MLS-C01 Practice Test 2 — 25 Questions

Question 1

A financial services company is deploying a machine learning model for credit risk assessment. The model must have an inference latency under 200ms and must be able to handle up to 1000 transactions per second (TPS). The company wants to minimize costs. The model is a gradient boosting model implemented in XGBoost. Which SageMaker deployment option should the team choose?

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

Accepted Answer

Deploy the model on a SageMaker real-time endpoint with multiple instances behind a load balancer.. A SageMaker real-time endpoint with multiple instances behind a load balancer provides the sub-200ms inference latency and 1000 TPS throughput required for synchronous, low-latency predictions. XGBoost models are well-suited for real-time endpoints, and horizontal scaling with multiple instances ensures high availability and cost efficiency by matching capacity to demand.

Answer

Use SageMaker Batch Transform to process transactions in batches.

Answer

Use SageMaker asynchronous inference for queued requests.

Answer

Use SageMaker Serverless Inference for automatic scaling.

Question 2

A machine learning team is using Amazon SageMaker to train a model with a custom algorithm packaged in a Docker container. The training job fails with the error 'Error: Unable to locate sagemaker-training toolkit.' What is the MOST likely cause?

Accepted Answer

The container does not include the SageMaker Training Toolkit. The SageMaker Training Toolkit is a required library that provides the interface between SageMaker and custom Docker containers for training jobs. When a custom container does not include this toolkit, SageMaker cannot execute the training script or communicate with the container, resulting in the 'Unable to locate sagemaker-training toolkit' error. This is a mandatory dependency for any custom training container used with SageMaker.

Answer

The container does not have internet access to download dependencies

Answer

The instance type is incompatible with the container

Answer

The training role does not have permissions to access the container repository

Question 3

Which THREE AWS services can be used together to build a serverless data pipeline that ingests streaming data, transforms it, and loads it into Amazon Redshift for analysis?

Accepted Answer

Amazon Kinesis Data Firehose. Amazon Kinesis Data Firehose (C) is correct because it is a fully managed, serverless service that can ingest streaming data and deliver it directly into Amazon Redshift (via S3 staging and the Redshift COPY command), making it ideal for the load stage of the pipeline. Amazon Kinesis Data Streams (D) is correct because it provides the serverless, scalable ingestion layer for capturing and buffering streaming data before it is consumed or transformed downstream. AWS Lambda (E) is correct because it is a serverless compute service that can be triggered by Kinesis to transform records in flight before they are loaded into Redshift, satisfying the transform requirement without managing servers. Amazon EMR (A) is not correct here because it is a managed big-data cluster service (EC2-based) rather than a serverless component, and it is not needed for this streaming ingest-transform-load pattern. Amazon SQS (B) is not correct because it is a message queue for decoupling applications, not a streaming data ingestion or delivery service for Redshift pipelines.

Answer

Amazon EMR

Answer

Amazon SQS

Question 4

A company uses Amazon Redshift for its data warehouse. The data engineering team needs to load 10 TB of data from Amazon S3 into Redshift every night. The team wants to minimize the load time and use the fewest number of COPY commands. The data is in CSV format and is partitioned by date in S3. Which approach should the team take?

Accepted Answer

Use a manifest file with a single COPY command.. Using a manifest file with a single COPY command is the most efficient approach because it allows Redshift to load data from multiple S3 objects (partitioned by date) in parallel, automatically splitting the workload across cluster nodes. This minimizes load time by leveraging Redshift's parallel processing without requiring multiple COPY commands or manual concatenation, and it avoids the overhead of additional services like AWS Glue for a straightforward bulk load.

Answer

Use multiple COPY commands, one per partition.

Answer

Concatenate all data into a single large file before loading.

Answer

Use AWS Glue to transform the data and then load into Redshift.

Question 5

A data scientist is building a regression model to predict house prices. The dataset contains features like 'number_of_rooms' (integer), 'sqft' (float), 'location' (categorical with 1000 unique values). Which feature engineering approach is BEST for the 'location' feature?

