MLS-C01 Practice Test 20 — 15 Questions

Question 1

A data engineer needs to process streaming data from an IoT fleet and store the results in Amazon S3 for analysis. The solution must be serverless and handle data that arrives at irregular intervals. Which AWS service should be used to ingest the data?

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

Accepted Answer

AWS IoT Core. AWS IoT Core is the correct choice because it is a fully managed, serverless service designed specifically to ingest data from IoT devices at scale, handling irregular and high-frequency message arrivals via MQTT, HTTP, or LoRaWAN protocols. It can directly route data to Amazon S3 using IoT Rules, making it ideal for this streaming IoT fleet scenario without requiring any server management.

Answer

Amazon S3

Answer

Amazon Simple Queue Service (SQS)

Answer

Amazon Kinesis Data Streams

Question 2

A company uses Amazon SageMaker to deploy a model for real-time inference. The model is a linear regression model that was trained using the SageMaker built-in Linear Learner algorithm. The endpoint is configured with an ml.m5.large instance. After deployment, the company notices that the endpoint returns incorrect predictions. The training data was normalized, but the inference requests send raw feature values without normalization. What should the company do to fix the issue?

Accepted Answer

Create a SageMaker inference pipeline that includes a preprocessing step to normalize the input data before passing it to the model.. The model was trained on normalized data, so it expects input features with the same normalization statistics (mean and standard deviation) applied during training. Raw feature values at inference time cause a mismatch, leading to incorrect predictions. A SageMaker inference pipeline allows you to include a preprocessing step that normalizes the input data before it reaches the model, ensuring consistency.

Answer

Retrain the model using raw data without normalization.

Answer

Change the endpoint instance type to a GPU instance to handle the raw data.

Answer

Use a batch transform job to preprocess the data before sending it to the endpoint.

Question 3

Drag and drop the steps to create an Amazon SageMaker notebook instance in the correct order.

Accepted Answer

First, open Amazon SageMaker console. Next, select 'Notebook instances' from the left navigation. Then, click 'Create notebook instance'. After that, configure the notebook instance settings (name, instance type, IAM role, VPC). Finally, click 'Create notebook instance'.. Creating a notebook instance requires navigating the SageMaker console, configuring instance settings, IAM role, and VPC, then launching.

Answer

First, open Amazon SageMaker console. Then, click 'Create notebook instance' immediately. Next, configure the notebook instance settings. Finally, select 'Notebook instances' from the navigation.

Answer

First, configure the notebook instance settings (name, instance type, IAM role, VPC). Then, open Amazon SageMaker console. Next, click 'Create notebook instance'. Finally, create the notebook instance.

Answer

First, click 'Create notebook instance'. Then, open Amazon SageMaker console. Next, select 'Notebook instances'. Finally, configure settings and create.

Question 4

A machine learning engineer is training a gradient boosting model on Amazon SageMaker using the built-in XGBoost algorithm. The training dataset contains 2 million rows and 50 features. The engineer notices that the model's validation AUC is significantly lower than the training AUC, indicating overfitting. Which hyperparameter adjustment is MOST likely to reduce this overfitting?

Accepted Answer

Increase the value of alpha (L1 regularization).. The model shows a large gap between training and validation AUC, a classic overfitting signal. Increasing L1 regularization (alpha) penalizes complex leaf weights, shrinking the model and improving generalization. Other options either increase model complexity (max_depth, subsample=1.0) or accelerate fitting without regularization (eta), which would not address the core issue. Regularization strength is the direct lever for controlling overfitting in XGBoost.

Answer

Increase the value of eta (learning rate).

Answer

Increase the value of max_depth.

Answer

Increase the value of subsample to 1.0 and disable column sampling.

Question 5

A data scientist is using Amazon SageMaker built-in XGBoost algorithm to train a regression model. The training job completes successfully but the model performance on the test set is poor, with high bias. Which hyperparameter adjustment is most likely to help reduce bias?

Accepted Answer

Increase the max_depth parameter.. High bias means the model is underfitting, so increasing max_depth allows XGBoost to build deeper trees that capture more complex interactions and reduce bias. Deeper trees increase variance, but when bias is the diagnosed problem, adding capacity is the correct direction. This is the standard bias-variance tradeoff adjustment for a boosted-tree model.

Answer

Reduce the num_round parameter.

Answer

Increase the gamma parameter.

Answer

Decrease the max_depth parameter.

