MLS-C01 Mock Exam 88 — 25 Questions

Question 1

A machine learning engineer is training a deep learning model on Amazon SageMaker. The training job is taking a long time. Which THREE actions can reduce training time? (Choose 3.)

Accepted Answer

Use SageMaker managed spot training. A is correct because SageMaker managed spot training leverages spare AWS EC2 capacity at a significantly lower cost, but more importantly, it can reduce training time by allowing you to use larger or more instances for the same budget. Spot instances can be interrupted, but SageMaker automatically resumes training from the last checkpoint, making this a viable speed-up strategy for fault-tolerant deep learning jobs.

Answer

Use a smaller batch size

Answer

Use SageMaker hyperparameter tuning jobs

Question 2

A company is using Amazon SageMaker to train a model on a dataset that is updated daily. The data is stored in an S3 bucket. The training pipeline uses AWS Step Functions to orchestrate data preprocessing and model training. The preprocessing step uses a SageMaker Processing job that reads data from S3, cleans it, and writes the output back to S3. The team notices that the training step often fails due to insufficient disk space on the processing instance. Which change should the team make to resolve this issue without increasing cost?

Accepted Answer

Configure the processing job to use local instance store (SSD) for scratch space.. The issue is insufficient disk space on the processing instance. Option D resolves this by configuring the processing job to use the local instance store (SSD) for scratch space, which provides high-throughput temporary storage without incurring additional cost, as the instance store is included with the instance. This allows the preprocessing step to handle larger intermediate data without requiring a larger or more expensive instance.

Answer

Enable automatic scaling for the processing job.

Answer

Use AWS Batch instead of SageMaker Processing.

Answer

Use a larger instance type with more memory.

Question 3

A data engineer needs to transfer 50 TB of historical data from an on-premises HDFS cluster to Amazon S3. The company has a 1 Gbps internet connection. Which service would complete the transfer in the shortest time?

Accepted Answer

AWS Snowball. AWS Snowball is the correct choice because transferring 50 TB over a 1 Gbps internet connection would take approximately 5.5 days (50 TB × 1024 GB/TB × 8 bits/byte ÷ 1 Gbps ÷ 86400 seconds/day), assuming full utilization, which is unrealistic due to overhead and contention. Snowball provides a physical appliance that can be loaded with data locally and shipped to AWS, completing the transfer in a few days including shipping time, making it faster than any network-based method for this volume.

Answer

Amazon S3 Transfer Acceleration

Answer

AWS Direct Connect

Answer

AWS DataSync

Question 4

A company is streaming clickstream data from a website to Amazon Kinesis Data Streams. The data is consumed by a Lambda function that enriches each record with geolocation information before writing to an S3 bucket. Recently, the Lambda function has been failing with throttling errors. What is the MOST likely cause?

Accepted Answer

The Lambda function's concurrent execution limit has been reached. The most likely cause is that the Lambda function's concurrent execution limit has been reached. Kinesis Data Streams invokes Lambda functions per shard, and with high throughput or many shards, concurrent invocations can exceed the default Lambda concurrency limit (1000 per region). This results in throttling errors. Option A is incorrect because the Lambda payload limit for asynchronous invocation (used by Kinesis) is 256 KB, not 6 MB. Option C is incorrect; setting reserved concurrency too high would not cause throttling—it could actually help avoid throttling. Option D is incorrect because the default shard limit is 500, but shard limits are a Kinesis concern, not directly causing Lambda throttling.

Answer

The Lambda function's payload size exceeds the 6 MB limit

Answer

The Lambda function's reserved concurrency is set too high

Answer

The Kinesis stream has exceeded the default shard limit of 500

Question 5

A company is using Amazon SageMaker to train a XGBoost model for predicting customer churn. The training data is stored in an S3 bucket as CSV files. The data scientist runs a hyperparameter tuning job with 50 training jobs. The tuning job completes, but the best model's accuracy on the holdout set is lower than expected. The data scientist suspects that the hyperparameter ranges are too narrow. Which corrective action is most appropriate?

