MLS-C01 Practice Test 36 — 15 Questions

Question 1

A DevOps engineer runs the CloudWatch Logs Insights query shown above on the log group for an ML training job. The result shows a spike in ERROR messages at a specific hour. What should the engineer do next to identify the root cause?

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

Accepted Answer

Modify the query to display the actual @message for the hour with the spike.. Modifying the query to include the @message field for the specific hour with the spike allows the engineer to see the actual error messages, which is the direct way to identify the root cause. Option B is incorrect because removing the filter would show all messages, which is less targeted. Option C is incorrect because changing the bin to 5m might be too granular and not helpful without examining the messages. Option D is incorrect because increasing the limit does not help identify the cause without seeing the messages.

Answer

Remove the filter on ERROR to see all messages.

Answer

Change the bin to 5m to see more detailed spikes.

Answer

Increase the limit to 50 to see more hours.

Question 2

A data scientist needs to deploy a PyTorch model for real-time inference. Which AWS service is best suited for this task?

Accepted Answer

Amazon SageMaker real-time endpoint. Amazon SageMaker real-time endpoints are purpose-built for hosting ML models that require low-latency, synchronous inference. They automatically manage the underlying infrastructure, including scaling, load balancing, and health checks, and support custom PyTorch containers via the SageMaker inference toolkit. This makes them the optimal choice for deploying a PyTorch model for real-time inference.

Answer

Amazon SageMaker Batch Transform

Answer

Amazon ECS with Fargate

Answer

AWS Lambda with custom container

Question 3

A data scientist needs to perform hyperparameter optimization for a gradient boosting model. Which built-in Amazon SageMaker feature should they use?

Accepted Answer

Amazon SageMaker Automatic Model Tuning. Amazon SageMaker Automatic Model Tuning (A) is the built-in feature specifically designed for hyperparameter optimization. It automates the search for the best combination of hyperparameters by launching multiple training jobs with different hyperparameter values, using strategies like Bayesian optimization, random search, or Hyperband. This directly addresses the data scientist's need to optimize a gradient boosting model's hyperparameters.

Answer

Amazon SageMaker Clarify

Answer

Amazon SageMaker Debugger

Answer

Amazon SageMaker Neo

Question 4

A data scientist is building a classification model to predict customer churn. The dataset has 10,000 samples with 100 features. After training a logistic regression model, the scientist observes that the model has high variance (overfitting). Which technique can reduce overfitting?

Accepted Answer

Use L2 regularization (Ridge). L2 regularization (Ridge) adds a penalty proportional to the square of the coefficients to the loss function, which shrinks coefficients and reduces model variance, thereby mitigating overfitting. It is a standard technique for high-variance models like logistic regression with many features. By penalizing large weights, it improves generalization on unseen data.

Answer

Remove the regularization term

Answer

Add polynomial features

Answer

Use a smaller learning rate

Question 5

A company has customer feedback data stored in CSV files in S3. The data includes a 'feedback_text' column. Which AWS service is best suited for performing sentiment analysis as part of exploratory data analysis?

Accepted Answer

Amazon Comprehend. Amazon Comprehend is a fully managed NLP service that includes a built-in sentiment analysis API (DetectSentiment) which classifies text as POSITIVE, NEGATIVE, NEUTRAL, or MIXED. It is purpose-built for analyzing customer feedback text stored in S3, and integrates natively with S3 and Lambda for batch or real-time processing. This makes it the correct choice for sentiment analysis during exploratory data analysis.

Answer

Amazon Rekognition

Answer

Amazon Textract

Answer

Amazon Lex

Question 6

A data analyst is performing exploratory data analysis on a dataset with 100 features. The analyst wants to identify which features contribute most to the variance in the data. Which technique should the analyst use?

Accepted Answer

Principal Component Analysis (PCA). PCA is a dimensionality reduction technique that identifies the principal components — linear combinations of features — that capture the maximum variance in the data. It directly answers the analyst's goal of finding which features contribute most to variance. The resulting components are ranked by explained variance ratio.

Answer

K-means clustering

Answer

t-Distributed Stochastic Neighbor Embedding (t-SNE)

Answer

Linear Discriminant Analysis (LDA)

Question 7

A machine learning engineer needs to deploy a model that requires custom inference code with dependencies. Which SageMaker deployment option should be used?

Accepted Answer

Create a custom Docker container and deploy to SageMaker endpoint.. When a model requires custom inference code with dependencies, the only way to fully control the runtime environment, libraries, and inference logic is to package everything into a custom Docker container. SageMaker endpoints can then deploy this container, allowing the engineer to specify the exact inference script and dependencies (e.g., via a Dockerfile and a requirements.txt). This approach supports any framework or custom logic that built-in algorithms cannot provide.

Answer

Use a SageMaker notebook instance as an endpoint.

Answer

Use a built-in SageMaker algorithm.

Answer

Use a SageMaker batch transform job.

Question 8

A data engineer is performing EDA on a dataset with 1 million rows and 200 columns. The dataset is stored in S3 as CSV files. The engineer notices that some columns have a high proportion of zeros. What is the best approach to determine if these zeros represent missing data or actual zero values?

Accepted Answer

Consult the data source documentation or domain experts to understand the meaning of zero values.. Domain knowledge and documentation are the most reliable ways to understand the meaning of zeros. Option A is wrong because statistical methods cannot distinguish missing vs actual zero without context. Option B is wrong because metadata may not have this detail. Option C is wrong because comparing to other columns might be misleading.

Answer

Check correlation of zero columns with other features; if low, assume zeros are missing.

Answer

Calculate the percentage of zeros and compare with other columns; if unusually high, treat as missing.

Answer

Use AWS Glue Data Catalog to view column statistics and infer missing values.

