MLS-C01 Mock Exam 82 — 25 Questions

Question 1

A company uses SageMaker to deploy a model for real-time inference. The model is a large ensemble that requires 8 GB of memory and has high latency. The team wants to reduce latency without increasing cost. Which strategy is most effective?

Accepted Answer

Use SageMaker Neo to compile the model for the target instance.. Option D is correct because SageMaker Neo optimizes trained models for target hardware, reducing latency and memory footprint. Option A is wrong because using a larger instance increases cost. Option B is wrong because batch transform is for offline, not real-time. Option C is wrong because multiple instances increase cost.

Answer

Use a larger instance type with more memory.

Answer

Deploy the model on multiple instances behind a load balancer.

Answer

Switch from real-time inference to batch transform.

Question 2

A data scientist is training a binary classification model on an imbalanced dataset where the positive class represents only 5% of the data. The model currently achieves 95% accuracy but only 10% recall on the positive class. Which metric should the scientist focus on to improve the model's ability to detect the positive class?

Accepted Answer

Recall. Option B is correct because recall measures the ability to find all positive samples, which is the key issue in this imbalanced dataset. Option A is wrong because accuracy is misleading when classes are imbalanced. Option C is wrong because precision does not directly address the low recall. Option D is wrong because AUC-ROC is a global metric that may not reflect the improvement in recall.

Answer

Accuracy

Answer

Precision

Answer

AUC-ROC

Question 3

Which THREE of the following are valid strategies to reduce overfitting in a deep neural network? (Choose 3)

Accepted Answer

Use early stopping.. Option A is correct because L2 regularization penalizes large weights. Option C is correct because dropout randomly drops units to prevent co-adaptation. Option E is correct because early stopping prevents overfitting. Option B is wrong because increasing model capacity increases overfitting. Option D is wrong because increasing learning rate may cause divergence.

Answer

Increase the number of layers.

Answer

Increase the learning rate.

Question 4

A data scientist is using SageMaker to train a custom TensorFlow model. The training script reads data from S3 using TensorFlow's tf.data API. The training is bottlenecked by I/O. Which strategy would MOST effectively improve data throughput?

Accepted Answer

Use SageMaker Pipe mode and shard the S3 dataset. Using SageMaker Pipe mode with a sharded S3 dataset allows the training instances to stream data in parallel, reducing I/O bottlenecks. Increasing workers in tf.data may help but not as effectively as optimizing data ingestion. Using FSx for Lustre provides high throughput but adds cost and complexity.

Answer

Compress the data files in S3

Answer

Use Amazon FSx for Lustre as a mounted filesystem

Answer

Increase the number of parallel workers in tf.data

Question 5

A data scientist is building a recommendation system for an e-commerce platform. The dataset contains user interactions (clicks, purchases) and item metadata. The scientist wants to use matrix factorization. Which algorithm should be used?

Accepted Answer

SageMaker Factorization Machines. Option D is correct because SageMaker provides the Factorization Machines algorithm for recommendation and matrix factorization. Option A is wrong because XGBoost is for gradient boosting, not matrix factorization. Option B is wrong because BlazingText is for text. Option C is wrong because Image Classification is for images.

Answer

SageMaker Image Classification

Answer

SageMaker BlazingText

Answer

SageMaker XGBoost

Question 6

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 7

A data scientist is building a binary classification model to predict customer churn. The dataset is highly imbalanced, with only 5% of customers churning. The scientist evaluates several models using accuracy, precision, recall, and F1 score. Which metric is most appropriate for comparing model performance in this scenario?

Accepted Answer

F1 score. F1 score is the harmonic mean of precision and recall and is suitable for imbalanced datasets where accuracy can be misleading. Accuracy would be high even if the model predicts no churn ever (95% accuracy). Precision and recall each consider only one aspect, but F1 balances both.

Answer

Accuracy

Answer

Precision

Answer

Recall

Question 8

A data scientist is building a deep learning model using Amazon SageMaker. The model is overfitting the training data. Which THREE actions can help reduce overfitting?

Accepted Answer

Add L2 regularization to the loss function.. Overfitting can be reduced by regularization (L2), dropout, data augmentation (increases effective data size), early stopping, and reducing model complexity. Increasing model complexity (more layers) would increase overfitting (Option B). So correct: A, C, D.