Accepted Answer

Expand the hyperparameter ranges for key parameters such as 'max_depth', 'learning_rate', and 'subsample'. The data scientist suspects the hyperparameter ranges are too narrow, which directly limits the model's ability to find an optimal configuration. Expanding ranges for key XGBoost parameters like 'max_depth', 'learning_rate', and 'subsample' allows the tuning job to explore a broader space of model complexities and regularization levels, potentially improving accuracy on the holdout set. This is the most direct fix for the stated problem, as it addresses the root cause rather than increasing job count or changing the search strategy.

Answer

Increase the number of training jobs in the tuning job

Answer

Switch to a different algorithm like Random Forest

Answer

Change the tuning strategy from random search to Bayesian optimization

Question 6

Refer to the exhibit. An IAM policy is attached to a data engineering team's role. The team needs to upload data to the 'confidential' prefix in the 'my-data-lake' bucket. However, they are receiving 'AccessDenied' errors. What is the likely cause?

Accepted Answer

The Deny statement with the condition explicitly denies access to the 'confidential' prefix for accounts other than 123456789012.. The Deny statement explicitly denies access to the 'confidential' prefix when the request comes from an AWS account other than 123456789012. Since the data engineering team's role likely belongs to a different account, the Deny condition matches and overrides any Allow statements, resulting in an 'AccessDenied' error. In IAM, an explicit Deny always takes precedence over an Allow, so even if the Allow statement grants PutObject, the Deny blocks the upload.

Answer

The condition in the Deny statement requires the team to use a specific source IP address.

Answer

The Allow statement only grants GetObject and PutObject, but the team needs ListBucket.

Answer

The Allow statement's resource does not include the 'confidential' prefix.

Question 7

A company is building a binary classifier to predict customer churn. The dataset has 10,000 samples with 500 churners (5% positive class). After training a logistic regression model, the precision is 0.8 and recall is 0.2. Which metric should the data scientist focus on to improve the model's ability to identify churners while minimizing false positives?

Accepted Answer

Increase recall. The model's recall is very low (0.2), meaning it misses most churners. Since the goal is to identify churners (positive class), improving recall should be the primary focus. Option A (accuracy) is misleading due to class imbalance. Option B (precision) is already high (0.8), so further improvement would likely reduce recall. Option D (F1 score) balances precision and recall, but the immediate need is to address the low recall, not to balance both.

Answer

Increase accuracy

Answer

Increase precision

Answer

Increase F1 score

Question 8

A company uses Amazon SageMaker to train a custom TensorFlow model for image classification. The training job runs on a single ml.p3.2xlarge instance. The dataset contains 500,000 images stored in S3. The training time is too long (over 24 hours). The data scientist wants to reduce training time without changing the model architecture. The dataset is already in TFRecord format. The training script uses the default TensorFlow data pipeline. Which change will MOST significantly reduce training time?

Accepted Answer

Use SageMaker's distributed data parallelism with multiple instances.. Using SageMaker's distributed data parallelism with multiple instances increases the number of GPUs and splits the training data across them, directly reducing the compute time. Option A is incorrect because simply increasing the number of data files does not reduce the computational workload, and Pipe mode primarily helps with streaming data but does not accelerate model training. Option C is incorrect because switching from File to Pipe mode improves data loading but does not address the core compute bottleneck. Option D is incorrect because optimizing the data pipeline with tf.data.Dataset.prefetch and cache can improve I/O efficiency, but the most significant performance gain comes from scaling out the training across multiple GPUs.

Answer

Use SageMaker Pipe mode and increase the number of data files.

Answer

Switch the input mode from File to Pipe.

Answer

Optimize the data pipeline using tf.data.Dataset.prefetch and cache.

Question 9

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 10

A company uses an XGBoost model to predict equipment failures. The model has high precision but low recall. The business impact of a false negative is very high (missing a failure). Which action would MOST effectively increase recall while keeping precision reasonably high?

Accepted Answer

Decrease the probability threshold for the positive class. Decreasing the probability threshold for the positive class means the model will classify a case as a failure at a lower predicted probability, which captures more true positives (increases recall). However, this also allows more false positives, so precision may drop, but the trade-off is acceptable given the high cost of false negatives. This is a standard post-training calibration technique for imbalanced classification problems.

