MLA-C01 Practice Test 2 — 25 Questions

Question 1

A machine learning engineer is preparing a dataset that contains both numerical and categorical features. The categorical features have high cardinality (e.g., zip code with thousands of unique values). Which technique is most appropriate for encoding these high-cardinality categorical features?

Accepted Answer

Target encoding. Target encoding is the most appropriate technique for high-cardinality categorical features because it replaces each category with the mean of the target variable for that category, effectively capturing the predictive signal while keeping the feature as a single numeric column. This avoids the dimensionality explosion of one-hot encoding and the arbitrary ordinality of label encoding, making it a common choice in gradient boosting frameworks like XGBoost or LightGBM for datasets with thousands of unique categories.

Answer

Label encoding

Answer

One-hot encoding

Answer

Frequency encoding

Question 2

A data scientist is building a text classification model using a pre-trained BERT model from the Hugging Face library on SageMaker. The scientist wants to fine-tune the model on a custom dataset. Which TWO steps are necessary to set up the fine-tuning job? (Select TWO.)

Accepted Answer

Use the HuggingFace estimator provided by SageMaker. Option A is correct because the SageMaker HuggingFace estimator is specifically designed to simplify fine-tuning of pre-trained Hugging Face models like BERT. It automatically handles the underlying infrastructure, including the correct PyTorch/TensorFlow and Transformers versions, without requiring custom Docker containers. This is the recommended approach for Hugging Face model fine-tuning on SageMaker.

Answer

Enable SageMaker Clarify for explainability during training

Answer

Build a custom Docker container with PyTorch and Transformers

Answer

Use SageMaker Processing to preprocess the data in parallel

Question 3

A machine learning engineer is deploying a custom PyTorch model to a SageMaker endpoint for real-time inference. The model requires GPU acceleration. The engineer wants to minimize latency and cost. Which THREE actions should the engineer take? (Select THREE.)

Accepted Answer

Compile the model with SageMaker Neo. SageMaker Neo compiles the PyTorch model into an optimized runtime binary that is specifically tuned for the target hardware (e.g., GPU instances like ml.p3). This reduces inference latency by applying graph-level optimizations, operator fusion, and memory layout transformations without changing the model's accuracy, while also lowering compute resource usage and cost.

Answer

Use an ml.c5.2xlarge instance with CPU only

Answer

Use SageMaker Batch Transform for inference

Question 4

A data scientist is preparing a large dataset for training a binary classification model. The dataset has a severe class imbalance (95% negative, 5% positive). Which data preparation technique should the scientist use to address this imbalance without losing too much data?

Accepted Answer

SMOTE (Synthetic Minority Over-sampling Technique). SMOTE (Synthetic Minority Over-sampling Technique) is the best choice because it generates synthetic examples for the minority class by interpolating between existing minority instances and their k-nearest neighbors, rather than simply duplicating data. This addresses the severe 95:5 class imbalance without losing data (as undersampling would) and without the overfitting risk of naive random oversampling. The synthetic samples help the model learn a more general decision boundary for the positive class.

Answer

Random undersampling of the majority class

Answer

Random oversampling of the minority class

Answer

Apply class weights during model training

Question 5

A company wants to use a pre-trained NLP model from SageMaker JumpStart for sentiment analysis. Which step is required to make predictions?

Accepted Answer

Deploy the model to an endpoint. D is correct because SageMaker JumpStart provides pre-trained models that are ready for inference without additional training. To make predictions, you must deploy the model to a SageMaker endpoint, which creates a hosted inference endpoint that can accept input data and return sentiment analysis results.

Answer

Label the dataset for fine-tuning

Answer

Train the model from scratch on the company's data

Answer

Convert the model to ONNX format

Question 6

A data scientist is training a binary classification model using imbalanced data where the positive class is only 1% of the dataset. The scientist wants to maximize the recall for the positive class while maintaining reasonable precision. Which evaluation metric is most appropriate to tune during model selection?

Accepted Answer

F1 score. The F1 score is the harmonic mean of precision and recall, making it ideal for imbalanced datasets where the positive class is only 1%. By tuning the F1 score, the data scientist directly balances the trade-off between maximizing recall (capturing true positives) and maintaining reasonable precision (avoiding false positives), which aligns with the stated goal.

Answer

Log loss

Answer

Area under the ROC curve (AUC)

Answer

Accuracy

Question 7

An ML engineer needs to split a dataset into training, validation, and test sets. The dataset has a time-based column that should not be leaked. Which split method is most appropriate?

Accepted Answer

Temporal split based on date. Option B is correct because a temporal split ensures that the time-based column is not leaked by preserving the chronological order of the data. This method uses the date column to assign earlier records to the training set and later records to the validation and test sets, preventing future information from influencing the model during training.

Answer

Stratified split based on target

Answer

Random split with 70/20/10

Answer

K-fold cross-validation

Question 8

A team is building a regression model on a dataset with missing values in multiple features. They decide to use a k-Nearest Neighbors (k-NN) imputer. The dataset has 100,000 rows and 50 features. Which step should the team take to ensure the imputation is efficient and accurate?

