MLS-C01 Practice Test 40 — 15 Questions

Question 1

Drag and drop the steps to deploy a model as a SageMaker endpoint for real-time inference in the correct order.

Accepted Answer

1. Create model, 2. Create endpoint configuration, 3. Create endpoint, 4. Test endpoint. Deployment requires model creation, endpoint configuration, endpoint creation, and testing.

Answer

1. Create endpoint configuration, 2. Create model, 3. Create endpoint, 4. Test endpoint

Answer

1. Create model, 2. Create endpoint, 3. Create endpoint configuration, 4. Test endpoint

Answer

1. Test endpoint, 2. Create model, 3. Create endpoint configuration, 4. Create endpoint

Question 2

A data scientist is using Amazon SageMaker to deploy a model for real-time inference. The model is a TensorFlow neural network. The scientist wants to use automatic scaling based on the number of incoming requests. Which service integration is required?

Accepted Answer

Amazon SageMaker endpoint configured with Application Auto Scaling. Amazon SageMaker endpoints natively integrate with Application Auto Scaling to adjust the number of instances based on a target metric, such as the number of incoming requests per instance. This allows the TensorFlow model to scale automatically in response to traffic, without needing additional orchestration services.

Answer

Amazon ECS with service auto scaling

Answer

AWS Lambda with provisioned concurrency

Answer

AWS Auto Scaling plans

Question 3

Which TWO are appropriate visualizations for exploring the distribution of a single numeric variable? (Select TWO.)

Accepted Answer

Histogram. Options B and E are correct. A histogram displays the frequency distribution of a single numeric variable by binning the data, and a box plot shows the five-number summary (minimum, first quartile, median, third quartile, maximum) to visualize spread and outliers. Option A (heatmap) is typically used for two numeric variables to show density or correlation. Option C (bar chart) is for categorical data, not numeric distribution. Option D (scatter plot) visualizes the relationship between two numeric variables, not the distribution of one.

Answer

Heatmap

Answer

Bar chart

Answer

Scatter plot

Question 4

A company is building a data lake on Amazon S3. Raw data is ingested from multiple sources in different formats (CSV, JSON, Parquet). The data must be cataloged and made queryable using Amazon Athena. The data schema may evolve over time. Which approach minimizes manual effort and supports schema evolution?

Accepted Answer

Use AWS Glue Crawlers to automatically create and update the Glue Data Catalog. AWS Glue Crawlers automatically infer schema from data in S3, create and update the Glue Data Catalog tables, and handle schema evolution by detecting changes such as new columns or partitions. This minimizes manual effort because the crawler runs on a schedule or trigger, and the catalog is natively integrated with Athena for querying without any additional setup.

Answer

Use Athena only, without a catalog, by directly querying files

Answer

Use Amazon EMR to process data and write to a Hive metastore

Answer

Manually create tables in Athena using DDL statements

Question 5

A company has a time series forecasting problem with daily sales data. The data shows both trend and seasonality. Which Amazon SageMaker built-in algorithm is most suitable?

Accepted Answer

DeepAR. DeepAR is a supervised learning algorithm for time series forecasting that explicitly models both trend and seasonality using recurrent neural networks (RNNs). It is designed to handle multiple related time series, incorporate additional features like holidays or promotions, and produce probabilistic forecasts, making it the most suitable choice for daily sales data with trend and seasonal patterns.

Answer

K-Means

Answer

Linear Learner

Answer

XGBoost

Question 6

A company is running a machine learning training job on Amazon SageMaker that reads training data from an S3 bucket. The job fails intermittently with an S3 throttling error. The data is partitioned across thousands of small files (average 100 KB). Which strategy is MOST effective to resolve the throttling issue?

Accepted Answer

Combine the small files into larger files (e.g., 100 MB) using a preprocessing step. S3 throttling errors (HTTP 503) occur when many small files cause a high request rate per prefix. By combining thousands of 100 KB files into fewer 100 MB files, you drastically reduce the number of GET requests, staying within S3's 5,500 GET requests per second per prefix limit. This preprocessing step directly addresses the root cause of the throttling without changing the training infrastructure.

Answer

Use Amazon Athena to query the data and output results to a new S3 location

Answer

Enable S3 Transfer Acceleration on the bucket

Answer

Increase the number of SageMaker training instances to distribute the load

Question 7

During EDA, a data scientist plots the distribution of a numeric feature and observes that it is right-skewed. The feature will be used as input to a linear model. Which transformation should the data scientist apply?

Accepted Answer

Log transformation. A right-skewed distribution indicates that the feature has a long tail on the right, which can violate the linear model assumption of normally distributed errors. The log transformation compresses the high values and expands the low values, making the distribution more symmetric and stabilizing variance, which improves linear model performance.

Answer

Square transformation

Answer

One-hot encoding

Answer

Standardization (Z-score)

Question 8

A machine learning team is developing a model to predict housing prices. They have a dataset with numerical features like square footage and number of bedrooms, and categorical features like neighborhood. Which preprocessing step is essential before training a linear regression model?

Accepted Answer

One-hot encode categorical features. Linear regression requires numerical inputs, so categorical features like neighborhood must be converted into a numerical representation before training. One-hot encoding creates binary indicator columns for each category, allowing the model to use the information without imposing a false ordinal relationship. This is an essential preprocessing step for categorical variables in linear regression.

Answer

Normalize all numerical features to have zero mean and unit variance

Answer

Remove highly correlated features

Answer

Apply Principal Component Analysis (PCA) to reduce dimensionality

Question 9

Which THREE of the following are common causes of overfitting in machine learning models?