Answer

Increase the regularization parameter lambda

Answer

Set the objective to 'reg:squarederror'

Answer

Increase the number of boosting rounds

Question 11

A company is using Amazon Kinesis Data Streams to ingest real-time clickstream data. The data must be processed and stored in S3 in near real-time. Which THREE services can be used together to achieve this?

Accepted Answer

Amazon Kinesis Data Analytics. Amazon Kinesis Data Analytics is correct because it can process streaming clickstream data in real-time using SQL or Apache Flink, enabling transformations, aggregations, and filtering before the data is delivered downstream. It integrates directly with Kinesis Data Streams as a source and can output processed records to Kinesis Data Firehose for storage in Amazon S3, achieving near real-time processing and storage.

Answer

AWS Glue ETL

Answer

Amazon EMR

Question 12

A data scientist is building a time series forecasting model for monthly sales data. The scientist has observed that the sales data shows a clear upward trend and a seasonal pattern that repeats every 12 months. Which algorithm would be most appropriate for this task?

Accepted Answer

ARIMA. ARIMA (Autoregressive Integrated Moving Average) is specifically designed for time series forecasting and can handle both trend and seasonality through its parameters: the 'I' (differencing) removes trend, and seasonal ARIMA (SARIMA) extends it with seasonal differencing and seasonal AR/MA terms to capture the 12-month repeating pattern. This makes it the most appropriate choice for monthly sales data with a clear upward trend and annual seasonality.

Answer

Random Forest

Answer

k-means clustering

Answer

Linear regression with time-based features

Question 13

A machine learning engineer is deploying a real-time inference endpoint using Amazon SageMaker. The model is a large deep learning model that requires low latency (under 100 ms) and high throughput (1000 requests per second). Which SageMaker deployment option is MOST suitable?

Accepted Answer

Use SageMaker Inference Recommender to find the optimal instance type and endpoint configuration.. SageMaker Inference Recommender runs load tests against the model to identify the optimal instance type, instance count, and endpoint configuration (e.g., container parameters, model server settings) that meet the specific latency and throughput requirements. For a large deep learning model demanding under 100 ms latency and 1000 requests per second, this automated benchmarking is essential to avoid over-provisioning or under-provisioning resources.

Answer

Deploy the model on a single endpoint with automatic scaling based on CPU utilization.

Answer

Use SageMaker Serverless Inference with provisioned concurrency.

Answer

Use a multi-model endpoint to load multiple copies of the model on the same instance.

Question 14

A data scientist is performing EDA on a large dataset (10 TB) stored in S3. They need to compute summary statistics for each column. Which approach is most cost-effective and efficient?

Accepted Answer

Use Amazon Athena with SQL queries. Amazon Athena is a serverless query service that allows you to run SQL queries directly on data stored in S3, charging only for the data scanned per query. This makes it highly cost-effective and efficient for computing summary statistics on large datasets without needing to provision or manage infrastructure. Option A is wrong because AWS Glue ETL jobs with PySpark have startup overhead and are better suited for complex data transformation tasks rather than simple ad-hoc analysis. Option C is wrong because downloading 10 TB to a SageMaker Studio notebook incurs high data transfer costs and requires substantial local storage, which is neither efficient nor cost-effective. Option D is wrong because launching an Amazon EMR cluster involves provisioning and managing compute resources, leading to higher costs and complexity for a straightforward statistical analysis that Athena can handle more simply.

Answer

Use an AWS Glue ETL job with PySpark to compute statistics

Answer

Download the dataset to an Amazon SageMaker Studio notebook and use pandas

Answer

Launch an Amazon EMR cluster and use Spark SQL

Question 15

A company wants to deploy a machine learning model that provides real-time inference with low latency. The model is a small ensemble of three tree-based models. Which Amazon SageMaker approach is most appropriate?

Accepted Answer

Use a SageMaker real-time endpoint with a single inference container.. A SageMaker real-time endpoint with a single inference container is the most appropriate approach because it provides persistent, low-latency inference by keeping the model loaded in memory and handling requests synchronously. For a small ensemble of three tree-based models, a single container can host all models (e.g., using a custom inference script or a multi-model endpoint) and deliver sub-second response times, meeting the real-time requirement.

