MLS-C01 Practice Exam 3 — 20 Questions

Question 1

A data engineering team is designing a data lake on AWS. They need to store raw data in S3 and allow multiple analytics services to query the data. Which service can be used to catalog and provide schema information for the data?

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

Accepted Answer

AWS Glue Data Catalog. AWS Glue Data Catalog is a fully managed metadata repository that stores table definitions, schema information, and partition details for data in S3. Amazon Athena, while it can query data in S3 using SQL, does not provide its own catalog; it relies on the Glue Data Catalog for schema information. Therefore, only AWS Glue Data Catalog directly catalogs and provides schema information.

Answer

Amazon Kinesis Data Streams

Answer

Amazon RDS

Answer

Amazon DynamoDB

Answer

Amazon Athena

Question 2

A machine learning engineer is performing exploratory data analysis on a dataset containing customer transaction records. The dataset has missing values in the 'age' column and outliers in the 'amount' column. Which combination of techniques should the engineer use to handle these issues during EDA?

Accepted Answer

Impute missing age values with the median and cap outliers in 'amount' using the interquartile range (IQR) method.. Median imputation is robust to outliers, and IQR-based capping is a standard method for handling outliers. Option B is wrong because removing rows with missing age can lead to data loss, and log transformation reduces skewness but does not handle outliers by capping. Option C is wrong because imputing with a constant like 0 is arbitrary and can bias the data, and capping using mean ± 3*std is sensitive to outliers. Option D is wrong because mean imputation is sensitive to outliers, and removing outliers via z-score can discard valid data points.

Answer

Remove rows with missing age and apply log transformation to 'amount'.

Answer

Impute missing age values with a constant (e.g., 0) and cap outliers using mean ± 3*std.

Answer

Impute missing age values with the mean and remove outliers in 'amount' using z-score.

Question 3

A data scientist is evaluating a binary classification model. The model's AUC-ROC is 0.95. Which TWO statements are true?

Accepted Answer

The model has excellent discriminative ability. Option B is correct because an AUC-ROC of 0.95 indicates excellent discriminative ability: the model has a high probability of ranking a randomly chosen positive instance above a randomly chosen negative instance, with 0.5 being random and 1.0 being perfect. Option C is correct because AUC-ROC is computed by integrating the ROC curve across all possible classification thresholds, so it summarizes performance independent of any single decision threshold. Option A is wrong because AUC-ROC does not guarantee zero false positives; a model can have a high AUC while still producing false positives at certain thresholds. Option D is wrong because AUC-ROC measures ranking discrimination, not calibration, which concerns whether predicted probabilities match observed frequencies. Option E is wrong because a high AUC does not imply accuracy of at least 95%, especially under class imbalance or at a poorly chosen threshold.

Answer

The model has no false positives

Answer

The model is well-calibrated

Answer

The model's accuracy is at least 95%

Question 4

A data engineer is using AWS Glue to catalog a dataset with 200 columns. During exploratory data analysis, they run a crawler and then view the table schema in the AWS Glue Data Catalog. They notice that many columns are inferred as 'string' even though they contain numeric values. What is the most likely cause?

Accepted Answer

The crawler sample size is too small, and the sampled rows contain non-numeric values.. AWS Glue crawlers sample a subset of data (default 1 MB or a configurable sample size) to infer schema. If the sampled rows contain non-numeric values (e.g., empty strings, 'N/A', or text) in columns that are mostly numeric, the crawler will infer the column as string to accommodate the mixed types.

Answer

The data is stored in JSON format, which only supports string types.

Answer

The data is stored in Parquet format, which does not support numeric types.

Answer

The column names contain special characters that prevent type inference.

Question 5

A data scientist uses Amazon SageMaker Data Wrangler to explore a dataset and notices that the target variable is highly imbalanced. Which technique should the data scientist apply to balance the dataset before training?

Accepted Answer

Synthetic Minority Oversampling Technique (SMOTE). Synthetic Minority Oversampling Technique (SMOTE) is the correct technique because it generates synthetic samples for the minority class by interpolating between existing minority instances and their k-nearest neighbors, effectively balancing the dataset without simply duplicating data. Amazon SageMaker Data Wrangler includes a built-in SMOTE transform, making it directly applicable for handling imbalanced target variables during exploratory data analysis.

