MLS-C01 Practice Test 12 — 15 Questions

Question 1

A machine learning engineer is working on a regression problem to predict house prices. The dataset contains 500,000 rows and 20 features, including 'sqft_living', 'bedrooms', 'bathrooms', 'floors', 'waterfront', 'view', 'condition', 'grade', 'yr_built', 'zipcode', and 'lat'. After performing exploratory data analysis, the engineer notices that the 'sqft_living' feature has a right-skewed distribution with a long tail. The 'zipcode' feature is categorical with 70 unique values. The 'lat' feature is continuous. The engineer wants to prepare the data for a linear regression model. Which action should the engineer take to improve model performance?

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

Accepted Answer

Apply a log transformation to the 'sqft_living' feature.. Linear regression assumes that features are approximately normally distributed, and a right-skewed distribution like 'sqft_living' can violate this assumption, leading to poor model performance. Applying a log transformation compresses the long tail, making the distribution more symmetric and helping the model learn a linear relationship between the feature and the target. This is a standard preprocessing step for skewed features in regression tasks.

Answer

Remove the 'sqft_living' feature because it violates the normality assumption.

Answer

One-hot encode the 'zipcode' feature to capture location effects.

Answer

Apply standard scaling (z-score) to the 'sqft_living' feature.

Question 2

A data scientist is using Amazon SageMaker to train a linear regression model. The dataset has outliers. Which TWO techniques can help reduce the impact of outliers? (Choose TWO.)

Accepted Answer

Trim the dataset to remove extreme values. Option A is correct because trimming (or winsorizing) the dataset removes or caps extreme values, so the linear regression fit is no longer dominated by outliers that would otherwise pull the coefficients disproportionately. Option D is correct because Huber loss behaves quadratically for small residuals but linearly for large residuals, so outliers contribute bounded gradients and have far less influence on the learned coefficients than with squared error. Option B is not appropriate because adding features does not address the influence of outliers and can even worsen overfitting. Option C is not appropriate because L1 regularization penalizes coefficient magnitude to induce sparsity, not to down-weight outlier residuals. Option E is not appropriate because standardization only rescales features to zero mean and unit variance; it does not reduce the leverage or residual impact of outliers.

Answer

Add more features

Answer

Apply L1 regularization

Answer

Standardize the features

Question 3

A team is training a deep learning model on Amazon SageMaker using a large dataset stored in S3. The training job is taking a long time, and the team suspects that data loading is the bottleneck. The dataset consists of many small files (average size 10KB). Which change would most effectively reduce the I/O bottleneck?

Accepted Answer

Combine the small files into larger files (e.g., TFRecord format). Combining small files into larger ones (e.g., TFRecord or Parquet) reduces the number of S3 GET requests and improves throughput. Using Pipe mode reads data sequentially, which is less efficient for random access. Increasing instance count or using P3 instances addresses compute, not I/O. Amazon EFS is not recommended for training jobs due to higher latency.

Answer

Use SageMaker Pipe mode instead of File mode

Answer

Increase the number of training instances

Answer

Use a P3 instance type for better GPU performance

Question 4

Which TWO metrics are suitable for evaluating a regression model? (Select TWO.)

Accepted Answer

Root Mean Squared Error (RMSE). Root Mean Squared Error (RMSE) (B) is correct because it is a standard regression metric that measures the average magnitude of prediction errors by taking the square root of the mean of squared differences between predicted and actual continuous values, expressed in the same units as the target. R-squared (C) is also correct because it quantifies the proportion of variance in the dependent variable explained by the model, making it a common goodness-of-fit measure for regression. Accuracy (A) is not suitable because it is a classification metric that requires exact matches of discrete labels, which is meaningless for continuous predictions. F1-score (D) and Precision (E) are classification metrics derived from the confusion matrix (true/false positives and negatives) and do not apply to regression tasks.

Answer

Accuracy

Answer

F1-score

Answer

Precision

Question 5

A data scientist is training a binary classification model on an imbalanced dataset where the positive class represents only 1% of the data. The model achieves 99% accuracy but fails to identify most positive cases. Which metric should the data scientist use to evaluate model performance?

Accepted Answer

F1 score. The F1 score is the harmonic mean of precision and recall, making it ideal for imbalanced datasets where accuracy is misleading. Since the model achieves 99% accuracy by simply predicting the majority class (negative), it fails to capture positive cases; F1 score penalizes this by balancing false positives and false negatives, providing a more truthful performance measure.

Answer

R-squared

Answer

Accuracy

Answer

RMSE

Question 6

A machine learning engineer is deploying a model on SageMaker and needs to ensure that the endpoint can handle a sudden spike in traffic. The engineer expects traffic to increase by 10x during a promotional event. Which scaling strategy should be used?

Accepted Answer

Use scheduled scaling to add instances before the event, combined with dynamic scaling for the remaining duration.. Scheduled scaling lets you pre-provision endpoint instances at a known future time (the promotional event), so capacity is already in place when the 10x traffic spike begins — avoiding the lag inherent in reactive scaling. Combining it with dynamic scaling (target-tracking on InvocationsPerInstance or CPU) covers any traffic beyond the scheduled baseline and handles the post-event wind-down, giving both proactive and reactive coverage.

Answer

Use a single large instance type instead of multiple smaller instances.

Answer

Manually increase the instance count before the event.

Answer

Use only dynamic scaling based on the average latency metric.

Question 7

A machine learning engineer needs to deploy a model that performs real-time fraud detection. The model must be highly available and scalable. Which AWS service should be used to host the model?

Accepted Answer

Amazon SageMaker real-time endpoint. Amazon SageMaker real-time endpoints are designed for low-latency, synchronous inference, making them ideal for real-time fraud detection. They automatically scale across multiple instances and Availability Zones, providing high availability and elasticity to handle variable traffic loads without manual intervention.