Answer

Increase the number of layers in the network.

Answer

Reduce the learning rate.

Question 9

A company is building a model to classify customer reviews as positive or negative. The dataset has 10,000 positive and 100 negative reviews. Which metric is most appropriate for evaluating model performance?

Accepted Answer

F1 score.. Option B is correct because F1 score balances precision and recall, important for imbalanced datasets. Option A is wrong because accuracy can be misleading (e.g., 99% by predicting all positive). Option C is wrong because AUC-ROC can be optimistic for imbalanced data. Option D is wrong because mean squared error is for regression.

Answer

Accuracy.

Answer

Mean squared error.

Answer

AUC-ROC.

Question 10

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?

Accepted Answer

Increase the batch size to better saturate the GPU.. Option B is correct because increasing batch size provides more work per GPU step, improving utilization. Option A is wrong because decreasing batch size reduces utilization. Option C is wrong because switching to CPU would be slower. Option D is wrong because reducing data increases risk of underfitting.

Answer

Reduce the training dataset size.

Answer

Switch to a CPU-only instance.

Answer

Decrease the batch size to reduce memory pressure.

Question 11

A data scientist is training a linear regression model and wants to handle multicollinearity among features. Which TWO actions are appropriate?

Accepted Answer

Use Ridge regression (L2 regularization). Ridge regression (L2) adds a penalty that can reduce the impact of correlated features. Removing one of the correlated features directly addresses multicollinearity. Lasso (L1) may also help but is less effective for groups of correlated features. Scaling features does not remove collinearity. Adding interaction terms increases multicollinearity.

Answer

Add interaction terms between features

Answer

Use Lasso regression (L1 regularization)

Answer

Scale all features to have zero mean and unit variance

Question 12

A company is fine-tuning a BERT model on Amazon SageMaker for a text classification task. The training script uses PyTorch and Hugging Face Transformers. The training job completes successfully, but the final model accuracy is low. The dataset has 10,000 labeled samples. What is the most likely cause and solution?

Accepted Answer

The model is overfitting due to small dataset; use a pre-trained checkpoint and fine-tune only top layers. Option C is correct because BERT is large and 10,000 samples may not be enough; using a pre-trained checkpoint and doing transfer learning is standard. Option A (learning rate) is possible but not most likely. Option B (SageMaker error) is unlikely. Option D (instance type) doesn't affect accuracy directly.

Answer

The instance type is insufficient; use a larger instance

Answer

The learning rate is too high; reduce it

Answer

The training script has a bug in the data loader

Question 13

A data scientist is working with a dataset containing categorical features with high cardinality. The scientist wants to use a tree-based model. Which encoding method should be used?

Accepted Answer

Ordinal encoding. Option C is correct because tree-based models can handle ordinal encoding naturally. Option A is wrong because one-hot encoding creates many dimensions, not ideal for high cardinality. Option B is wrong because label encoding may impose ordinal relationship. Option D is wrong because target encoding may cause overfitting.

Answer

Target encoding

Answer

Label encoding

Answer

One-hot encoding

Question 14

A machine learning team is using Amazon SageMaker to build a regression model. The target variable is heavily right-skewed with a long tail. Which data transformation should the team apply to the target variable before training?

Accepted Answer

Log transformation. A log transformation compresses the range of the target and makes the distribution more symmetric, improving model performance.

Answer

One-hot encoding

Answer

Min-max scaling

Answer

Standardization (z-score)

Question 15

A data scientist is using Amazon SageMaker built-in XGBoost algorithm to train a regression model. The training job completes successfully but the model performance on the test set is poor, with high bias. Which hyperparameter adjustment is most likely to help reduce bias?

Accepted Answer

Increase the max_depth parameter.. High bias (underfitting) can be reduced by increasing the model complexity. Increasing max_depth allows more complex trees. Decreasing max_depth would increase bias. Increasing gamma increases regularization and bias. Reducing num_round (number of trees) reduces complexity.

Answer

Reduce the num_round parameter.

Answer

Increase the gamma parameter.

Answer

Decrease the max_depth parameter.

Question 16

Refer to the exhibit. A data scientist ran a SageMaker training job and reviewed the logs. The training completed quickly, but the model performance is very poor. What is the most likely cause?

