MLS-C01 Practice Questions

Question 1

A data scientist needs to run a one-time query on 10 TB of data stored in S3 using Amazon Athena. The query scans 5 TB and returns a small result set. Which approach minimizes cost?

Accepted Answer

Query the data directly in Athena without any preprocessing. Athena charges based on the amount of data scanned per query. Since this is a one-time query on 10 TB of data that scans only 5 TB, querying directly in Athena without preprocessing is the most cost-effective approach because you pay only for the 5 TB scanned, with no additional costs for data conversion, storage, or cluster provisioning.

Answer

Create an S3 Select query to filter data before Athena

Answer

Use Amazon Redshift Spectrum to query the data

Answer

Use AWS Glue to convert the data to Parquet format and repartition by date

Question 2

A machine learning team is deploying a model using Amazon SageMaker. The model inference code runs on GPUs and requires a custom container. The team wants to minimize cold start latency. Which SageMaker hosting option should they use?

Accepted Answer

Use a real-time endpoint with a single production variant using a GPU instance.. A real-time endpoint with a single production variant using a GPU instance provides a persistent, always-on inference environment. This eliminates cold start latency entirely, as the container and GPU resources are pre-warmed and ready to serve requests immediately, which is critical for minimizing latency in GPU-based custom containers.

Answer

Use a multi-model endpoint with GPU instances.

Answer

Use a serverless inference endpoint.

Answer

Use a real-time endpoint with multiple production variants for redundancy.

Question 3

During exploratory data analysis, a data scientist notices that a categorical feature 'city' has over 1,000 unique values. The dataset has 10,000 rows. Which technique should the scientist consider to reduce the cardinality of this feature?

Accepted Answer

Group low-frequency categories into a single 'other' category.. Grouping rare categories into an 'other' bucket is a common technique to reduce cardinality. Option A (label encoding) assigns numeric labels but still has 1000 unique values. Option B (grouping into 'other') reduces cardinality. Option C (one-hot encoding) would create too many columns. Option D (frequency encoding) replaces categories with frequency but still has 1000 values.

Answer

Apply label encoding to assign numeric labels.

Answer

Apply one-hot encoding to all categories.

Answer

Apply frequency encoding to replace each category with its frequency.

Question 4

A company is building a data pipeline using AWS Glue to transform data from Amazon RDS to Amazon S3. The pipeline runs daily and processes about 500 GB of data. The team notices that the job is taking longer than expected. Which change would MOST improve the job performance?

Accepted Answer

Increase the number of DPUs for the Glue job. Increasing the number of DPUs (Data Processing Units) for the AWS Glue job directly allocates more distributed computing resources, allowing the job to process the 500 GB dataset in parallel across multiple workers. This is the most effective way to reduce runtime for a large-scale ETL job, as Glue's Spark-based execution scales horizontally with DPU count.

Answer

Disable job bookmarking

Answer

Upgrade the RDS instance to a larger class

Answer

Use smaller file sizes in S3 output

Question 5

Refer to the exhibit. An IAM policy is attached to an IAM role used by a SageMaker training job. The training job fails with an access denied error when trying to write model artifacts to an S3 bucket. What is the most likely cause?

Accepted Answer

The IAM role does not have permission to write to the S3 bucket. The IAM role attached to the SageMaker training job must have an IAM policy that grants s3:PutObject permission on the S3 bucket where model artifacts are written. The access denied error indicates that the role lacks the necessary write permissions for that specific bucket, causing the training job to fail when it attempts to upload the model output.

Answer

The training job is trying to write to a different S3 bucket

Answer

The IAM role does not have permission to read the training data

Answer

The IAM role does not have permission to create training jobs

Question 6

A data scientist is training a neural network on Amazon SageMaker. The network has many layers and the training is very slow. The scientist suspects that the gradients are vanishing. Which technique is most specifically designed to mitigate the vanishing gradient problem?

Accepted Answer

Use batch normalization.. Batch normalization helps by normalizing the activations, which reduces the problem of vanishing/exploding gradients. Dropout is for regularization. Data augmentation increases data. Gradient clipping deals with exploding gradients, not vanishing.

Answer

Use gradient clipping.

Answer

Use data augmentation.

Answer

Use dropout layers.

Question 7

A data scientist is training a text classification model using Amazon SageMaker. The dataset consists of 100,000 labeled documents. The data scientist notices that the model performs well on the training set but poorly on the validation set. Which regularization technique should the data scientist apply to reduce overfitting?