Answer

One-hot encoding of the target variable

Answer

Random undersampling of the majority class

Answer

Min-Max scaling of all features

Question 6

A company is using Amazon Athena to query a data lake in S3. Queries are slow and expensive. The data is stored as JSON. Which action will improve query performance and reduce cost?

Accepted Answer

Convert the data to Parquet format. Converting JSON data to Parquet format significantly improves Athena query performance and reduces cost. Parquet is a columnar storage format that allows Athena to scan only the columns needed for a query, drastically reducing the amount of data read from S3. This minimizes I/O and compute costs, as Athena charges based on the amount of data scanned. In contrast, JSON is row-based and requires scanning entire files even for queries that only touch a few columns.

Answer

Compress the JSON files using gzip

Answer

Partition the data by date

Answer

Increase the number of Athena workers

Question 7

A company wants to use Amazon SageMaker to automatically tune hyperparameters for a XGBoost model. Which built-in SageMaker feature should be used?

Accepted Answer

SageMaker Automatic Model Tuning. SageMaker Automatic Model Tuning (AMT) is the built-in feature designed specifically to automatically search for the best hyperparameter configuration for a model. It uses Bayesian optimization (or random search) to run multiple training jobs with different hyperparameter combinations, evaluating each against a chosen objective metric. For XGBoost, you define the hyperparameter ranges (e.g., eta, max_depth, subsample) and AMT finds the optimal set, reducing manual tuning effort. This directly matches the requirement to 'automatically tune hyperparameters'.

Answer

SageMaker Debugger

Answer

SageMaker Model Monitor

Answer

SageMaker Experiments

Question 8

A data scientist is training a model using Amazon SageMaker and wants to track hyperparameter tuning jobs, training jobs, and model metrics. The team also needs to compare experiments visually. Which AWS service should be used?

Accepted Answer

Amazon SageMaker Experiments. Amazon SageMaker Experiments is purpose-built for tracking and comparing machine learning experiments, including hyperparameter tuning jobs, training jobs, and model metrics. It provides a visual interface for comparison. Option A is wrong because Amazon CloudWatch Logs is for storing logs and monitoring, not for experiment tracking and comparison. Option B is wrong because AWS Glue DataBrew is a visual data preparation tool, not for experiment management. Option C is wrong because AWS Step Functions orchestrates workflows but does not provide experiment tracking or visual comparison.

Answer

Amazon CloudWatch Logs

Answer

AWS Glue DataBrew

Answer

AWS Step Functions

Question 9

A machine learning team is using SageMaker Pipelines to orchestrate a multi-step workflow. The pipeline fails with a 'ThrottlingException' when submitting a training job. Which TWO actions can reduce the likelihood of throttling?

Accepted Answer

Implement retry logic with exponential backoff in the pipeline. Option B is correct because implementing retry logic with exponential backoff in the pipeline directly mitigates transient ThrottlingException errors from SageMaker API calls by spacing out retries and giving the service time to recover, which is the AWS-recommended pattern for handling throttling. Option D is correct because reducing the number of concurrent pipeline steps lowers the rate of simultaneous SageMaker API requests (for example, CreateTrainingJob calls), keeping request volume under the service's per-account throttling limits and thereby decreasing the chance of hitting ThrottlingException. Option A is not relevant because SageMaker Model Registry is for versioning and tracking models, not for controlling API request rates. Option C is incorrect because increasing parallel training jobs raises concurrent API call volume and would worsen throttling rather than reduce it. Option E is not the right fit here because a service quota increase addresses limits on resource counts (such as concurrent training jobs), whereas ThrottlingException is caused by exceeding API request-rate limits, which are not raised through the standard service quota increase process.

Answer

Use SageMaker Model Registry to version models

Answer

Increase the number of parallel training jobs

Answer

Request a service quota increase for training jobs

Question 10

A data scientist is analyzing a dataset with 500 features and 100,000 observations. The target variable is binary. The dataset contains highly correlated features and some categorical variables with high cardinality. Which combination of techniques should the data scientist use to reduce dimensionality while preserving interpretability for EDA?