Accepted Answer

Standardize the features before applying k-NN imputation. Standardizing features before applying k-NN imputation is critical because k-NN relies on distance calculations (e.g., Euclidean distance). If features are on different scales (e.g., one feature ranges 0–1 and another 0–100,000), the distance metric will be dominated by the larger-scale feature, leading to biased neighbor selection and inaccurate imputation. Standardization (e.g., z-score scaling) ensures each feature contributes equally to the distance computation, improving both efficiency and accuracy.

Answer

Set k=1 to minimize bias

Answer

Use all 100,000 rows to find neighbors for each missing value

Answer

Use only the feature with missing values to find neighbors

Question 9

A company wants to deploy a machine learning model that was trained on-premises using TensorFlow. The model is a TensorFlow SavedModel. The company uses AWS and wants to minimize operational overhead. Which deployment option meets these requirements?

Accepted Answer

Deploy the model using Amazon SageMaker with a TensorFlow inference container.. Amazon SageMaker provides a fully managed TensorFlow inference container that directly supports TensorFlow SavedModel format, enabling deployment without any custom infrastructure management. This minimizes operational overhead compared to self-managed options like ECS or Lambda, as SageMaker handles scaling, load balancing, and model updates automatically.

Answer

Deploy the model on Amazon ECS using a custom Docker image.

Answer

Deploy the model as an AWS Lambda function with the TensorFlow runtime.

Answer

Deploy the model using Amazon SageMaker Studio.

Question 10

A SageMaker Processing job fails with 'Access Denied' when listing objects in an S3 bucket, despite the IAM policy shown in the exhibit. What is the most likely cause?

Accepted Answer

The policy lacks `s3:ListBucket` permission.. The error 'Access Denied' when listing objects in an S3 bucket indicates that the IAM role used by the SageMaker Processing job lacks the `s3:ListBucket` permission. This permission is required for the `ListObjectsV2` API call, which is necessary to enumerate objects in the bucket. Even if the role has `s3:GetObject` and `s3:PutObject` permissions, without `s3:ListBucket`, the job cannot list the bucket contents and will fail with an access denied error.

Answer

The role does not have a trust relationship with SageMaker.

Answer

The bucket policy denies the access.

Answer

The bucket is in a different region.

Question 11

Refer to the exhibit. A Glue job runs successfully the first time but on subsequent runs with new data (added to the same input location), the job does not process the new data. What is the most likely cause?

Accepted Answer

The job bookmark is enabled, causing the job to skip already processed data. Option C is correct because when a Glue job bookmark is enabled, the job tracks previously processed data using a persistent state stored in a DynamoDB table. On subsequent runs, the bookmark mechanism skips files that have already been processed, so new data added to the same input location is ignored unless the bookmark is reset or the job is configured to process new partitions. This explains why the first run succeeds but later runs do not process new data.

Answer

The script location is incorrect

Answer

The MaxRetries is set to 0, so the job does not retry on failure

Answer

The WorkerType is Standard, which does not support incremental processing

Question 12

A company ingests daily log data into an S3 bucket. They need to update the existing ML training dataset with new data without reprocessing the entire history. Which two strategies should they adopt? (Choose two.)

Accepted Answer

Use AWS Glue to incrementally process new partitions. AWS Glue can perform incremental processing by using job bookmarks to track previously processed data and only process new partitions or files. This avoids reprocessing the entire historical dataset, making it efficient for updating ML training datasets with daily log data.

Answer

Store all data in a single large file and use append operations

Answer

Manually copy new files to the same S3 bucket

Answer

Overwrite the entire existing dataset with the new data

Question 13

Refer to the exhibit. The Glue job reads a CSV file and attempts to write to a Parquet table. What is the most likely cause of this error?

Accepted Answer

The 'price' column contains non-numeric values in some rows. Option C is correct because the error message indicates a 'NumberFormatException' when parsing the 'price' column, which occurs when Spark attempts to convert a string value to a numeric type. Since the Glue job's schema inference likely detected 'price' as a numeric column based on the majority of rows, any row containing a non-numeric value (e.g., 'N/A', 'null', or a currency symbol) will cause this parsing failure during the write to Parquet.

Answer

The 'price' column is missing from some rows

Answer

The schema inference incorrectly detected the column as String

Answer

The CSV file is compressed and not properly decompressed

Question 14

A data scientist is training a binary classifier on a highly imbalanced dataset (1:100 class ratio). The dataset contains 500,000 rows and 30 features. The data is stored in S3 in Parquet format. The data scientist wants to use SageMaker's built-in XGBoost algorithm. Which data preparation technique should the data scientist apply to best address the class imbalance without causing data leakage?

Accepted Answer

Use the scale_pos_weight parameter in XGBoost to assign higher weight to the minority class.. The scale_pos_weight parameter in XGBoost directly adjusts the loss function to penalize misclassifications of the minority class more heavily, effectively handling class imbalance without modifying the dataset. This avoids data leakage because the weighting is applied during training only, not during preprocessing, and does not involve any synthetic data generation or resampling that could inadvertently expose test information.