Accepted Answer

Dropout. Dropout is a regularization technique that randomly drops a fraction of neurons during training, which prevents the model from relying too heavily on any single feature and forces it to learn more robust representations. This directly addresses the overfitting symptom of high training accuracy and low validation accuracy by reducing the model's capacity to memorize noise in the training data.

Answer

Data augmentation

Answer

Batch normalization

Answer

Early stopping

Question 8

A data science team is using Amazon SageMaker to train a deep learning model for object detection using the built-in SSD algorithm. The dataset consists of 100,000 labeled images stored in a SageMaker Pipe Mode input. The training job uses a single ml.p3.2xlarge instance. After 2 hours, the training job fails with the error 'ResourceLimitExceeded: The account-level service limit for ml.p3.2xlarge for training job usage is 1. Contact AWS Support to request a limit increase'. However, the team has already submitted a limit increase request and it was approved for 5 instances. What is the most likely cause of the error?

Accepted Answer

The service limit increase has not yet been applied to the account in the current region. The error 'ResourceLimitExceeded' indicates that the account's service limit for ml.p3.2xlarge training instances has been exceeded. Even though the team requested and received approval for a limit increase to 5 instances, the increase may not have taken effect yet in the current region. AWS service limit increases are applied per region, and there can be a propagation delay after approval. Option A (GPU memory) would cause a different error such as 'OutOfMemory'. Option B (algorithm requirement) is unrelated because the SSD algorithm does run on the chosen instance. Option D (S3 permissions) would result in an 'AccessDenied' error, not a limit error. Therefore, option C is the correct answer.

Answer

The instance is running out of GPU memory

Answer

The built-in SSD algorithm requires a GPU instance type with at least 16 GB of GPU memory

Answer

The IAM role does not have permission to access the S3 bucket for model artifacts

Question 9

A team is building a data pipeline that ingests data from an Amazon S3 bucket, transforms it using AWS Glue, and loads it into Amazon Redshift for analysis. The Glue job runs on a schedule every hour. The team has noticed that the job takes longer than expected and sometimes fails due to memory issues. The data volume is variable, with occasional spikes. Which solution should the team implement to optimize the pipeline?

Accepted Answer

Enable job bookmarks to process only new data and use a G.2X worker type for more memory.. Enabling job bookmarks allows the Glue job to process only new or changed data since the last run, reducing the data volume per execution. Using the G.2X worker type provides additional memory (e.g., 16 GB per DPU vs. 4 GB for G.1X), which helps prevent out-of-memory failures during data spikes. Together, these optimizations address both the variable data volume and memory constraints without requiring a complete pipeline redesign.

Answer

Decrease the number of workers to reduce memory contention.

Answer

Increase the schedule frequency to run the job more often with smaller data increments.

Answer

Replace AWS Glue with Amazon EMR using Spark.

Question 10

Which TWO options are best practices for training machine learning models using SageMaker? (Choose TWO.)

Accepted Answer

Use incremental training when you have new data that is similar to the original training data. Option B is correct because SageMaker incremental training lets you reuse an existing trained model artifact and continue training it with new data that resembles the original dataset, avoiding a full retrain from scratch and saving time and compute. Option C is correct because SageMaker Managed Spot Training uses spare EC2 capacity at up to 90% lower cost, and SageMaker automatically manages checkpointing and job resumption when spot capacity is interrupted. Option A is not a best practice because the test set must remain held out to give an unbiased estimate of generalization; training on it causes data leakage and overly optimistic metrics. Option D is wrong because the largest instance type is not always optimal — it can waste money when the job is not compute-bound, and right-sizing via instance benchmarking is preferred. Option E is wrong because checkpointing after every epoch is not universally required; it adds S3 storage and I/O overhead and is mainly recommended for long-running or spot-training jobs.

Answer

Train the final model on the combined training and test sets to maximize data usage

Answer

Always use the largest possible instance type to minimize training time

Answer

Always enable checkpointing to save the model after every epoch

Question 11

A machine learning engineer is deploying a model for real-time inference using Amazon SageMaker. The model is a large ensemble that requires 8 GB of memory and 4 vCPUs. The expected traffic is 100 requests per second with a 200 ms latency requirement. Which instance configuration should they choose?