Answer

Use a SageMaker batch transform job.

Answer

Use AWS Lambda with the model packaged in a layer.

Answer

Use a SageMaker Serverless Inference endpoint.

Question 16

A data scientist is using Amazon SageMaker to train a model. The training dataset contains missing values in several features. The data scientist wants to impute missing values using the median of each feature. Which approach is most appropriate?

Accepted Answer

Compute the median of each feature on the training set only, then impute both training and test sets using that median. Computing the median on the training set only avoids data leakage, and applying that median to both training and test sets ensures consistent imputation without using test set information. Option A is incorrect because dropping rows with missing values discards potentially useful data and is not imputation. Option B is incorrect because computing the median on the entire dataset before splitting introduces data leakage, as the test set influences the imputation values. Option C is incorrect because imputing with zero is arbitrary and does not use the median; also, doing it before splitting would use the entire dataset, causing leakage.

Answer

Drop all rows that contain missing values

Answer

Compute the median on the entire dataset, then split into training and test sets

Answer

Impute missing values with zero for all features before splitting

Question 17

A data scientist is training a model using SageMaker's built-in XGBoost algorithm with a large dataset stored in CSV format. The training job is using File mode. The data scientist wants to reduce the time it takes to start training. Which approach would be most effective?

Accepted Answer

Use Pipe mode for the input data channel.. Pipe mode streams data directly from Amazon S3 into the training container, eliminating the need to first download the entire dataset to the EBS volume. This reduces the startup time significantly because training can begin as soon as the first records arrive, rather than waiting for the full download to complete.

Answer

Increase the size of the EBS volume.

Answer

Convert the data to Parquet format.

Answer

Increase the number of training instances.

Question 18

A data scientist is using Amazon SageMaker to train a deep learning model using a built-in algorithm. The training job uses an ml.p3.2xlarge instance and takes 10 hours to complete. The scientist wants to reduce training time without changing the algorithm or model architecture. The instance's GPU utilization is consistently at 95%, but CPU utilization is only 20%. The data input pipeline uses SageMaker Pipe mode with the 'TrainingInputMode' set to 'Pipe'. The training dataset is 200 GB in CSV format stored in S3. Which approach is most likely to reduce training time?

Accepted Answer

Use a larger instance type with more GPUs, such as ml.p3.8xlarge. GPU utilization is already at 95%, indicating the GPU is the bottleneck. Switching to a larger instance type like ml.p3.8xlarge provides four times the number of GPUs (4 vs. 1), allowing parallel processing of more data and directly reducing wall-clock training time without altering the algorithm or model architecture. The low CPU utilization (20%) confirms that the data pipeline is not a bottleneck, so I/O optimizations are unlikely to help.

Answer

Switch from Pipe mode to File mode to reduce I/O overhead

Answer

Use Pipe mode with 'S3DataType' as 'AugmentedManifestFile'

Answer

Reduce the batch size to improve GPU utilization

Question 19

A company is using Amazon SageMaker to tune hyperparameters for a gradient boosting model. The objective is to minimize root mean squared error (RMSE). The data scientist wants to explore the hyperparameter space efficiently. Which THREE hyperparameter tuning strategies should the data scientist consider? (Choose 3.)

Accepted Answer

Bayesian optimization. Bayesian optimization is correct because it builds a probabilistic model of the objective function (RMSE) and uses an acquisition function to select the next hyperparameter combination to evaluate. This approach is sample-efficient, making it ideal for expensive-to-evaluate models like gradient boosting, as it balances exploration and exploitation to find optimal hyperparameters with fewer trials.

Answer

Grid search

Answer

Manual search

Question 20

Which THREE of the following are best practices for feature engineering during EDA? (Select THREE.)

Accepted Answer

Apply log transformation to highly skewed features. Applying a log transformation to highly skewed features helps normalize their distribution, reducing the impact of extreme values and making the data more suitable for many machine learning algorithms that assume normally distributed features. This is a common technique during exploratory data analysis (EDA) to stabilize variance and improve model performance, especially for linear models and neural networks.

Answer

Remove all outliers from the dataset

Answer

Standardize all features to have zero mean and unit variance