MLS-C01 Practice Test 36 — 15 Questions

Question 1

A data scientist is using SageMaker to train a deep learning model. The training script uses TensorFlow and runs on a single p3.2xlarge instance. The scientist wants to reduce training time by using multiple GPUs. What should the scientist do?

Accepted Answer

Modify the training script to use Horovod for distributed training.. Modifying the training script to use Horovod (Option B) is required for distributed training across multiple GPUs. Option A (increasing instance type) only uses more GPUs on one machine if the script supports it. Option C (using Spot) does not add GPUs. Option D (changing to PyTorch) is unnecessary.

Answer

Increase the instance count to 4 without changing the script.

Answer

Switch to PyTorch framework.

Answer

Use SageMaker Managed Spot Training.

Question 2

A company is using Amazon SageMaker to build a binary classification model. The dataset is highly imbalanced, with 95% negative class and 5% positive class. Which technique should be used to address the class imbalance?

Accepted Answer

Use a weighted loss function during training.. Option D is correct because using a weighted loss function during training assigns higher weight to the minority class, helping the model learn better from imbalanced data. Option A is wrong because removing the majority class reduces data size and may lose important patterns. Option B is wrong because random under-sampling can discard useful data. Option C is wrong because using accuracy as the evaluation metric is inappropriate for imbalanced data; precision/recall or AUC are better.

Answer

Use accuracy as the primary evaluation metric.

Answer

Perform random under-sampling of the majority class.

Answer

Remove all examples from the majority class.

Question 3

A data scientist is deploying a PyTorch model to Amazon SageMaker for real-time inference. The model runs on a large instance but inference latency is too high. Which action is MOST likely to reduce latency without sacrificing accuracy?

Accepted Answer

Compile the model using SageMaker Neo. Option B is correct because SageMaker Neo optimizes trained models for target hardware, reducing latency without retraining. Option A may reduce latency but could affect accuracy. Option C changes instance type but not necessarily optimize the model. Option D changes endpoint type, not latency.

Answer

Switch from a GPU instance to a CPU instance

Answer

Quantize the model weights from FP32 to INT8

Answer

Deploy the model to a multi-model endpoint

Question 4

A company is using Amazon SageMaker to train a large natural language processing model. The training job uses a GPU instance and is expected to take several hours. The data scientist wants to monitor GPU utilization in real-time. Which approach is MOST effective?

Accepted Answer

Enable CloudWatch metrics for the training job and view GPU utilization in the CloudWatch console. Option A is correct because SageMaker publishes CloudWatch metrics for GPU utilization. Option B uses a custom solution when a built-in one exists. Option C is for debugging, not real-time monitoring. Option D is for managed spot training, not monitoring.

Answer

Use SageMaker Managed Spot Training to reduce cost and monitor utilization via spot instance status

Answer

Modify the training script to periodically log GPU utilization to a file in S3

Answer

Use SageMaker Debugger to capture GPU utilization tensors

Question 5

An ML team deploys a real-time inference endpoint on Amazon SageMaker. Users report high latency. The model is a PyTorch model using a custom container. Which combination of changes should the team implement to reduce latency? (Choose the best answer.)

Accepted Answer

Use SageMaker Inference Recommender to benchmark different instance families and select the best.. Enabling SageMaker Inference Recommender (Option D) generates multiple endpoint configurations to find the optimal instance type and model compilation settings. Option A (compilation only) helps but may not find the best instance. Option B (Elastic Inference) is deprecated. Option C (Asynchronous Inference) is for near-real-time, not true low-latency.

Answer

Switch to asynchronous inference endpoint.

Answer

Use SageMaker Elastic Inference to attach an accelerator.

Answer

Compile the model using SageMaker Neo.

Question 6

A company has a real-time inference endpoint on Amazon SageMaker that uses a custom container. The endpoint is experiencing high latency and occasional 502 errors. The logs from the container show that the model inference time is low, but the overall response time is high. Which step is MOST likely to reduce the latency?

Accepted Answer

Increase the number of instances and enable auto-scaling. Option C is correct because increasing the endpoint's instance count and enabling auto-scaling can distribute the load and reduce queuing delays. Option A is wrong because the inference time is already low, so optimizing the model further won't help much. Option B is wrong because increasing instance size may help but is less cost-effective than scaling out. Option D is wrong because switching to batch transform is for offline inference, not real-time.

Answer

Switch to batch transform to process requests in batches

Answer

Use a larger instance type for the endpoint

Answer

Optimize the model to reduce inference time

Question 7

A company uses Amazon SageMaker to host a model for fraud detection. The model uses a custom XGBoost container. The endpoint receives about 100 requests per second, each with 50 features. The team notices that the model's predictions are occasionally incorrect for a subset of requests. Which approach should the team take to debug the issue?

Accepted Answer

Enable SageMaker Model Monitor to capture and analyze inference data.. Enabling SageMaker Model Monitor with data capture (Option D) allows the team to review actual input data and predictions to detect data drift or anomalies. Option A (CloudWatch Logs) only shows container logs, not per-request payloads. Option B (Debugger) is for training, not inference. Option C (increase instances) addresses capacity, not accuracy.

Answer

Use SageMaker Debugger to capture tensors during inference.

Answer

Scale the endpoint to more instances to reduce load.

Answer

Enable detailed CloudWatch Logs for the endpoint.

Question 8

A company uses Amazon SageMaker to deploy a model for real-time predictions. The model is updated weekly. The company wants to ensure that the new model version is gradually rolled out to a small percentage of traffic before full deployment, and that it can be rolled back quickly if issues are detected. Which deployment strategy should be used?

