MLS-C01 Practice Test 23 — 15 Questions

Question 1

A company is deploying a machine learning model for real-time fraud detection. The model must have low latency (under 100 ms) and high throughput. The data scientist trains a gradient boosting model and deploys it to a SageMaker endpoint with a single ml.c5.xlarge instance. During load testing, the endpoint exceeds the latency threshold. Which change is MOST likely to reduce latency?

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

Accepted Answer

Replace the model with a simpler model, such as logistic regression. Replacing the gradient boosting model with a simpler model like logistic regression reduces the computational complexity per inference. Gradient boosting involves traversing many decision trees, each requiring multiple conditional checks and arithmetic operations, while logistic regression is a single linear transformation. This directly lowers CPU utilization per request, reducing latency under the same instance resources.

Answer

Use a larger instance type, such as ml.c5.4xlarge

Answer

Switch to batch transform for inference

Answer

Enable automatic scaling on the endpoint

Question 2

A company is using SageMaker to host a model that performs real-time fraud detection. The model receives high request volumes with occasional spikes. The company wants to ensure that the endpoint can handle spikes without throttling while minimizing cost. Which scaling strategy should be used?

Accepted Answer

Use a target tracking scaling policy with a target value of 70% for the SageMakerVariantInvocationsPerInstance metric.. A target tracking scaling policy with the SageMakerVariantInvocationsPerInstance metric is the correct choice because it automatically adjusts the instance count to maintain a target utilization (e.g., 70%), handling spikes without manual intervention while minimizing cost by scaling down during low traffic. This is the recommended approach for real-time endpoints with variable traffic, as it aligns with AWS best practices for dynamic scaling.

Answer

Use a simple scaling policy with a step adjustment based on the InvocationsPerInstance metric.

Answer

Manually adjust the instance count based on monitoring dashboards.

Answer

Use a scheduled scaling action to add instances during peak hours.

Question 3

A company uses Amazon SageMaker to deploy a model that predicts customer churn. The model is retrained weekly. The data scientist notices that the model's accuracy remains high, but the business reports that the model is not capturing new churn patterns. What is the most likely cause?

Accepted Answer

The model is experiencing concept drift. Concept drift occurs when the statistical properties of the target variable change over time, causing the model's predictions to become less relevant even if accuracy metrics remain high. In this scenario, the model is retrained weekly but still fails to capture new churn patterns because the underlying customer behavior has shifted—a classic sign of concept drift rather than a data or overfitting issue. Amazon SageMaker's built-in Model Monitor can detect such drift by comparing inference data distributions against a baseline.

Answer

The model is underfitting the data

Answer

The model has data leakage from future data

Answer

The model is overfitting to the training data

Question 4

A company is using Amazon SageMaker to train a model on a dataset with many categorical features. They want to use SageMaker's built-in Linear Learner algorithm. What preprocessing step is required for the categorical features?

Accepted Answer

Apply one-hot encoding to convert them to numerical vectors.. The SageMaker Linear Learner algorithm requires numerical input features. Categorical features must be converted to numerical vectors, typically via one-hot encoding, because the algorithm performs linear regression or classification on numerical data. Without this preprocessing, the algorithm cannot interpret categorical values directly.

Answer

Use label encoding to assign integers to categories.

Answer

Normalize the categorical features using min-max scaling.

Answer

Remove categorical features with high cardinality.

Question 5

A data scientist is using SageMaker to train an XGBoost model for regression. The training data contains categorical features with high cardinality (e.g., zip code with over 10,000 unique values). Which feature engineering approach is MOST appropriate to avoid overfitting while preserving predictive power?

Accepted Answer

Use target encoding with smoothing. Target encoding with smoothing is the most appropriate approach because it replaces each high-cardinality category with the mean of the target variable for that category, regularized by a smoothing factor that pulls estimates toward the global mean. This preserves predictive power by capturing the relationship between the category and the target while preventing overfitting on rare categories that have few samples. In SageMaker XGBoost, this avoids the curse of dimensionality from one-hot encoding and the arbitrary ordering from label encoding.

Answer

One-hot encode the categorical features

Answer

Apply frequency encoding based on category occurrence

Answer

Label encode the categorical features

Question 6

A data scientist is using Amazon SageMaker to train a linear regression model. The training job fails with the error: 'AlgorithmError: Input data has NaN values'. Which step should the data scientist take to resolve this issue?

