MLS-C01 Practice Test 35 — 15 Questions

Question 1

A data scientist is building a recommender system using Amazon SageMaker. The dataset contains user-item interactions with implicit feedback (clicks). Which THREE evaluation metrics are appropriate for this use case?

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

Accepted Answer

Precision@k. For implicit feedback (e.g., clicks) in recommender systems, evaluation metrics should focus on ranking quality without requiring explicit negative labels. Precision@k measures the proportion of relevant items among top-k recommendations, Recall@k measures the proportion of relevant items retrieved in top-k, and Mean Average Precision (MAP) averages precision across multiple recall levels, all suitable for top-k recommendation tasks. RMSE is for explicit rating prediction and requires ground truth ratings, not applicable to implicit feedback. AUC-ROC is for binary classification with both positive and negative samples, but implicit feedback lacks explicit negatives, making it unsuitable.

Answer

Root Mean Squared Error (RMSE)

Answer

Area Under the ROC Curve (AUC-ROC)

Question 2

A data scientist is using Amazon SageMaker to train a model with the built-in K-Means algorithm. They have a dataset with 10,000 observations and want to segment them into 5 clusters. After training, they notice that the clusters are highly imbalanced, with one cluster containing over 90% of the data points. Which action should they take to improve cluster quality?

Accepted Answer

Standardize the features before training.. K-Means clustering relies on distance calculations, which are affected by feature scales. Unscaled features can dominate, causing skewed clusters. Standardizing features ensures each feature contributes equally, leading to more balanced and meaningful clusters. Other options do not directly address the scaling issue and may not resolve the imbalance.

Answer

Use a different distance metric such as Manhattan distance.

Answer

Increase the number of clusters to 10.

Answer

Reduce the number of features by removing less important ones.

Question 3

A data scientist is training a deep learning model for image classification. The model is overfitting on the training data. Which combination of techniques will most effectively reduce overfitting?

Accepted Answer

Add dropout layers and use data augmentation. Dropout layers randomly deactivate a fraction of neurons during training, which forces the network to learn more robust features and prevents co-adaptation. Data augmentation artificially expands the training dataset by applying transformations (e.g., rotation, flipping, cropping), which reduces the model's ability to memorize spurious patterns and improves generalization. Together, these techniques directly counteract overfitting by increasing regularization and effective training diversity.

Answer

Reduce the batch size

Answer

Train for more epochs without early stopping

Answer

Increase the number of layers and neurons

Question 4

A data scientist is training a model using Amazon SageMaker and wants to reduce the training time. The training job uses a single GPU instance. Which THREE actions can reduce training time?

Accepted Answer

Use distributed training across multiple GPU instances.. Option A is correct because distributed training across multiple GPU instances parallelizes the compute and data processing workload, so the model trains faster than on a single GPU. Option B is correct because Pipe input mode streams data directly from Amazon S3 to the training container instead of downloading the full dataset to local storage first, reducing startup and I/O overhead. Option C is correct because a larger instance type with more GPU memory and compute provides greater throughput per iteration, shortening overall training time. Option D is not correct because adding more training data increases the work the model must process, which generally lengthens training rather than reducing it. Option E is not correct because reducing the batch size means more iterations are needed to complete an epoch, which typically increases training time.

Answer

Increase the amount of training data.

Answer

Reduce the batch size.

Question 5

A company uses SageMaker to host a model for real-time predictions. The model is updated weekly. To minimize downtime during model updates, what should the company do?

Accepted Answer

Create a new endpoint configuration with the new model and update the endpoint to use the new configuration. SageMaker allows you to create a new endpoint configuration with the updated model and then update the existing endpoint to use this new configuration. This triggers a rolling update where SageMaker gradually shifts traffic from the old model to the new one, ensuring zero downtime during the transition. The endpoint remains available throughout the process, and you can roll back quickly if needed by reverting to the previous configuration.