Accepted Answer

Apply correlation-based feature selection to remove highly correlated pairs, then use target encoding for high-cardinality categorical variables.. Correlation-based feature selection removes highly correlated features, reducing redundancy without distorting the original feature space, and target encoding converts high-cardinality categorical variables into numeric values based on the target mean, which preserves interpretability and avoids dimensionality explosion. Option A is incorrect because PCA reduces interpretability by transforming features into principal components and does not handle categorical variables directly. Option B is incorrect because mutual information is a feature selection method, but label encoding for high-cardinality categoricals can impose arbitrary ordinal relationships. Option C is incorrect because chi-squared test requires categorical features and is not suitable for high-dimensional numerical data; also, one-hot encoding high-cardinality categoricals leads to a drastic increase in dimensionality.

Answer

Apply Principal Component Analysis (PCA) to all features and then train a model on the top 50 components.

Answer

Use mutual information to select top features and apply label encoding to categorical variables.

Answer

Use chi-squared test to select top features and one-hot encode categorical variables.

Question 11

A data engineer runs the AWS CLI command above to inspect a file in S3. They need to determine if the file was modified after a Glue ETL job processed it. What additional information could they obtain from this command?

Accepted Answer

The object's last modified timestamp.. The AWS CLI command `aws s3api head-object --bucket my-bucket --key my-key` returns metadata about an S3 object without downloading it. The `LastModified` field in the response provides the exact timestamp of the last modification, which can be compared to the Glue ETL job's execution time to determine if the file was modified after processing. This is the only field that directly answers the question about modification timing.

Answer

The object's content type.

Answer

The object's storage class.

Answer

The object's ETag.

Question 12

A data scientist is performing EDA on a dataset of 1 million images stored in Amazon S3. Each image is 100x100 pixels in RGB format. The data scientist wants to compute the mean pixel value per channel across the entire dataset. Which approach is most efficient?

Accepted Answer

Use Amazon SageMaker Processing with a custom Python script that iterates over S3 objects and aggregates pixel values.. (Amazon SageMaker Processing with a custom Python script) is the most efficient because it can distribute the computation across multiple instances, processing images in parallel without loading all into memory at once. This is ideal for a large dataset of 1 million images. Option B (Athena) is designed for querying structured data, not image processing. Option C (AWS Glue ETL) is for ETL on tabular data, not image processing. Option D (SageMaker notebook with large instance) would require loading all images into memory, which is not feasible for 1 million images.

Answer

Use Amazon Athena with a SQL query on the image metadata stored in a CSV file.

Answer

Use AWS Glue ETL to read images and compute the mean.

Answer

Use a SageMaker notebook instance with a large instance type to load all images into memory and compute the mean.

Question 13

Which TWO of the following are appropriate methods for handling missing data in a dataset?

Accepted Answer

Multiple imputation. Multiple imputation and using algorithms that handle missing values (e.g., XGBoost) are valid. Listwise deletion reduces sample size. Mean imputation may bias distributions. Dropping features with many missing values may lose information.

Answer

Dropping features with more than 50% missing values

Answer

Mean imputation for all features

Answer

Listwise deletion (removing rows with missing values)

Question 14

A data scientist is using SageMaker to train a linear regression model. The target variable has a long-tail distribution. Which data transformation is LEAST likely to improve model performance?

Accepted Answer

Normalize all feature values to [0,1]. Normalizing feature values to [0,1] is a scaling technique that does not address the long-tail distribution of the target variable. Long-tail distributions typically require transformations that compress the tail (e.g., log or Box-Cox) to make the relationship more linear and reduce the influence of extreme values. Feature normalization helps with gradient descent convergence but does not fix skewness in the target, so it is least likely to improve model performance for this specific issue.

Answer

Add interaction terms between features

Answer

Apply log transformation to the target variable

Answer

Remove outliers from the target variable

Question 15

A machine learning team is reviewing a dataset for a regression problem. They notice that the target variable has a right-skewed distribution. Which transformation should they consider applying to the target variable to improve model performance?

Accepted Answer

Apply log transformation to the target variable.. Log transformation is commonly applied to right-skewed data to make it more normally distributed, which can improve model performance. Option A (StandardScaler) is for scaling, not skewness. Option B (MinMaxScaler) also doesn't address skewness. Option D (One-hot encoding) is for categorical variables.