Answer

AWS Lambda

Answer

Amazon ECS with a custom container

Answer

Amazon SageMaker batch transform

Question 8

A company is using Amazon SageMaker to deploy a machine learning model for real-time inference. The model was trained using XGBoost and achieves high accuracy. However, during deployment, the endpoint returns a 'ModelError' when receiving input data. The input is a CSV string. What is the most likely cause?

Accepted Answer

The input data format does not match the model's expected format (e.g., CSV vs JSON). A 'ModelError' on a SageMaker endpoint receiving a CSV string most commonly occurs when the input format does not match what the model's container expects. For example, an XGBoost model trained with a specific content type (e.g., text/csv or application/json) will fail if the InvokeEndpoint call sends a mismatched ContentType or a malformed CSV (wrong number of columns, headers included when not expected). The container's input_fn parses the payload and raises an error on mismatch.

Answer

The inference instance type is too small

Answer

The model is not properly loaded into memory

Answer

The model weights are corrupted during deployment

Question 9

Which TWO AWS services can be used to transform data in transit before storing it in Amazon S3? (Choose TWO.)

Accepted Answer

AWS Glue. AWS Glue is correct because it provides a serverless data integration service that can transform data in transit using its built-in transformation jobs (e.g., PySpark scripts) before writing the results to Amazon S3. This allows you to clean, enrich, or reshape streaming or batch data as it moves through the pipeline.

Answer

Amazon Redshift Spectrum

Answer

AWS Data Pipeline

Answer

Amazon Athena

Question 10

A team wants to move data from an on-premises Oracle database to Amazon S3 for analytics. The pipeline must run daily and handle incremental updates. Which THREE services should they use together? (Choose three.)

Accepted Answer

Amazon S3. Amazon S3 is the correct destination for storing the data because it provides a scalable, durable, and cost-effective object storage solution ideal for analytics workloads. The pipeline requires daily incremental updates, and S3 integrates seamlessly with AWS DMS for continuous replication and AWS Glue for ETL processing, making it the central storage layer for the analytics pipeline.

Answer

Amazon SageMaker

Answer

Amazon Athena

Question 11

A company is using Amazon SageMaker to train a model. The training job is using a large dataset stored in S3. The data scientist notices that the training job is spending a significant amount of time reading data from S3. Which approach would BEST reduce data loading time?

Accepted Answer

Use the Pipe mode input for the training data. Pipe mode streams data directly from S3 into the training algorithm without first downloading it to the training instance's local storage. This eliminates the I/O bottleneck of writing large datasets to disk, significantly reducing data loading time compared to File mode, which downloads the entire dataset before training begins.

Answer

Use the File mode input with a larger instance

Answer

Use a larger training instance with more CPU

Answer

Increase the batch size to reduce the number of batches

Question 12

A data engineer needs to analyze large CSV files stored in Amazon S3 using SQL queries. The data is not frequently accessed, and cost is a primary concern. Which AWS service should be used to query the data directly in S3 without moving it?

Accepted Answer

Amazon Athena. Amazon Athena is a serverless interactive query service that allows you to analyze data directly in Amazon S3 using standard SQL, without needing to load or transform the data. It is ideal for this use case because it charges only for the data scanned per query, making it cost-effective for infrequently accessed large datasets. Athena integrates with AWS Glue Data Catalog for schema management and supports common formats like CSV, JSON, Parquet, and ORC.

Answer

Amazon EMR

Answer

Amazon Redshift Spectrum

Answer

AWS Glue

Question 13

A team is building a data lake on Amazon S3 and using AWS Glue to catalog data. They notice that Glue crawlers are taking too long to update the catalog for a large dataset with millions of small files. Which approach will MOST improve crawler performance?

Accepted Answer

Consolidate the small files into larger files (e.g., 100 MB each).. AWS Glue crawlers incur significant overhead when processing millions of small files because each file requires a separate read, schema inference, and metadata write operation. Consolidating small files into larger files (e.g., 100 MB each) reduces the total number of objects that the crawler must scan, dramatically decreasing the time spent on file-level operations and improving overall throughput.

Answer

Increase the frequency of the crawler runs.

Answer

Partition the data by date in S3.

Answer

Use a custom classifier to parse the data.

Question 14

An Athena query SELECT COUNT(*) FROM table WHERE col1 IS NULL returns the value 5000. What does this value represent?

Accepted Answer

The number of rows where col1 is NULL. The exhibit shows the result of an Athena query that counts the number of rows where col1 is NULL. The value 5000 is that count. Therefore, Option B is correct. Option A is incorrect because the query does not count total rows; it filters for NULLs. Option C is incorrect because the query counts NULL rows, not non-NULL. Option D is incorrect because the query does not use DISTINCT to count distinct values.

Answer

The total number of rows in the table

Answer

The number of rows where col1 is not NULL

Answer

The number of distinct values in col1

Question 15

A machine learning team is deploying a model that performs real-time inference on streaming data from Amazon Kinesis Data Streams. The model requires sub-100ms latency. Which deployment option should the team choose?

Accepted Answer

Deploy the model on an Amazon SageMaker real-time endpoint. A SageMaker real-time endpoint is designed for low-latency, synchronous inference and can consistently deliver sub-100ms responses, making it the correct choice for real-time streaming inference. It keeps the model loaded on persistent instances and responds immediately to each request. This matches the sub-100ms latency requirement for Kinesis-sourced streaming data.

Answer

Use Amazon SageMaker batch transform

Answer

Use Amazon SageMaker asynchronous inference

Answer

Deploy a custom inference container on AWS Lambda