Accepted Answer

Using a complex model like a deep neural network on a small dataset. Option A is correct because a highly complex model such as a deep neural network has enormous capacity and can memorize the idiosyncrasies and noise of a small dataset instead of learning generalizable patterns, which is a classic overfitting cause. Option B is correct because when the number of trainable parameters greatly exceeds the number of training samples, the model has enough degrees of freedom to fit the training data almost perfectly, including its noise, leading to poor generalization. Option D is correct because training for too many epochs lets the model continue optimizing the training loss past the point of best generalization, so it starts fitting noise and the validation/test error rises even as training error keeps falling. Option C is not a cause of overfitting; a large dataset with many samples generally reduces overfitting by providing more evidence and constraining the model. Option E is not a cause of overfitting either; regularization techniques such as L1/L2 penalties, dropout, or early stopping are explicitly used to prevent or reduce overfitting.

Answer

Having a large dataset with many samples

Answer

Using regularization techniques

Question 10

A data analyst is investigating a dataset where the target variable is binary (0/1). The analyst wants to check for multicollinearity among the numerical features. Which statistical measure should the analyst use?

Accepted Answer

Variance Inflation Factor (VIF).. Variance Inflation Factor (VIF) is the standard statistical measure for detecting multicollinearity among numerical features. VIF quantifies how much the variance of a regression coefficient is inflated due to correlation with other predictors; values above 5 or 10 typically indicate problematic multicollinearity. It directly addresses the analyst's goal of checking relationships among the numerical features themselves.

Answer

Mutual information between features and target.

Answer

Chi-square test of independence.

Answer

Pearson correlation coefficient between each pair of features.

Question 11

A team is building a model to predict house prices. They have a dataset with features like 'SquareFootage', 'Bedrooms', 'YearBuilt', and 'Neighborhood'. They notice that 'SquareFootage' has a few extreme values (e.g., 50,000 sq ft) that are likely data entry errors. They want to handle these outliers without losing all the data. Which of the following approaches is most robust?

Accepted Answer

Cap 'SquareFootage' at the 99th percentile value.. Capping 'SquareFootage' at the 99th percentile limits extreme values while retaining most data points, making it robust against data entry errors. Option B is incorrect because replacing extreme values with the mean distorts the distribution and can bias the model. Option C is incorrect because a log transformation does not fix data entry errors; it only changes the scale. Option D is incorrect because removing rows with values above 3 standard deviations from the mean may discard valid data points and is not robust when the data contains errors.

Answer

Replace extreme values with the mean of 'SquareFootage'.

Answer

Apply log transformation to 'SquareFootage'.

Answer

Remove rows where 'SquareFootage' is above 3 standard deviations from the mean.

Question 12

A company is using Amazon Rekognition to detect objects in images stored in S3. They want to reduce costs by processing images only when they are uploaded. Which AWS service should be used to trigger Rekognition automatically?

Accepted Answer

AWS Lambda. AWS Lambda is the correct service because it can be triggered directly by S3 events (e.g., s3:ObjectCreated:Put) to invoke Amazon Rekognition's DetectLabels API on the newly uploaded image. This serverless architecture ensures processing occurs only on upload, eliminating idle costs and manual polling.

Answer

Amazon CloudWatch Events

Answer

Amazon Simple Notification Service (SNS)

Answer

AWS Step Functions

Question 13

A data engineer is performing exploratory data analysis on a dataset stored in Amazon S3 using AWS Glue DataBrew. The dataset contains a column 'age' with missing values. DataBrew's profile shows that the column has 5% missing values, a mean of 45, and a standard deviation of 15. Which imputation strategy should the engineer recommend to minimize bias if the missing data is Missing at Random (MAR)?

Accepted Answer

Use multiple imputation to generate several plausible values and combine results. Multiple imputation is the recommended strategy for Missing at Random (MAR) data because it generates several plausible values for each missing entry and combines the results, preserving the variability and relationships in the data. This minimizes bias compared to single-value imputation methods.

Answer

Replace missing values with the mean (45)

Answer

Remove rows with missing 'age' values

Answer

Replace missing values with the median

Question 14

A company has a dataset with 1 million rows and 500 features. They want to reduce dimensionality for visualization. Which technique is most suitable for preserving global structure?

Accepted Answer

Principal Component Analysis (PCA). PCA is the most suitable technique for reducing dimensionality while preserving global structure. It performs a linear projection onto the directions of maximum variance, which retains the overall geometry and relationships among all points. For a 1M x 500 dataset used for visualization, PCA is fast, deterministic, and preserves global structure far better than t-SNE, which prioritizes local neighborhoods.

Answer

Autoencoder

Answer

t-Distributed Stochastic Neighbor Embedding (t-SNE)

Answer

Linear Discriminant Analysis (LDA)

Question 15

A company is building a machine learning model to detect anomalies in industrial sensor data. The data is time-series with seasonal patterns. The data scientist wants to use Amazon SageMaker to train a model. Which algorithm is most suitable for this task?

Accepted Answer

Random Cut Forest (RCF). Random Cut Forest (RCF) is the most suitable algorithm because it is designed for unsupervised anomaly detection on streaming and time-series data. It works by constructing an ensemble of random trees that isolate anomalies based on how quickly a data point can be separated from the rest, making it effective for detecting outliers in sensor data with seasonal patterns without requiring labeled training data.

Answer

K-Means

Answer

DeepAR

Answer

XGBoost