Accepted Answer

ml.c5.2xlarge (8 vCPU, 16 GB). (ml.c5.2xlarge) is correct because it offers 8 vCPUs and 16 GB memory, meeting both the compute and memory requirements while being cost-effective for CPU-based inference. Option A (ml.t2.medium) is wrong because it has only 2 vCPUs and 4 GB, insufficient for the 8 GB memory need. Option C (ml.p3.2xlarge) is wrong because it includes a GPU, which is unnecessary and overkill for this CPU-bound workload, and costs more. Option D (ml.m5.large) is wrong because it has only 2 vCPUs and 8 GB memory, lacking the required vCPUs and barely meeting memory.

Answer

ml.t2.medium (2 vCPU, 4 GB)

Answer

ml.p3.2xlarge (8 vCPU, 61 GB GPU)

Answer

ml.m5.large (2 vCPU, 8 GB)

Question 12

A data scientist is exploring a dataset with many features and suspects that some features are highly correlated. Which TWO methods can the scientist use to detect and handle multicollinearity before building a linear regression model?

Accepted Answer

Compute Variance Inflation Factor (VIF) for each feature and remove features with VIF > 10.. Option C is correct because the Variance Inflation Factor quantifies how much the variance of an estimated regression coefficient is inflated due to collinearity with other predictors, and a common rule of thumb is that VIF > 10 (or sometimes > 5) indicates problematic multicollinearity that warrants removing or combining the offending features. Option E is correct because Ridge regression adds an L2 penalty (lambda * sum of squared coefficients) to the ordinary least squares loss, which shrinks correlated coefficients toward zero and stabilizes estimates, making it a standard way to handle multicollinearity without dropping features. Option A is not appropriate as stated because although PCA can decorrelate features, using all components retains the same dimensionality and does not by itself address multicollinearity for interpretable regression; typically one drops components or uses PCR. Option B is a preprocessing step for scale sensitivity and does not detect or resolve correlation among features. Option D, stepwise selection, may incidentally drop some correlated variables but is not a reliable or targeted multicollinearity detection/handling method and can introduce other issues such as overfitting and unstable selection.

Answer

Apply Principal Component Analysis (PCA) and use all components.

Answer

Standardize all features to have zero mean and unit variance.

Answer

Use stepwise feature selection.

Question 13

A data scientist wants to understand the relationship between a categorical feature with 3 levels and a continuous target variable. Which visualization is most appropriate?

Accepted Answer

Box plot grouped by category. A box plot grouped by category (Option C) is the most appropriate visualization because it directly compares the distribution of a continuous target variable across the three levels of a categorical feature. It displays median, quartiles, and potential outliers for each group, making it ideal for understanding central tendency, spread, and skewness in a side-by-side comparison.

Answer

Correlation matrix

Answer

Line chart

Answer

Scatter plot

Question 14

A data scientist is performing exploratory data analysis on a dataset with missing values. The dataset contains a column 'income' with 20% missing values. The income distribution is right-skewed. Which imputation method is most appropriate to preserve the skewness?

Accepted Answer

Impute with the median income. Imputing with the median is most appropriate because the income distribution is right-skewed. The median is robust to outliers and extreme values, so it preserves the central tendency and the skewness of the distribution better than the mean, which is pulled upward by high-income outliers. This keeps the imputed values representative of the typical income in the dataset.

Answer

Impute with the mean income

Answer

Drop rows with missing income

Answer

Impute with the mode income

Question 15

A data scientist is analyzing a dataset with a continuous target variable and suspects that the relationship between a predictor and the target is non-linear. Which THREE techniques can the scientist use to explore and model this non-linearity?

Accepted Answer

Add polynomial features (e.g., x^2, x^3) and check if model performance improves.. Options C, D, and E are correct. Adding polynomial features (e.g., x^2, x^3) allows a linear model to capture non-linear relationships. Decision tree regressors naturally model non-linear interactions between predictors and the target. A scatter plot with a LOESS smooth curve visually reveals non-linear patterns in the data. Option A (logistic regression) is incorrect because it is for binary classification, not for exploring non-linearity with a continuous target. Option B (Pearson correlation) only measures linear relationships, so it is not suitable for detecting non-linearity.

Answer

Apply logistic regression to binarize the target.

Answer

Compute the Pearson correlation coefficient between the predictor and target.

AWS Certified Machine Learning Specialty MLS-C01 practice test

Three ways to study

Study MLS-C01 by domain

Study MLS-C01 by topic

Data Engineering practice questions

Machine Learning Implementation and Operations practice questions

Modeling practice questions

Exploratory Data Analysis practice questions

MLS-C01 fundamentals practice questions

MLS-C01 scenario practice questions

MLS-C01 troubleshooting practice questions

Top MLS-C01 questions

AWS Certified Machine Learning Specialty MLS-C01 practice questions