AWS Certified Machine Learning – SpecialtyStudy guide
The specialty certification for designing ML data preparation, analysis, modeling, and operations on AWS (MLS-C01): the full ML workflow centered on SageMaker.
About AWS Certified Machine Learning – Specialty (MLS-C01)
AWS Certified Machine Learning – Specialty (MLS-C01) is a Specialty-level certification from AWS. This page organizes the exam scope into a 6-chapter, 18-section study guide and lets you check your understanding with exam-style practice questions. A good flow is to read the chapters below in order, then test yourself via "Practice questions."
Exam domains (approximate weighting)
- Data Engineering~20%
- Exploratory Data Analysis~24%
- Modeling~36%
- Machine Learning Implementation and Operations~20%
Weights are approximate guidance for the live exam. Each domain is covered in detail in the chapters and sections below.
Note: This exam has been retired.
Official exam information: https://aws.amazon.com/certification/certified-machine-learning-specialty/
1Data Engineering
- 1.1Data Collection and Ingestion
The starting point of ML—understand data sources, streaming ingestion (Kinesis), batch ingestion, and the S3 data lake. Land training data in S3 first.
- 1.2Data Transformation and Feature Preparation
Shape data into usable form—understand Glue ETL, the data catalog, Data Wrangler, feature engineering, and the Feature Store. Good features drive model quality.
- 1.3Storage and Data Formats
Store efficiently—understand columnar (Parquet/ORC), partitioning, S3 storage classes, and SageMaker input modes. Format and layout drive cost and speed.
2Exploratory Data Analysis
- 2.1Statistics and Distributions
Know your data—understand summary statistics (mean/median/variance), distributions, outliers, class imbalance, and correlation. Grasp the data before modeling.
- 2.2Exploration with Visualization
See to understand—learn when to use histograms, box plots, scatter plots, and correlation heatmaps. Quickly grasp data characteristics with the right chart.
- 2.3Preprocessing and Data Quality
Prepare for the model—understand imputation, outlier handling, encoding/scaling, class-imbalance handling (SMOTE), and avoiding data leakage.
3Modeling
- 3.1Choosing Algorithms
Match the model to the task—understand supervised (classification/regression), unsupervised (clustering/dimensionality reduction), SageMaker built-in algorithms, and specialized tasks (images/text/time series).
- 3.2Training, Overfitting, and Hyperparameter Tuning
Train well—understand overfitting/underfitting, bias/variance, regularization/early stopping, hyperparameter tuning (SageMaker Automatic Model Tuning), and cross-validation.
- 3.3Model Evaluation Metrics
Measure quality—understand the confusion matrix, precision/recall/F1, ROC-AUC, regression metrics (RMSE/MAE/R²), and metric choice under imbalance. Evaluate with the right metric.
4Machine Learning Implementation and Operations
- 4.1Deploying Models
Serve inference—understand real-time endpoints, batch transform, serverless/async inference, auto scaling, and multi-model endpoints. Choose the serving mode by use case.
- 4.2Monitoring and Retraining
Protect in production—understand Model Monitor, data drift, CloudWatch (latency/errors/invocations), and drift-triggered retraining. Models degrade over time.
- 4.3MLOps and Security
Automation and safety—understand SageMaker Pipelines, Model Registry, safe rollout (A/B/canary), and security via IAM/KMS/VPC. Achieve reproducible, secure ML operations.
5Advanced Modeling and Deep Learning
- 5.1Neural Network Fundamentals
The foundation of deep learning—understand layers and neurons, activation functions (ReLU/sigmoid/softmax), backpropagation, learning rate/epochs/batch, and the vanishing gradient.
- 5.2Deep Learning Architectures
Architectures by data—understand CNN (images), RNN/LSTM (sequences), Transformer (language), and choosing by use case. Pick architecture by the nature of the data.
- 5.3Transfer Learning and Tuning Deep Nets
Smart with little data—understand transfer learning/fine-tuning, SageMaker JumpStart, dropout/batch normalization, data augmentation, and early stopping.
6SageMaker Ecosystem and AI Services
- 6.1The SageMaker Workflow
A unified ML platform—understand SageMaker Studio, built-in algorithms, training jobs, Processing, and the prepare → train → deploy → monitor flow.
- 6.2High-Level AI Services
Use without building—understand Rekognition, Comprehend, Transcribe/Polly, Translate, Textract, and Personalize (the time-series Forecast service is closed to new use; its successor is SageMaker Canvas, etc.). Implement quickly via no-training APIs.
- 6.3Data Labeling and Build Strategy
The final call—understand Ground Truth (labeling), AI services vs custom, the cost/effort trade-off, and choosing wisely. Decide build vs buy smartly.