Question 6

A data scientist is tuning a random forest model using SageMaker Hyperparameter Tuning. The objective metric is validation:accuracy. Which THREE hyperparameters are most commonly tuned for random forest? (Choose THREE.)

Accepted Answer

Minimum samples per leaf (min_samples_leaf). The three hyperparameters most commonly tuned for a random forest are min_samples_leaf (B), max_depth (C), and n_estimators (D). Minimum samples per leaf (B) controls the minimum number of samples required to be at a leaf node, directly affecting the bias-variance tradeoff and preventing overfitting on small leaves. Maximum depth (C) limits how deep each decision tree can grow, which governs model complexity and helps regularize the ensemble. Number of trees (n_estimators) (D) determines how many trees are built in the forest, and increasing it generally improves accuracy up to a point of diminishing returns. Learning rate (A) is a gradient-boosting hyperparameter (e.g., XGBoost), not a random forest parameter, and batch size (E) is a training/optimization setting for neural networks or mini-batch gradient descent, not applicable to random forest tuning.

Answer

Learning rate

Answer

Batch size

Question 7

A data scientist trains a linear regression model to predict house prices. The model has high bias (underfitting). Which action is most likely to reduce bias?

Accepted Answer

Increase model complexity. Increasing model complexity (e.g., adding polynomial features or using a more flexible algorithm) can reduce bias. Adding L1 regularization increases bias, reducing features reduces complexity, and lowering max_depth for a tree also increases bias.

Answer

Reduce the number of features

Answer

Decrease the maximum depth of the tree

Answer

Add L1 regularization

Question 8

A data science team needs to process streaming data from thousands of IoT devices and perform real-time anomaly detection. The data must be persisted in Amazon S3 for batch processing later. Which combination of AWS services should be used to meet these requirements?

Accepted Answer

Amazon Kinesis Data Streams for ingestion, Amazon Kinesis Data Analytics for anomaly detection, and Amazon Kinesis Data Firehose to deliver data to Amazon S3.. Amazon Kinesis Data Streams provides durable, real-time ingestion for high-throughput IoT data. Kinesis Data Analytics can perform SQL-based anomaly detection on the stream, and Kinesis Data Firehose reliably delivers the processed or raw data to Amazon S3 for batch processing. This combination meets all requirements for streaming ingestion, real-time analytics, and persistent storage.

Answer

Amazon Kinesis Data Streams for ingestion, AWS Glue for anomaly detection, and Amazon S3 for storage.

Answer

AWS Lambda for both ingestion and anomaly detection, and Amazon S3 for storage.

Answer

Amazon Simple Queue Service (SQS) for ingestion, AWS Lambda for anomaly detection, and Amazon S3 for storage.

Question 9

Which TWO of the following are common techniques for detecting outliers in a dataset?

Accepted Answer

Z-score. The Z-score is a standard statistical technique for outlier detection: it measures how many standard deviations a data point lies from the mean, and points with |Z| above a threshold (commonly 3) are flagged as outliers, so option A is correct. The Interquartile range (IQR) method is also a classic outlier detection technique: it computes IQR = Q3 − Q1 and flags values below Q1 − 1.5×IQR or above Q3 + 1.5×IQR as outliers, so option B is correct. Principal Component Analysis (PCA) is a dimensionality-reduction technique, not an outlier detection method, so option C does not belong. K-means clustering is an unsupervised clustering algorithm that groups data but does not by itself identify outliers, so option D is not correct. Standard scaling (z-score normalization) merely rescales features to mean 0 and standard deviation 1 and is a preprocessing step, not an outlier detection technique, so option E does not belong.

Answer

Principal Component Analysis (PCA)

Answer

K-means clustering

Answer

Standard scaling

Question 10

A data scientist needs to profile a large dataset in Amazon S3 to understand its schema, data types, and quality. Which AWS service can automatically generate a data profile with statistics and visualizations?

Accepted Answer

AWS Glue DataBrew. AWS Glue DataBrew is purpose-built for visual data preparation and profiling, automatically generating column-level statistics (null counts, distinct values, min/max, correlations) and visualizations like histograms and box plots without writing code. It connects directly to S3 and produces a 'data profile' artifact that summarizes schema, data types, and quality metrics. This matches the requirement exactly.

