Search...

AWS Machine Learning Specialty Study Guide

Domain-by-domain study guide for AWS Certified Machine Learning - Specialty (MLS-C01). Covers all 4 exam objectives with topic checklists, quick notes, and practice links.

Download PDF Notes

Exam Overview

Key facts before you start studying

Duration

180 min

Questions

Exam Code

MLS-C01

Domains

About this exam

Citation-ready facts for AWS Machine Learning Specialty (MLS-C01)

AWS Machine Learning Specialty (MLS-C01) is a AWS certification exam with about 65 questions over 180 minutes, typically requiring a scaled score of 750 to pass. Official domain weights on CertStud: Data Engineering (20%); Exploratory Data Analysis (24%); Modeling (36%); ML Implementation and Operations (20%).

Use this study guide with free practice questions, the week-by-week study plan, and detailed notes. Confirm current objectives and scoring on the official AWS exam page before booking.

Quick Navigation

Jump to a specific exam domain

1. Data Engineering (20%)
2. Exploratory Data Analysis (24%)
3. Modeling (36%)
4. ML Implementation and Operations (20%)

Domain 1

20%

Data Engineering

Create data repositories and ingest, transform data for ML

Topics to Master

Data collection strategies and ingestion patterns
AWS Glue for ETL and data cataloging
Amazon S3 for data lakes and storage optimization
Amazon Kinesis for streaming data ingestion
AWS Data Pipeline and Step Functions for orchestration
Database options for ML workloads (DynamoDB, RDS, Redshift)
Data preprocessing and cleansing techniques
Data partitioning and compression strategies
Lake Formation and data governance
Real-time vs batch processing trade-offs

Domain 2

24%

Exploratory Data Analysis

Sanitize and prepare data for modeling, perform feature engineering

Topics to Master

Feature engineering and transformation techniques
Statistical analysis and hypothesis testing
Handling missing values, outliers, and imbalanced data
Data visualization for ML insights
Dimensionality reduction (PCA, t-SNE)
Encoding categorical variables
SageMaker Data Wrangler for EDA
Amazon Athena for ad-hoc data analysis
Correlation analysis and feature importance
Train/validation/test split strategies

Domain 3

36%

Modeling

Frame ML problems, train models, perform hyperparameter tuning

Topics to Master

SageMaker built-in algorithms (XGBoost, Linear Learner, K-Means)
Supervised vs unsupervised vs reinforcement learning
Model training strategies and distributed training
Hyperparameter tuning with SageMaker Automatic Model Tuning
Deep learning frameworks (TensorFlow, PyTorch, MXNet)
Model evaluation metrics (accuracy, AUC, F1, RMSE)
Cross-validation and regularization techniques
Transfer learning and fine-tuning pre-trained models
Model debugging with SageMaker Debugger
Handling overfitting and underfitting

Domain 4

20%

ML Implementation and Operations

Deploy and operationalize ML solutions, monitor performance

Topics to Master

SageMaker endpoint deployment and auto-scaling
Batch transform for bulk inference
A/B testing with SageMaker multi-variant endpoints
Model monitoring and data drift detection
SageMaker Pipelines for MLOps automation
SageMaker Model Registry and model versioning
Security controls for ML workloads (IAM, VPC, KMS)
Cost optimization for ML training and inference
SageMaker Edge Manager for edge deployments
Containerized ML workflows with Docker on SageMaker

Continue Your Prep

Free CertStud resources for MLS-C01

Study Notes Exam Study Plan Start Practice Test

Back to AWS Machine Learning Specialty

AWS Machine Learning Specialty Study Guide

Domain-by-domain study guide for AWS Certified Machine Learning - Specialty (MLS-C01). Covers all 4 exam objectives with topic checklists, quick notes, and practice links.

Download PDF Notes

Exam Overview

Key facts before you start studying

Duration

180 min

Questions

Exam Code

MLS-C01

Domains

About this exam

Citation-ready facts for AWS Machine Learning Specialty (MLS-C01)

Use this study guide with free practice questions, the week-by-week study plan, and detailed notes. Confirm current objectives and scoring on the official AWS exam page before booking.

Quick Navigation

Jump to a specific exam domain

1. Data Engineering (20%)
2. Exploratory Data Analysis (24%)
3. Modeling (36%)
4. ML Implementation and Operations (20%)

Domain 1

20%

Data Engineering

Create data repositories and ingest, transform data for ML

Topics to Master

Data collection strategies and ingestion patterns
AWS Glue for ETL and data cataloging
Amazon S3 for data lakes and storage optimization
Amazon Kinesis for streaming data ingestion
AWS Data Pipeline and Step Functions for orchestration
Database options for ML workloads (DynamoDB, RDS, Redshift)
Data preprocessing and cleansing techniques
Data partitioning and compression strategies
Lake Formation and data governance
Real-time vs batch processing trade-offs

Domain 2

24%

Exploratory Data Analysis

Sanitize and prepare data for modeling, perform feature engineering

Topics to Master

Feature engineering and transformation techniques
Statistical analysis and hypothesis testing
Handling missing values, outliers, and imbalanced data
Data visualization for ML insights
Dimensionality reduction (PCA, t-SNE)
Encoding categorical variables
SageMaker Data Wrangler for EDA
Amazon Athena for ad-hoc data analysis
Correlation analysis and feature importance
Train/validation/test split strategies

Domain 3

36%

Modeling

Frame ML problems, train models, perform hyperparameter tuning

Topics to Master

SageMaker built-in algorithms (XGBoost, Linear Learner, K-Means)
Supervised vs unsupervised vs reinforcement learning
Model training strategies and distributed training
Hyperparameter tuning with SageMaker Automatic Model Tuning
Deep learning frameworks (TensorFlow, PyTorch, MXNet)
Model evaluation metrics (accuracy, AUC, F1, RMSE)
Cross-validation and regularization techniques
Transfer learning and fine-tuning pre-trained models
Model debugging with SageMaker Debugger
Handling overfitting and underfitting

Domain 4

20%

ML Implementation and Operations

Deploy and operationalize ML solutions, monitor performance

Topics to Master

SageMaker endpoint deployment and auto-scaling
Batch transform for bulk inference
A/B testing with SageMaker multi-variant endpoints
Model monitoring and data drift detection
SageMaker Pipelines for MLOps automation
SageMaker Model Registry and model versioning
Security controls for ML workloads (IAM, VPC, KMS)
Cost optimization for ML training and inference
SageMaker Edge Manager for edge deployments
Containerized ML workflows with Docker on SageMaker

Continue Your Prep

Free CertStud resources for MLS-C01

Study Notes Exam Study Plan Start Practice Test