Accepted Answer

Target encoding. Target encoding is the best approach for the 'location' feature because it has 1,000 unique categories, making one-hot encoding infeasible (would create 1,000 dummy columns) and label encoding inappropriate (imposes arbitrary ordinal relationships). Target encoding replaces each category with the mean of the target variable (house price) for that category, capturing the predictive signal of location while keeping the feature as a single numeric column. This balances model performance with dimensionality and avoids overfitting when regularized (e.g., with smoothing or cross-validation).

Answer

Remove the feature

Answer

One-hot encoding

Answer

Label encoding

Question 6

Which TWO of the following are common techniques for handling missing values in a dataset during exploratory data analysis? (Select TWO.)

Accepted Answer

Remove rows or columns with missing values if they are few.. Option B is correct because listwise deletion (dropping rows) or dropping entire columns is a standard, simple technique when the proportion of missing data is small, minimizing information loss and bias. Option E is correct because mean or median imputation replaces missing entries with a central tendency statistic of the column, preserving sample size and being especially suitable for numerical features (median being robust to outliers). Option A is not a missing-value technique; feature scaling (e.g., Min-Max or StandardScaler) only rescales existing values and cannot handle NaNs. Option C, PCA, is a dimensionality-reduction method and does not address missing values directly (it typically requires complete data or prior imputation). Option D is incorrect because one-hot encoding converts categorical variables into binary vectors and does not fill or handle missing values.

Answer

Apply feature scaling to normalize the data.

Answer

Use Principal Component Analysis (PCA) to reduce dimensionality.

Answer

Apply one-hot encoding to the missing values.

Question 7

A data scientist uses SageMaker to train a model. The training job takes 10 hours, but the team needs to reduce costs. Which approach is MOST cost-effective?

Accepted Answer

Enable Managed Spot Training. Managed Spot Training on SageMaker uses spare EC2 capacity at up to 90% discount compared to on-demand pricing, making it the most cost-effective option for a 10-hour training job that can tolerate interruption. SageMaker automatically checkpoints and resumes training if the spot instance is reclaimed, so long jobs remain viable.

Answer

Use SageMaker Automatic Model Tuning

Answer

Use a larger instance type to finish faster

Answer

Use SageMaker Distributed Training with more instances

Question 8

A data scientist is training a neural network for image classification. The training loss is decreasing steadily, but the validation loss starts increasing after a few epochs. What is the MOST likely cause?

Accepted Answer

The model is overfitting to the training data. The validation loss increasing while the training loss continues to decrease is the classic signature of overfitting. The model is memorizing the training data (including noise) rather than learning generalizable patterns, causing it to perform poorly on unseen validation data.

Answer

The learning rate is too high

Answer

The gradients are vanishing

Answer

The model is underfitting

Question 9

A data scientist needs to run a one-time SQL query on a large dataset in Amazon S3. The dataset is stored in Parquet format and is about 500 GB. The query requires complex aggregations and joins. Which AWS service should be used to minimize cost and setup time?

Accepted Answer

Amazon Athena. Amazon Athena is the correct choice because it is a serverless query service that allows you to run SQL directly on data stored in S3 without provisioning any infrastructure. For a one-time query on 500 GB of Parquet data, Athena minimizes cost (pay-per-query, no idle cluster costs) and setup time (no cluster creation or data loading). Its ability to handle complex aggregations and joins on columnar formats like Parquet makes it ideal for this ad-hoc use case.

Answer

Amazon Redshift

Answer

Amazon RDS for MySQL

Answer

Amazon EMR with Spark SQL

Question 10

During EDA, a data scientist finds that a feature has a skewed distribution. They want to apply a log transformation to make it more Gaussian-like. Which Amazon SageMaker feature is most appropriate for this transformation?

Accepted Answer

Amazon SageMaker Data Wrangler. Amazon SageMaker Data Wrangler is designed for data preparation and feature engineering, including built-in transforms like log transformation to reduce skewness and make distributions more Gaussian-like. It provides a visual interface to apply, preview, and export these transformations directly into a SageMaker pipeline.