Answer

Amazon Athena

Answer

Amazon QuickSight

Answer

Amazon Redshift

Question 11

An IAM policy attached to a SageMaker notebook role is shown. The data engineer tries to run an Athena query on a table in the 'my_database' Glue database. The query fails with an access denied error. What is the MOST likely cause?

Accepted Answer

The policy does not allow athena:StartQueryExecution on the Athena workgroup.. The IAM policy does not include the `athena:StartQueryExecution` action on the Athena workgroup, which is required to submit a query. Even if the role has permissions for Glue and S3, Athena will deny the request if the workgroup-level permission to start queries is missing, resulting in an access denied error.

Answer

The policy does not allow s3:PutObject on the query results location.

Answer

The policy does not allow glue:GetTable on the specific database.

Answer

The policy does not allow s3:ListBucket on the bucket.

Question 12

A data scientist is working on a regression problem to predict house prices. The dataset has 80 features, including categorical variables with high cardinality (e.g., zip code with 10,000 unique values). The target variable is log-transformed. The data scientist trains a linear regression model and obtains an R² of 0.45 on the test set. To improve performance, the data scientist considers: A) Applying one-hot encoding to all categorical features and using Ridge regression. B) Using target encoding for high-cardinality features and using a tree-based model like XGBoost. C) Removing all categorical features and using polynomial features for numerical features. D) Using principal component analysis (PCA) on all features before training a linear model. Which approach is MOST likely to improve the model's performance?

Accepted Answer

Target encoding + XGBoost. High-cardinality categorical features like zip code with 10,000 unique values make one-hot encoding explode dimensionality and sparsity, which hurts linear models. Target encoding replaces each category with a statistic (e.g., mean target) computed from training data, preserving signal in a single numeric column. XGBoost handles non-linear relationships and interactions well, and combined with target encoding it can capture the zip-code effect without the curse of dimensionality. This combination is the standard best practice for high-cardinality categorical regression.

Answer

Remove categorical features and use polynomial features

Answer

One-hot encoding + Ridge regression

Answer

PCA on all features before linear regression

Question 13

A company uses Amazon SageMaker to train a time-series forecasting model using the built-in DeepAR algorithm. The training data consists of daily sales for 1000 products over 2 years. The model performs well on most products, but for a few products with intermittent demand (sporadic sales), the predictions are poor. Which action should the data scientist take to improve predictions for these products?

Accepted Answer

Create a separate forecasting model specifically for intermittent demand products, using a model designed for such patterns (e.g., Croston's method).. DeepAR is a deep learning model that works well for time series with continuous or count data, but it assumes a certain regularity and may struggle with intermittent demand where many zero values occur. Croston's method is specifically designed for intermittent demand by separately forecasting the demand size and the inter-demand interval, then combining them. Thus, creating a separate model for these products using a method like Croston's is the most appropriate action.

Answer

Use a linear regression model for all products.

Answer

Increase the context length of the DeepAR model to capture longer history.

Answer

Add more training data by including additional product categories.

Question 14

A data scientist is analyzing a dataset with many features and wants to identify which features are most correlated with the target variable. Which EDA technique should be used?

Accepted Answer

Correlation matrix. A correlation matrix displays pairwise Pearson correlation coefficients between all numeric features and the target variable, enabling quick identification of the most correlated features. Option A (box plots grouped by target) is useful for visualizing feature distributions across target categories but does not directly measure correlation strength. Option B (scatter plot matrix) can show pairwise relationships but becomes impractical with many features and lacks a single quantitative correlation measure. Option C (histogram) only shows the distribution of a single feature, not its relationship with the target. Therefore, the correlation matrix is the appropriate EDA technique for identifying features most correlated with the target.

Answer

Box plots grouped by target

Answer

Scatter plot matrix

Answer

Histogram of each feature

Question 15

A data scientist is using Amazon SageMaker to train a model with a custom Docker container. The training job fails with an error: 'Container exited with code 137'. What is the most likely cause?

Accepted Answer

The training instance ran out of memory.. Exit code 137 (128+9) indicates the container was killed by the SIGKILL signal, which typically occurs when the Linux Out-Of-Memory (OOM) killer terminates a process that has exceeded its memory allocation. In Amazon SageMaker, training instances have finite memory, and if the training algorithm or data loading exceeds that limit, the OOM killer forcibly stops the container, resulting in exit code 137.

Answer

The training data was corrupted.

Answer

The training job exceeded the maximum runtime.

Answer

The Docker entrypoint script was not found.