced. Which technique should be used to address this issue before training a classification model?

Accepted Answer

Use SMOTE to generate synthetic samples for the minority class. SMOTE (Synthetic Minority Over-sampling Technique) is a popular method for handling imbalanced datasets by generating synthetic samples for the minority class. Option A (PCA) is wrong because dimensionality reduction does not address class imbalance. Option B (removing outliers) is wrong because it may worsen imbalance and is not a standard technique for imbalance. Option C (cross-validation) is a model evaluation technique, not a solution for imbalance. Option D (feature scaling) does not affect class distribution.

Answer

Apply PCA to reduce dimensionality

Answer

Remove outliers from the majority class

Answer

Use cross-validation to evaluate the model

Answer

Apply feature scaling to all features

Question 14

A financial institution is using Amazon SageMaker to train a binary classification model to detect fraudulent transactions. The dataset is highly imbalanced, with only 0.5% of transactions being fraudulent. The data scientist wants to improve the model's ability to identify fraud without significantly increasing false positives. Which of the following approaches is most appropriate when using the SageMaker built-in XGBoost algorithm?

Accepted Answer

Set the 'scale_pos_weight' hyperparameter to the ratio of negative to positive samples.. For imbalanced binary classification with XGBoost, setting 'scale_pos_weight' to the ratio of negative to positive samples is a standard and effective technique. It adjusts the gradient updates to give more weight to the minority class, improving recall without drastically increasing false positives. Other options do not directly address the imbalance.

Answer

Reduce the number of training epochs to prevent overfitting.

Answer

Use the 'objective' hyperparameter set to 'binary:logistic' and rely on default settings.

Answer

Increase the 'max_depth' hyperparameter to allow the model to learn more complex patterns.

Question 15

Which TWO statements about handling missing data during exploratory data analysis are correct? (Select TWO.)

Accepted Answer

Visualizing the pattern of missingness can help determine if data is missing at random.. Options B and C are correct. Visualizing the pattern of missingness helps determine if data is missing at random, which is a key EDA step. Understanding the missing data mechanism (MCAR, MAR, MNAR) is important for selecting an appropriate imputation strategy. Option A is incorrect because missing values should be addressed during EDA, not deferred to model training. Option D is incorrect because listwise deletion can introduce bias if data is not MCAR. Option E is incorrect because mean imputation reduces the variance of the imputed variable.

Answer

Missing values can be ignored during EDA and handled during model training.

Answer

Listwise deletion (removing rows with missing values) is always safe and unbiased.

Answer

Imputing missing values with the mean preserves the original variance.