Answer

Amazon SageMaker Clarify

Answer

Amazon SageMaker JumpStart

Answer

Amazon SageMaker Ground Truth

Question 11

A company is using SageMaker to train a large NLP model. The training job is taking too long due to high I/O wait time. The data is stored as CSV files in S3. Which optimization should the company implement to reduce I/O wait time?

Accepted Answer

Use SageMaker Pipe mode to stream data directly from S3. SageMaker Pipe mode streams data directly from S3 into the training algorithm without first writing it to the local disk, eliminating the I/O wait time caused by downloading and decompressing CSV files. This is the most effective optimization for high I/O wait during training because it bypasses the bottleneck of writing large datasets to the instance's local storage.

Answer

Convert CSV files to RecordIO format

Answer

Use SageMaker batch transform before training

Answer

Use SageMaker File mode with larger instance storage

Answer

Use SageMaker ShardedByS3Key data distribution

Question 12

A machine learning engineer is building a pipeline to preprocess data and train a model using Amazon SageMaker. The data is stored in Amazon S3 and the preprocessing step is computationally intensive. The engineer wants to minimize costs while ensuring that the preprocessing step does not fail due to instance termination. Which instance type should be used for the preprocessing step?

Accepted Answer

On-demand instances. On-demand instances (Option B) are the correct choice because they provide reliable, non-interruptible compute capacity for the preprocessing step. Spot instances can be terminated at any time (with a 2-minute warning) when AWS reclaims capacity, which would cause the computationally intensive preprocessing to fail. Reserved instances require a 1- or 3-year commitment and are not cost-effective for a single preprocessing job that may not run continuously.

Answer

Reserved instances

Answer

A larger instance type to speed up processing

Answer

Spot instances

Question 13

Which THREE techniques can help reduce overfitting in a neural network trained on a small dataset?

Accepted Answer

Apply L2 weight regularization. L2 weight regularization (also known as weight decay) penalizes large weights by adding a term to the loss function proportional to the sum of squared weights. This forces the network to learn simpler patterns and reduces sensitivity to noise in the training data, which is especially helpful when the dataset is small and prone to overfitting.

Answer

Increase the number of hidden layers

Answer

Train for more epochs

Question 14

Which THREE factors should be considered when choosing an instance type for a SageMaker training job?

Accepted Answer

The number of vCPUs needed for parallel processing. Option A is correct because the number of vCPUs directly determines how many parallel data-processing threads or worker processes the training job can run, which affects throughput for CPU-bound workloads such as data loading, augmentation, and traditional ML algorithms. Option B is correct because the instance's RAM must accommodate the model parameters, gradients, optimizer states, and the training batch in memory; insufficient memory causes out-of-memory failures or forces smaller batch sizes. Option E is correct because GPU requirements (type, count, and GPU memory) are a primary driver for deep learning training, since frameworks like TensorFlow and PyTorch rely on CUDA-enabled GPUs such as the P3 or G4dn families for accelerated matrix operations. Option C is not relevant because endpoint latency concerns real-time inference hosting, not the training job itself. Option D is not a factor in instance-type selection because the AWS region determines availability and pricing, but the instance type is chosen based on compute, memory, and accelerator needs regardless of region.

Answer

The endpoint latency requirement

Answer

The AWS region where the instance is launched

Question 15

A data scientist wants to understand the statistical relationship between two categorical variables in a dataset. Which test is most appropriate?

Accepted Answer

Chi-squared test. The chi-squared test is used to determine if there is a significant association between two categorical variables, which is exactly what the data scientist wants to understand. Option B (Pearson correlation coefficient) is incorrect because it measures linear relationship between two continuous variables. Option C (Student's t-test) is used to compare means of two groups, typically for continuous data. Option D (ANOVA) is used to compare means across three or more groups, also for continuous data.

Answer

Pearson correlation coefficient

Answer

Student's t-test

Answer

ANOVA test

Question 16

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?

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 17

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 18

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 19

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 20

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