Accepted Answer

Canary deployment using SageMaker endpoint variants. Option D is correct because SageMaker supports canary deployments using endpoint variants, allowing a small percentage of traffic to be directed to the new model version. Option A is wrong because blue/green deployment switches all traffic at once. Option B is wrong because A/B testing is for comparing models, not gradual rollout. Option C is wrong because rolling deployment is not natively supported by SageMaker endpoints.

Answer

Blue/green deployment

Answer

A/B testing with a holdout group

Answer

Rolling deployment across multiple endpoints

Question 9

A data science team is deploying a machine learning model using Amazon SageMaker. The model requires GPU inference and must handle variable traffic with low latency. Which TWO options should the team implement to meet these requirements? (Choose TWO.)

Accepted Answer

Use a SageMaker multi-model endpoint with a GPU instance to serve multiple models.. Option A (SageMaker real-time endpoint with GPU instance) ensures GPU inference and low latency for real-time predictions. Option E (SageMaker multi-model endpoint) reduces cost by sharing a GPU instance across multiple models, which is efficient for variable traffic. The other options either do not support GPU (B, D) or are not suitable for real-time low-latency inference (C).

Answer

Deploy to a SageMaker real-time endpoint using a CPU instance and attach an Elastic Inference accelerator.

Answer

Use AWS Lambda with an attached GPU function for inference.

Answer

Host the model on a SageMaker batch transform job with GPU instances.

Question 10

A team wants to move data from an on-premises Oracle database to Amazon S3 for analytics. The pipeline must run daily and handle incremental updates. Which THREE services should they use together? (Choose three.)

Accepted Answer

Amazon S3. Options A, B, and D are correct. AWS DMS can do continuous replication from Oracle to S3. Glue can transform the data. S3 is the target. Option C is wrong because SageMaker is for ML, not data ingestion. Option E is wrong because Athena is a query engine, not a data movement service.

Answer

Amazon SageMaker

Answer

Amazon Athena

Question 11

A company uses Amazon Kinesis Data Streams to ingest clickstream data. They need to archive raw data to S3 every hour and also enable real-time processing with sub-second latency. Which TWO actions should they take? (Choose two.)

Accepted Answer

Configure a Lambda function as a consumer of the stream for real-time processing.. Options A and D are correct. Option A provides real-time processing via Lambda. Option D archives data to S3 using Firehose with hourly buffering. Option B is wrong because Kinesis Agent is for log files, not archiving. Option C is wrong because Data Analytics does not write to S3 directly. Option E is wrong because S3 events are not used for archiving.

Answer

Use Kinesis Data Analytics to write output to S3.

Answer

Use S3 events to trigger a Lambda function that reads from the stream.

Answer

Install the Kinesis Agent on an EC2 instance to write data to S3.

Question 12

A company is building a recommendation system using Amazon SageMaker. The data is stored in a large S3 bucket with millions of small CSV files. The team wants to train a factorization machines model. Which data ingestion strategy will be MOST efficient?

Accepted Answer

Use a SageMaker Processing job with a Spark container to read the files and write a single RecordIO file.. Using SageMaker Processing with Spark (Option C) can efficiently read many small files and convert them to a single RecordIO file, which is optimal for SageMaker training. Option A (direct training) would be slow due to many small files. Option B (Athena) is for SQL queries, not data conversion. Option D (Data Wrangler) is for smaller datasets and manual analysis.

Answer

Use Amazon Athena to query the data and output to a single CSV.

Answer

Point the training job directly to the S3 bucket containing the CSV files.

Answer

Use SageMaker Data Wrangler to create a data flow and export to a training dataset.

Question 13

A data engineer needs to set up a data lake on S3 that supports both batch and streaming ingestion. The data must be queryable by Athena, Redshift Spectrum, and EMR. Which TWO configurations are essential? (Choose two.)

Accepted Answer

Store data in columnar formats like Parquet or ORC.. Options A and B are correct. Option A ensures the Glue Data Catalog is used as a metastore for all services. Option B stores data in columnar format for query efficiency. Option C is wrong because S3 Select is not required. Option D is wrong because Kinesis is needed only for streaming. Option E is wrong because S3 versioning is not essential for querying.

Answer

Enable S3 Select on the target buckets.

Answer

Enable S3 versioning on all buckets.

Answer

Set up Kinesis Data Firehose for streaming ingestion.

Question 14

A data engineer needs to move 50 TB of historical data from an on-premises Hadoop cluster to Amazon S3. The network bandwidth is limited to 100 Mbps. Which AWS service should be used to transfer the data most efficiently?

Accepted Answer

AWS Snowball Edge device to physically ship the data.. Option C is correct because AWS Snowball is designed for large data transfers over limited bandwidth. Option A is wrong because Direct Connect requires high bandwidth and doesn't physically move data. Option B is wrong because S3 Transfer Acceleration speeds up transfers over the internet but still limited by bandwidth. Option D is wrong because VPN is not efficient for 50 TB.

Answer

Amazon S3 Transfer Acceleration to speed up the transfer.

Answer

AWS Direct Connect to establish a dedicated network connection.

Answer

AWS Site-to-Site VPN to connect and copy data.

Question 15

A company uses AWS Glue to run ETL jobs on a daily schedule. The jobs are failing intermittently with 'OutOfMemory' errors. The data volume has grown 5x over the past month. Which is the MOST cost-effective fix?

Accepted Answer

Increase the number of DPUs for the Glue job. Increasing the number of DPUs (data processing units) in the Glue job configuration provides more memory and parallelism cost-effectively. Switching to EMR is more expensive and complex. Reducing data is not a solution. Increasing S3 partitions does not affect memory.

Answer

Increase the number of partitions in the source S3 data

Answer

Reduce the data volume by sampling

Answer

Switch from AWS Glue to Amazon EMR