Answer

Undersample the majority class to create a balanced dataset, then split.

Answer

Oversample the minority class using SMOTE on the entire dataset before splitting into train/validation sets.

Answer

Randomly oversample the minority class by duplicating rows, then perform stratified train/test split.

Question 15

A team is using Amazon SageMaker for feature engineering. They have a dataset with a column 'TransactionDate' in string format (e.g., '2023-01-15 10:30:00'). They need to create features: year, month, day, hour, and day_of_week. What is the most efficient way to do this in a SageMaker processing job?

Accepted Answer

Use pandas datetime functions and then split. Option A is correct because using pandas datetime functions within a SageMaker processing job is the most efficient approach for this task. SageMaker processing jobs run custom Python scripts, and pandas provides vectorized operations (e.g., `pd.to_datetime()`, `.dt.year`, `.dt.month`, `.dt.day`, `.dt.hour`, `.dt.dayofweek`) that parse the string column and extract all required features in a single pass without external dependencies or data movement.

Answer

Use SageMaker built-in first party algorithms

Answer

Use AWS Glue for transformation

Answer

Use SQL query in Athena on S3 data

Question 16

A data scientist is performing feature engineering for a dataset with both numerical and categorical features. The data scientist wants to apply transformations that preserve the interpretability of the features. Which TWO transformations should the data scientist use? (Select TWO)

Accepted Answer

Log transformation of skewed numerical features. Log transformation is correct because it reduces skewness in numerical features by compressing the scale of large values, making the distribution more normal while preserving the original feature's interpretability (e.g., a log-transformed income value still relates to income). This is a monotonic transformation, so the order of values is maintained, and the feature remains directly understandable.

Answer

Target encoding of high-cardinality categorical features

Answer

PCA dimensionality reduction

Answer

One-hot encoding of categorical features

Question 17

A data scientist needs to convert categorical variables to numerical format for a linear regression model. The dataset contains a 'Country' column with 50 unique values. Which transformation should the engineer use to avoid introducing ordinal relationships?

Accepted Answer

One-hot encoding. One-hot encoding is correct because it creates binary columns for each category, avoiding any implicit ordinal relationship between the 50 unique countries. This is essential for linear regression, which assumes numerical inputs have meaningful order; one-hot encoding ensures the model treats each country as an independent category without ranking.

Answer

Label encoding

Answer

Target encoding

Answer

Ordinal encoding

Question 18

A data engineer is using Amazon SageMaker Processing to run a data preprocessing script on a dataset with 500 million rows. The script runs out of memory on a single ml.r5.24xlarge instance. The engineer needs to modify the processing job to handle the dataset size. Which approach is most cost-effective and scalable?

Accepted Answer

Configure the Processing job with multiple instances and use ShardedByS3Key for data splitting.. Option A is correct because SageMaker Processing with ShardedByS3Key splits the input dataset by S3 object boundaries across multiple instances, allowing distributed processing of the 500 million rows without exceeding memory on any single instance. This approach is cost-effective as it uses multiple smaller instances (e.g., ml.r5.xlarge) rather than a single oversized instance, and scales linearly with data size.

Answer

Write the script to process data in chunks and write intermediate results to local ephemeral storage.

Answer

Increase the instance type to a larger one like ml.p3dn.24xlarge with more memory.

Answer

Reduce the number of instances to one and increase the volume size for swap space.

Question 19

Refer to the exhibit. A data engineer deploys this Glue job via CloudFormation. When running, the job fails with a timeout after 2 hours. The job processes a large dataset and expected to take 3 hours. Which change would resolve the issue?

Accepted Answer

Increase the Timeout property to 240 minutes. The Glue job failed due to a timeout after 2 hours, but the expected runtime is 3 hours. The default timeout for AWS Glue jobs is 2880 minutes (48 hours), but the CloudFormation template likely set a lower value. Increasing the Timeout property to 240 minutes (4 hours) provides enough time for the job to complete without being prematurely terminated.

Answer

Increase NumberOfWorkers to 20

Answer

Set MaxRetries to 3

Answer

Change WorkerType to G.2X

Question 20

A data scientist is working with a dataset containing customer demographics and purchase history. The dataset includes categorical variables with high cardinality (e.g., ZIP code, product ID). The data scientist wants to perform feature engineering to improve model performance. Which THREE feature engineering techniques should the data scientist consider? (Choose three.)

Accepted Answer

Principal Component Analysis (PCA) to reduce dimensionality of numerical features.. Principal Component Analysis (PCA) is a dimensionality reduction technique that transforms correlated numerical features into a smaller set of uncorrelated principal components, capturing the maximum variance in the data. This is correct because the dataset includes numerical features (e.g., purchase amounts, age) where PCA can reduce noise and multicollinearity, improving model performance without losing critical information.

Answer

Domain-specific feature engineering based on business rules.

Answer

One-hot encoding all categorical features.