Question 9

Which TWO of the following are benefits of feature scaling for machine learning algorithms?

Accepted Answer

Faster convergence of gradient descent. Feature scaling, typically via standardization (z-score) or min-max normalization, ensures that gradient descent converges faster. Without scaling, features with larger numerical ranges dominate the gradient updates, causing the algorithm to oscillate and require more iterations to reach the optimum. Scaling produces a more spherical contour of the loss function, allowing gradient descent to take more direct steps toward the minimum.

Answer

Eliminates the effect of outliers

Answer

Reduces the need for feature selection

Answer

Improves performance of decision tree algorithms

Question 10

A machine learning engineer is evaluating a multi-class classification model that predicts product categories. The model outputs probabilities for 10 classes. The engineer wants to improve the model's calibration so that the predicted probabilities reflect the true likelihood of each class. Which THREE techniques can help?

Accepted Answer

Use temperature scaling. Temperature scaling (A) is correct because it divides the logits by a single learned scalar T before the softmax, directly adjusting the confidence of the 10-class probability outputs without changing the predicted class, making it the standard post-hoc calibration method for multi-class neural networks. Isotonic regression (B) is correct because it is a non-parametric calibration technique that fits a monotonic mapping from predicted probabilities to empirical frequencies, and it can be applied per-class or in a multiclass extension (e.g., one-vs-rest) to improve calibration. Platt scaling (D) is correct because it fits a logistic (sigmoid) transformation on the model's scores to produce calibrated probabilities, and although originally binary, it is commonly extended to multi-class via one-vs-rest or multiclass variants. Increasing model complexity (C) is not a calibration technique; it typically affects discrimination and can even worsen overconfidence rather than aligning probabilities with true likelihoods. Focal loss (E) is a training objective that reweights hard examples to address class imbalance, not a post-hoc or training-time calibration method for making predicted probabilities reflect true frequencies.

Answer

Increase model complexity

Answer

Use focal loss

Question 11

A data scientist is performing EDA on a time-series dataset and observes a strong upward trend and seasonal patterns. The scientist needs to make the data stationary for modeling. Which transformation should be applied?

Accepted Answer

Apply differencing to the series. Differencing is a technique that removes trends and seasonality by subtracting the previous observation from the current one, making the time series stationary. One-hot encoding (A) is used for categorical variables. PCA (B) reduces dimensionality but does not address stationarity. Min-max scaling (C) normalizes the range of data but does not remove trend or seasonality. Logarithmic transformation (E) stabilizes variance but does not eliminate trends. Therefore, differencing (D) is the correct choice.

Answer

Apply one-hot encoding

Answer

Apply PCA

Answer

Apply min-max scaling

Answer

Apply logarithmic transformation

Question 12

A company is designing a data pipeline to process log files from multiple sources. The logs are written to Amazon S3 every hour. The data is then transformed using AWS Glue ETL jobs and loaded into Amazon Redshift for analysis. The company needs to ensure that the data is available for analysis within 30 minutes of being written to S3. Currently, the Glue job is triggered hourly, but the company wants to reduce the latency. Which solution should the company implement?

Accepted Answer

Use Amazon S3 event notifications to invoke an AWS Lambda function that starts the Glue job automatically. The requirement is to reduce latency so that data is available for analysis within 30 minutes of being written to S3. Currently, the Glue job runs hourly, which is too slow. Using S3 event notifications to trigger a Lambda function that starts the Glue job immediately upon new data arrival ensures the ETL process begins as soon as data is written, minimizing latency. This event-driven approach is more efficient than scheduled triggers.

Answer

Increase the frequency of the Glue crawler to run every 5 minutes

Answer

Use Amazon Redshift Spectrum to query the data directly from S3 without transformation

Answer

Reduce the Glue job trigger frequency to every 15 minutes

Question 13

A company's machine learning model is overfitting to the training data. The data scientist has already tried reducing the model complexity and adding regularization, but the model still overfits. Which technique could the data scientist use to further reduce overfitting?

Accepted Answer

Use data augmentation to increase the training dataset size. Data augmentation artificially increases the size and diversity of the training dataset by applying transformations (e.g., rotations, flips, noise injection) to existing samples. This exposes the model to more varied examples, reducing its tendency to memorize noise and improving generalization — directly countering overfitting when other methods have failed.

Answer

Decrease the batch size

Answer

Increase the number of training epochs

Answer

Increase the learning rate

Question 14

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.. Option A is correct because adding L2 regularization (weight decay) to the loss function penalizes large weights, which constrains model complexity and reduces overfitting. Option B is correct because data augmentation synthetically expands the training set with transformed samples, giving the model more varied data and improving generalization. Option E is correct because dropout layers randomly deactivate neurons during training, preventing the network from relying on specific units and acting as a strong regularizer. Option C is not correct because increasing the number of layers raises model capacity, which typically worsens overfitting. Option D is not correct because reducing the learning rate only affects optimization speed and stability, not the model's tendency to overfit.

Answer

Increase the number of layers in the network.

Answer

Reduce the learning rate.

Question 15

A data analyst is examining the distribution of a continuous variable and notices that its histogram is heavily skewed to the right. Which transformation should the analyst apply to make the distribution more symmetrical?

Accepted Answer

Logarithmic transformation (log).. A logarithmic transformation compresses the right tail of a right-skewed distribution, pulling in large values and making the distribution more symmetrical and closer to normal. It is the standard remedy for positive right skew, especially when the data spans orders of magnitude. Box-Cox is a family that includes log (lambda=0), but lambda=2 is a square transformation that would worsen right skew, not fix it.

Answer

Box-Cox transformation with lambda=2.

Answer

Standardization (z-score).

Answer

Square root transformation.