Accepted Answer

Impute missing values or remove rows with NaN values. The error 'AlgorithmError: Input data has NaN values' indicates missing values in the dataset. Linear regression cannot handle NaN values. The appropriate action is to either impute missing values (e.g., using mean/median) or remove rows with NaN values. Option A (convert to sparse format) is used for handling zero values, not missing values, and will not resolve NaN errors. Option B (switch to a different algorithm) is unnecessary because data preprocessing can fix the issue; moreover, many algorithms also cannot handle NaN. Option C is correct. Option D (increase training instances) only adds more compute resources and does not fix data quality issues.

Answer

Convert the data to a sparse format

Answer

Switch to a different algorithm that handles missing values

Answer

Increase the number of training instances

Question 7

A data scientist is training a deep learning model on a large dataset using Amazon SageMaker. The training job is taking too long. The scientist notices that GPU utilization is low and data loading is the bottleneck. Which action should the scientist take to improve training performance?

Accepted Answer

Use Pipe mode for the training data channel. Low GPU utilization with a data loading bottleneck indicates that the CPU cannot feed data to the GPU quickly enough. SageMaker's Pipe mode streams training data directly from S3 without first downloading it to the instance's local storage, reducing I/O overhead and improving data throughput. Option A: Increasing the number of training instances does not address the per-instance data loading bottleneck; each GPU would still be underutilized. Option C: Changing to a CPU instance would be slower because CPUs are less efficient for deep learning training. Option D: Reducing the batch size would decrease GPU utilization further, exacerbating the underutilization problem.

Answer

Increase the number of training instances

Answer

Change the instance type to a CPU instance

Answer

Reduce the batch size

Question 8

A company wants to serve predictions from a model using a REST API with low latency. Which SageMaker deployment option is most appropriate?

Accepted Answer

SageMaker real-time endpoint. SageMaker real-time endpoints are designed for low-latency inference, deploying the model behind an HTTPS endpoint that autoscales to handle request traffic. This directly meets the requirement for serving predictions via a REST API with minimal latency, as the endpoint keeps the model loaded and ready to respond to individual requests in milliseconds.

Answer

SageMaker Notebook instance

Answer

SageMaker Processing job

Answer

SageMaker Batch Transform

Question 9

An e-commerce company uses Amazon DynamoDB as the primary data store for user sessions. They want to run analytics on historical session data using Amazon Athena. What is the recommended approach to export DynamoDB data to S3 in a format optimized for Athena?

Accepted Answer

Use AWS Glue ETL to read from DynamoDB and write to S3 as Parquet. AWS Glue ETL can read from DynamoDB and write to S3 in Parquet format, which is optimized for Athena due to its columnar storage and compression. Option A (AWS Data Pipeline) can copy data to S3 as CSV, but CSV is less efficient for Athena and Data Pipeline is a legacy service. Option B (Amazon Kinesis Data Firehose) is designed for streaming data, not for exporting existing DynamoDB tables. Option C (DynamoDB Streams with Lambda) writes to S3 as JSON, which is less performant than Parquet for Athena queries and adds operational complexity.

Answer

Use AWS Data Pipeline to copy data to S3 as CSV

Answer

Use Amazon Kinesis Data Firehose to stream data from DynamoDB to S3

Answer

Use DynamoDB Streams with AWS Lambda to write to S3 as JSON

Question 10

A data scientist is training a classification model on an imbalanced dataset where the positive class represents only 5% of the data. Which technique would BEST address the class imbalance without discarding data?

Accepted Answer

Use SMOTE to generate synthetic samples for the minority class. SMOTE (Synthetic Minority Oversampling Technique) is the best choice because it generates synthetic samples for the minority class by interpolating between existing minority instances, effectively balancing the dataset without discarding any data. This avoids the information loss of undersampling and the overfitting risk of simple random oversampling, making it ideal for a 5% positive class scenario.

Answer

Randomly undersample the majority class

Answer

Adjust the decision threshold to 0.95

Answer

Randomly oversample the minority class with replacement

Question 11

A company is using Amazon SageMaker to host a real-time inference endpoint for a natural language processing model. The endpoint is configured with an ml.m5.large instance. After deployment, the company observes that the inference latency is higher than expected, and the endpoint is experiencing CPU utilization near 100% during peak hours. The model is a PyTorch model that uses a transformer architecture. The company wants to reduce latency without increasing cost significantly. Which approach should the company take?