Answer

Create a second endpoint with the new model and use an Application Load Balancer to route traffic

Answer

Update the existing endpoint configuration with the new model URL

Answer

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

Question 6

A data scientist is building a recommender system using Amazon SageMaker. The dataset contains user-item interactions with implicit feedback (clicks). Which THREE evaluation metrics are appropriate for this use case?

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

Accepted Answer

RecordIO-protobuf format with sparse features. SageMaker's built-in Factorization Machines algorithm expects training data in RecordIO-protobuf format, which efficiently encodes sparse features common in collaborative filtering (user-item matrices). RecordIO-protobuf reduces storage and network overhead by storing only non-zero entries, which is critical when the interaction matrix is extremely sparse. CSV would bloat the payload with zeros and slow training.

Answer

CSV format with all features as columns

Answer

JSON format with nested arrays

Answer

Parquet format

Question 7

A data scientist is training a binary classifier using logistic regression on a dataset that is highly imbalanced (95% negative class, 5% positive class). The model achieves 95% accuracy but only predicts the negative class. Which metric should the scientist use to evaluate the model's performance on the positive class?

Accepted Answer

Recall. Recall (also called sensitivity or true positive rate) measures the proportion of actual positive cases that are correctly identified by the model. In a highly imbalanced dataset where the model predicts only the negative class, recall for the positive class would be zero, making it the most informative metric to evaluate performance on the positive class.

Answer

Precision

Answer

F1 Score

Answer

Accuracy

Question 8

A data scientist is training a deep learning model using TensorFlow on Amazon SageMaker. The training job uses a single GPU instance but the GPU utilization is low. Which action is MOST likely to improve GPU utilization?

Accepted Answer

Increase the batch size. Increasing the batch size allows the GPU to process more data in parallel per training step, which keeps the GPU compute units busier and reduces idle time. In TensorFlow on SageMaker, a small batch size can cause the GPU to finish computation quickly and then wait for the next batch to be loaded, leading to low utilization. This is the most direct way to improve GPU throughput without changing the instance or model architecture.

Answer

Use a smaller instance type

Answer

Add more features

Answer

Decrease the number of epochs

Question 9

A data scientist is using AWS Glue to prepare training data. The job reads from an S3 bucket, performs transformations, and writes to another S3 bucket. The job is failing due to insufficient memory. Which solution should the data scientist use to fix this?

Accepted Answer

Increase the number of DPU (Data Processing Units) for the job.. The job is failing due to insufficient memory, which is a resource constraint. Increasing the number of DPU (Data Processing Units) allocates more memory and compute capacity to the AWS Glue job, directly addressing the out-of-memory error. This is the standard approach to scale Glue ETL jobs when they hit memory limits.

Answer

Use AWS Glue's job bookmark feature.

Answer

Use Amazon Athena instead of AWS Glue.

Answer

Use a columnar file format like Parquet.

Question 10

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) (B) is a wrapper method that repeatedly trains a model, ranks features by importance (e.g., coefficients), and prunes the weakest ones until the desired count remains, directly reducing the feature set and overfitting while keeping features interpretable. L1 regularization (Lasso) (C) adds a penalty equal to the absolute value of coefficients, which drives many coefficients exactly to zero, performing embedded feature selection that yields a sparse, interpretable model. Feature importance from a random forest (E) ranks features by their contribution to impurity reduction (Gini/entropy) or permutation importance, allowing the data scientist to retain only the top predictors and improve interpretability. PCA (A) is a dimensionality-reduction technique that creates new orthogonal components rather than selecting original features, so it harms interpretability and is not a feature-selection method. Adding random noise to features (D) is not a feature-selection technique at all; it degrades signal and does not reduce the feature count.

Answer

Principal Component Analysis (PCA)

Answer

Adding random noise to the features

Question 11

During exploratory data analysis, a data scientist notices that the distribution of a continuous feature is heavily right-skewed. Which transformation should be applied to make the distribution more symmetric for linear regression?

Accepted Answer

Log transformation. A log transformation compresses the right tail of a right-skewed distribution, pulling in extreme high values and making the distribution more symmetric — which satisfies the normality assumption of linear regression. It is the standard remedy for positive skew in continuous features.

