MLS-C01 Practice Test 4 — 10 Questions

Question 1

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 2

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 3

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 4

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 5

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 6

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 7

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 8

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 9

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 10

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