Accepted Answer

The training dataset is too small for the model complexity.. The training ran for only about 1 minute, which is too short for a typical training. The model likely didn't converge. This indicates that the training job might have been configured with too few epochs or the data was very small, or the algorithm stopped early. The logs show 'Training completed' quickly. The most likely cause is that the training job used a very small number of epochs or early stopping criteria caused premature termination. Option C (model overfitting) would show longer training and high training accuracy. Option D (data leakage) would show good performance. Option A (insufficient training data) could cause poor performance, but the logs show training completed quickly, suggesting the job didn't run long enough. Option B (incorrect learning rate) could cause divergence but would still train for the specified epochs. The quick completion suggests the job was configured with too few epochs or early stopping. But among the options, A (insufficient training data) is plausible. However, the question says 'most likely'. I'll choose B (incorrect learning rate) because if the learning rate is too high, the loss may explode and cause early stopping or NaN, leading to quick termination. But the log doesn't show errors. Actually, the log shows normal completion. So it's likely the model didn't train enough. Option B: If learning rate is too low, training can be slow but still complete epochs. The quick completion suggests the number of epochs was small. But the options don't mention epochs. Option A: insufficient training data would still train for the number of epochs. Option C: overfitting would not cause quick completion. Option D: data leakage would give good performance. So I'm leaning towards B: incorrect learning rate (too high) could cause the loss to become NaN and training to stop, but the log says 'Training completed' not 'Stopped'. It might be that the training completed all epochs because of a small dataset. Actually, the log shows 'Training completed' after 1 minute, so it might have finished all epochs. If the dataset is very small, training could be fast. That would lead to poor performance due to insufficient data. So A is plausible. I'll go with A.

Answer

The model is overfitting to the training data.

Answer

There is data leakage from the test set into the training set.

Answer

The learning rate is too low, causing slow convergence.

Question 17

A data scientist is using Amazon SageMaker to deploy a custom model container. The model is a large transformer that requires 16 GB of memory. The scientist wants to minimize inference latency. Which SageMaker hosting option should they choose?

Accepted Answer

Use a real-time endpoint with an instance that has sufficient memory.. Option B is correct because multi-model endpoints allow multiple models to share resources, but for a single large model, a real-time endpoint with a suitable instance is best. Option A is wrong because serverless inference has memory limits (up to 6 GB) and may cold start. Option C is wrong because batch transform is for offline. Option D is wrong because asynchronous inference introduces latency for processing requests.

Answer

Use an asynchronous inference endpoint.

Answer

Use SageMaker Serverless Inference.

Answer

Use a batch transform job.

Question 18

A data scientist is using Amazon SageMaker to build a text classification model. The dataset has 100,000 labeled samples and 20 classes. The scientist wants to use a pre-trained BERT model and fine-tune it. Which approach is MOST cost-effective?

Accepted Answer

Fine-tune a pre-trained BERT-base model using a GPU instance.. Option A is correct because using a small BERT variant like BERT-base reduces computational cost while still being effective. Option B is wrong because training from scratch is expensive. Option C is wrong because using the full BERT-large is overkill. Option D is wrong because using a CNN from scratch would require more data and training.

Answer

Train a BERT model from scratch using a larger instance.

Answer

Use a pre-trained BERT-large model with a larger instance.

Answer

Train a CNN model from scratch using CPU instances.

Question 19

A team is training a deep learning model on Amazon SageMaker. The training job is slow because the data is stored in S3 as many small files. Which approach is MOST effective to improve training throughput?

Accepted Answer

Use SageMaker Pipe mode for training input. Using SageMaker Pipe mode streams data directly from S3, reducing startup time. Shuffling files or increasing instance count does not address the small file overhead. Using EFS would introduce latency.

Answer

Increase the number of ml.c5.xlarge instances

Answer

Shuffle the S3 objects to randomize order

Answer

Use Amazon EFS instead of S3

Question 20

A data scientist is evaluating a binary classification model. The model's AUC-ROC is 0.95. Which TWO statements are true?

Accepted Answer

The model has excellent discriminative ability. AUC-ROC measures the model's ability to distinguish between classes across all thresholds. A high AUC (close to 1) indicates good performance. AUC-ROC is threshold-independent. It does not directly indicate accuracy or calibration.

Answer

The model has no false positives

Answer

The model is well-calibrated

Answer

The model's accuracy is at least 95%