Answer

Standardization (z-score)

Answer

One-hot encoding

Answer

Min-max scaling

Question 12

A data engineering team needs to orchestrate a complex workflow that involves multiple AWS Glue jobs, Lambda functions, and S3 operations. The workflow must run on a schedule and allow monitoring of each step. Which AWS service should they use?

Accepted Answer

AWS Step Functions. AWS Step Functions is a serverless orchestration service that lets you coordinate multiple AWS services, including AWS Glue jobs, Lambda functions, and S3 operations, into a state machine workflow. It provides built-in scheduling via Amazon EventBridge (formerly CloudWatch Events) and offers visual monitoring, logging, and error handling for each step, making it the ideal choice for complex, multi-step workflows that require observability.

Answer

Amazon Simple Workflow Service (SWF)

Answer

AWS Data Pipeline

Answer

Amazon CloudWatch Events

Question 13

A team has deployed a SageMaker endpoint for a sentiment analysis model. The model was trained on text data from social media. After deployment, the team notices that the model's accuracy has dropped significantly after 3 months. Which action should the team take to detect and address this issue?

Accepted Answer

Enable SageMaker Model Monitor to detect data drift and trigger a retraining pipeline.. B is correct because SageMaker Model Monitor is specifically designed to detect data drift (changes in the input data distribution over time) and model drift (degradation in prediction quality). When a sentiment analysis model trained on social media text sees a drop in accuracy after months, it is likely due to shifts in language, slang, or topics. Model Monitor can continuously track the distribution of input features and predictions against a baseline, and when drift is detected, it can automatically trigger a retraining pipeline to update the model, directly addressing the root cause of the accuracy drop.

Answer

Use SageMaker A/B testing to compare with a new model.

Answer

Re-deploy the model using the same training script.

Answer

Create a CloudWatch alarm on invocation errors.

Question 14

A team is deploying a model for fraud detection. The dataset is highly imbalanced (99% legitimate, 1% fraudulent). They trained a logistic regression model and achieved 99% accuracy on the test set. However, the model fails to detect most fraud cases. Which metric should the team focus on to evaluate the model?

Accepted Answer

Recall. Recall measures the proportion of actual positive cases (fraud) that were correctly identified. In a highly imbalanced dataset where fraud is only 1%, a model can achieve 99% accuracy by simply predicting 'legitimate' for all cases, but it would miss all fraud cases. Recall directly addresses the goal of detecting as many fraud cases as possible, making it the most relevant metric.

Answer

Mean squared error

Answer

Precision

Answer

Accuracy

Question 15

A data scientist is building a regression model to predict housing prices. The dataset includes numerical features such as square footage, number of bedrooms, and year built, as well as categorical features such as neighborhood and roof type. Which TWO preprocessing steps are most important to apply before training a linear regression model?

Accepted Answer

One-hot encode categorical features. Option B is correct because linear regression requires numeric inputs, and categorical features such as neighborhood and roof type must be converted into a numeric representation; one-hot encoding creates binary indicator columns for each category, allowing the model to estimate a separate coefficient per category without imposing a false ordinal relationship. Option E is correct because the numerical features (square footage, number of bedrooms, year built) are on very different scales, and standardizing (z-score) or normalizing them improves the conditioning of the least-squares problem and ensures regularized or gradient-based training treats features comparably. Option A is not required here: PCA is a dimensionality-reduction technique that can help with multicollinearity or high dimensionality, but it is not an essential preprocessing step for this small, interpretable feature set and would sacrifice interpretability. Option C is not mandatory: outlier removal via the IQR rule can be useful for robustness, but it is a data-cleaning choice rather than a required preprocessing step and may discard legitimate high-price observations. Option D is incorrect because adding interaction terms between all features is not a necessary preprocessing step and would inflate the feature space, risking overfitting and multicollinearity without being specifically justified by the scenario.

Answer

Apply principal component analysis (PCA) for dimensionality reduction

Answer

Remove outliers using IQR

Answer

Add interaction terms between all features