Accepted Answer

Change the endpoint instance type to ml.g4dn.xlarge to use GPU acceleration.. The endpoint is CPU-bound on an ml.m5.large (CPU-only) instance running a transformer model, causing high latency and 100% CPU. Switching to an ml.g4dn.xlarge instance provides GPU acceleration, which is well-suited for transformer inference and can dramatically reduce latency. The cost increase is moderate compared to scaling out many CPU instances, and it addresses the root cause (CPU saturation).

Answer

Configure the endpoint with Auto Scaling to add more instances during peak hours.

Answer

Switch to batch transform for inference.

Answer

Attach an Elastic Inference accelerator to the existing instance.

Question 12

A company uses Amazon SageMaker to train a model for fraud detection. The training data is highly imbalanced. The data scientist uses SMOTE to oversample the minority class. However, the model still has poor recall on the minority class. Which additional technique should the data scientist consider?

Accepted Answer

Use class weights in the loss function. SMOTE generates synthetic samples for the minority class, but it does not directly address the model's tendency to prioritize the majority class during training. By assigning higher class weights to the minority class in the loss function, the model penalizes misclassifications of minority samples more heavily, which directly improves recall on that class. This technique is especially effective when combined with oversampling, as it forces the optimizer to focus on the underrepresented class during gradient updates.

Answer

One-vs-rest encoding

Answer

L1 regularization

Answer

Principal component analysis (PCA)

Question 13

A machine learning engineer is deploying a model to an Amazon SageMaker endpoint. The model is a PyTorch model that requires a custom inference script. The engineer notices that the endpoint is returning 500 errors after deployment. Which step should the engineer take to debug the issue?

Accepted Answer

View the CloudWatch Logs for the endpoint.. When a SageMaker endpoint returns 500 errors, it typically indicates an application-level failure in the inference container, such as an unhandled exception in the custom inference script. CloudWatch Logs capture the stdout and stderr of the container, including Python tracebacks, which directly reveal the root cause. Option D is correct because viewing these logs is the first and most effective step to diagnose the specific error.

Answer

Redeploy the endpoint with a different instance type.

Answer

Check the CloudWatch metrics for the endpoint.

Answer

Modify the inference script and update the endpoint.

Question 14

A data pipeline uses AWS Glue to crawl an S3 bucket and create a table in the AWS Glue Data Catalog. The data is in Parquet format with partitions by date. After a new partition is added to S3, the crawler runs but the new partition is not reflected in the table. What is the most likely cause?

Accepted Answer

The new partition folder does not follow the Hive-style partition naming convention expected by the crawler.. AWS Glue crawlers rely on Hive-style partition naming (e.g., year=2024/month=01/day=15/) to detect and register partitions in the Data Catalog. If the new partition folder is named differently — such as 2024/01/15/ without the key=value format — the crawler will not recognize it as a partition and the table will not be updated. This is the most common cause of missing partitions after a crawler run.

Answer

The crawler requires an AWS Lambda trigger to be configured for new partitions.

Answer

The Parquet schema in the new partition does not match the existing table schema.

Answer

The S3 bucket has too many partitions, exceeding the Glue crawler limit.

Question 15

Which TWO techniques can help reduce overfitting in a decision tree model?

Accepted Answer

Limit the maximum depth of the tree. Limiting the maximum depth of the tree (option C) is correct because it constrains how finely the model can partition the feature space, preventing the tree from growing deep enough to memorize noise in the training data. Pruning the tree after training (option D) is correct because post-pruning removes branches that provide little predictive power on validation data, reducing variance and thus overfitting. Increasing the number of trees in the forest (option A) applies to ensemble methods like Random Forest and does not reduce overfitting in a single decision tree. Increasing the number of features considered per split (option B) tends to make the tree more complex and can worsen overfitting. Increasing the maximum depth of the tree (option E) directly allows more splits and greater model complexity, which increases overfitting rather than reducing it.

Answer

Increase the number of trees in the forest

Answer

Increase the number of features considered per split

Answer

Increase the maximum depth of the tree