Answer

Apply StandardScaler to the target variable.

Answer

Apply MinMaxScaler to the target variable.

Answer

Apply one-hot encoding to the target variable.

Question 16

During exploratory data analysis, a data scientist notices that the Pearson correlation coefficient between two continuous variables is 0.85. What does this indicate?

Accepted Answer

A strong positive linear relationship. A correlation coefficient of 0.85 indicates a strong positive linear relationship. Option A is wrong because correlation does not imply causation. Option C is wrong because the coefficient is positive and strong, not negative and weak. Option D is wrong because a coefficient of 0.85 indicates a strong relationship, not no relationship.

Answer

A causal relationship between the two variables

Answer

A weak negative linear relationship

Answer

No relationship between the variables

Question 17

A machine learning engineer is examining a dataset containing text reviews. They want to convert the text into numerical features for a model. During EDA, they notice that the word 'the' appears in almost every review, while words like 'excellent' appear rarely. Which of the following techniques should they use to reduce the impact of very common words?

Accepted Answer

Apply TF-IDF transformation.. TF-IDF transformation downweights common words (like 'the') and emphasizes rare but informative words (like 'excellent'). Option B (removing stopwords) is insufficient because it does not adjust for frequency beyond removing a predefined list; TF-IDF handles frequency weighting. Option C (word2vec embeddings) captures semantic relationships but does not specifically reduce the impact of common words. Option D (bag-of-words) does not perform any weighting, so common words dominate.

Answer

Remove stopwords from the text.

Answer

Use word2vec embeddings.

Answer

Use a bag-of-words representation.

Question 18

A data scientist is training a binary classification model on an imbalanced dataset where the positive class represents only 5% of the data. The model currently achieves 95% accuracy but only 10% recall on the positive class. Which metric should the scientist focus on to improve the model's ability to detect the positive class?

Accepted Answer

Recall. Recall measures the proportion of actual positives the model correctly identifies (TP / (TP + FN)). With only 10% recall on the positive class, the model is missing 90% of true positives — exactly the problem the scientist needs to fix. Optimizing recall (e.g., via class weighting, resampling, or threshold tuning) directly improves the model's ability to detect the minority positive class.

Answer

Accuracy

Answer

Precision

Answer

AUC-ROC

Question 19

A machine learning team is building a fraud detection system using Amazon SageMaker. The training data is highly imbalanced (99% legitimate, 1% fraudulent). They need to maximize the recall of the fraud class while keeping precision above 90%. Which approach should they take?

Accepted Answer

Train a model using the original data, then adjust the decision threshold on the validation set to maximize recall while precision > 90%. Adjusting the decision threshold on the validation set directly optimizes the trade-off between recall and precision. By lowering the threshold, the model classifies more instances as fraud, increasing recall, while the precision constraint (≥90%) ensures the threshold is set at a point where false positives remain acceptably low. This approach works with any probabilistic classifier and does not alter the training data distribution.

Answer

Undersample the majority class to create a balanced dataset and train a Random Forest

Answer

Train an XGBoost model with scale_pos_weight parameter set to 99

Answer

Use SMOTE to oversample the fraud class and then train a logistic regression

Question 20

A data scientist is training a deep learning model for object detection using Amazon SageMaker. The training job is using a single GPU instance and is taking too long. Which THREE actions can reduce training time? (Choose THREE.)

Accepted Answer

Enable mixed precision training with FP16. Option B is correct because mixed precision training with FP16 reduces memory bandwidth and uses tensor cores on modern NVIDIA GPUs, allowing faster matrix operations and larger effective batch sizes, which shortens training time. Option C is correct because moving from a single-GPU instance to a multi-GPU instance like p3.16xlarge (8 V100 GPUs) enables data-parallel training within one instance, increasing throughput and reducing wall-clock training time. Option E is correct because distributed training across multiple instances (e.g., SageMaker distributed data parallel) scales the workload horizontally, further cutting training time for large models. Option A is incorrect because CPU instances lack the massive parallelism and tensor cores of GPUs, so training would be dramatically slower. Option D is incorrect because reducing the batch size lowers per-step compute but increases the number of steps and often reduces hardware utilization, generally increasing total training time.

Answer

Use a CPU instance instead of GPU

Answer

Reduce the batch size