AWS Certified Machine Learning - Specialty Exam Prep Add-On (exam retired March 31, 2026)
AWS Certified Machine Learning - Specialty (MLS-C01) was AWS's senior-tier ML credential; AWS retired it March 31, 2026 and it can no longer be scheduled. AWS split its scope across three newer credentials rather than a direct replacement: AWS Certified Machine Learning Engineer Associate (closest successor for SageMaker/MLOps scope), AWS Certified AI Practitioner (foundation AI/GenAI), and AWS Certified Generative AI Developer Professional (Bedrock/foundation models). This content remains for MLS-C01 holders studying for the free renewal assessment; new candidates should target one of the three successors instead. The exam itself covered data engineering for ML, exploratory data analysis and modeling, ML deployment and operations on AWS, and ML implementation across the AWS service catalog, 180 minutes, 65 questions, scaled passing score of approximately 750/1000.
The exam owner retired this exam on 2026-03-31, so nobody can sit it now. We keep the questions for study and no longer sell an analysis for it.
We could not confirm which languages this exam is offered in. Check the owner's page before you book.
Owner: AWS · Read: · Source: AWS Certified Machine Learning Specialty
Exam fee at last check: not confirmed (the owner's page could not be read for the price on 2026-10-25; we hold $300 from an earlier check), per the vendor. The official objectives are at aws.amazon.com/certification/certified-machine-learning-specialty/. Verified 2026-10-25.
Practice is free. The full analysis adds the right answer, the explanation and the source for every question, readiness by domain and a study plan, for one payment.
- Data Engineering20%
- Exploratory Data Analysis and Modeling24%
- ML Implementation and Operations28%
- Machine Learning Implementation Across AWS Services28%
Source: Vendor exam objectives. Checked 2026-10-25. Bar length is relative to the heaviest domain; the figure beside each name is the published weight.
What's on the exam
Data Engineering 20%
How data lands in AWS for ML: ingestion, storage, ETL, feature engineering, data validation.
- Storage choices: S3, EBS, EFS, FSx for Lustre
- Ingestion: Kinesis Data Streams, Kinesis Data Firehose, AWS Glue
- ETL: AWS Glue, EMR with Spark, AWS Lambda
- Feature engineering: encoding categoricals, scaling, embeddings, time-window features
- Data validation: AWS Glue Data Quality, SageMaker Model Monitor data quality checks
Primary sources: AWS Certified Machine Learning Specialty exam guide, AWS SageMaker Developer Guide
Exploratory Data Analysis and Modeling 24%
Algorithm selection, hyperparameter tuning, and modeling decisions in AWS.
- Algorithm families: linear, tree-based (XGBoost), deep learning
- SageMaker built-in algorithms: XGBoost, Linear Learner, BlazingText, Object2Vec, etc.
- Hyperparameter tuning: SageMaker Automatic Model Tuning, Bayesian vs random search
- Evaluation metrics: accuracy, precision, recall, F1, ROC-AUC, RMSE, MAE
- Imbalanced data techniques: oversampling, class weighting, threshold adjustment
Primary sources: SageMaker built-in algorithms reference
ML Implementation and Operations 28%
Deploying, monitoring, and operating ML in AWS production.
- Deployment patterns: SageMaker real-time, batch transform, async, serverless
- Multi-model endpoints and multi-variant endpoints
- SageMaker Pipelines: orchestrating training, evaluation, registration
- Monitoring: SageMaker Model Monitor for data drift and model drift
- Security: VPC endpoints, KMS encryption, IAM least-privilege, network isolation
Primary sources: SageMaker Pipelines documentation, SageMaker Model Monitor
Machine Learning Implementation Across AWS Services 28%
Choosing the right AWS service for the use case and integrating across services.
- AI services: Rekognition, Transcribe, Translate, Comprehend, Textract, Forecast, Personalize
- AWS Bedrock: foundation models, model evaluation, agent framework
- Glue, EMR, Athena, Redshift for upstream data
- Choosing between custom training (SageMaker) and pre-built AI services (Comprehend, Rekognition)
- Hybrid architectures: SageMaker plus AWS AI services plus Bedrock
Primary sources: AWS Machine Learning services overview, AWS Bedrock developer guide
Exam-day strategy
Identify which exam domain a question targets (Data Engineering vs Modeling vs Implementation vs Cross-Service). The right answer often resolves by domain alignment.
AWS scenario questions usually have one option that names a managed service designed for the exact use case. Eliminate options that require custom code for problems AWS sells a service for.
Watch for distractors that confuse training-time vs serving-time services (Feature Store vs Model Monitor, Pipelines vs endpoints).
On algorithm questions, prefer the SageMaker built-in algorithm where one fits the data shape; custom Docker containers are rarely the canonical answer.
Pace at roughly 2 minutes 45 seconds per question. 180 minutes for 65 questions is generous; flag and return on multi-service architecture questions.
How to prepare for AWS Certified Machine Learning - Specialty Exam Prep Add-On (exam retired March 31, 2026)
- EVIDENCE-BACKEDPractice in the same format as the exam. How well practice matches the final test shapes how much it helps. (Yang et al., 2021)
- EVIDENCE-BACKEDStart practice questions in week one, even on topics you have not studied. Failed attempts before seeing the answer still helped learning. (Kornell et al., 2009 and others)
- EVIDENCE-BACKEDSpace your reviews over weeks instead of cramming the week before. (Cepeda et al., 2006 and others)
- PLAUSIBLEDivide the minutes by the questions before you start, and keep a margin for a second pass if the exam allows one. (Sound arithmetic; no study compared time budgets on a licensing exam.)
Why this works
EVIDENCE-BACKED At least one peer-reviewed study or official source found the effect or states the fact. A study can be small.
PLAUSIBLE Reasonable and partly studied, but not tested on exams, or the results are mixed.
Practice that matches the final test format works better than practice that does not.
Failed attempts before seeing the answer still improved later learning of the material asked about; the benefit for material not asked about was virtually nil.
Spacing beat massing across hundreds of experiments and beat cramming with flashcards; combined with retrieval it raised scores on a real high-stakes exam.
Sound arithmetic; no study compared time budgets on a licensing exam.
Sources
- Yang, C., Luo, L., Vadillo, M. A., Yu, R., & Shanks, D. R. (2021). Testing (quizzing) boosts classroom learning: A systematic and meta-analytic review. Psychological Bulletin, 147(4), 399-435. doi.org/10.1037/bul0000309
- Kornell, N., Hays, M. J., & Bjork, R. A. (2009). Unsuccessful retrieval attempts enhance subsequent learning. Journal of Experimental Psychology: Learning, Memory, and Cognition, 35(4), 989-998. doi.org/10.1037/a0015729
- Richland, L. E., Kornell, N., & Kao, L. S. (2009). The pretesting effect: Do unsuccessful retrieval attempts enhance learning? Journal of Experimental Psychology: Applied, 15(3), 243-257. doi.org/10.1037/a0016496
- St. Hilaire, K. J., Chan, J. C. K., & Ahn, D. (2024). Guessing as a learning intervention: A meta-analytic review of the prequestion effect. Psychonomic Bulletin & Review, 31(2), 411-441. doi.org/10.3758/s13423-023-02353-8
- Cepeda, N. J., Pashler, H., Vul, E., Wixted, J. T., & Rohrer, D. (2006). Distributed practice in verbal recall tasks: A review and quantitative synthesis. Psychological Bulletin, 132(3), 354-380. doi.org/10.1037/0033-2909.132.3.354
- Kornell, N. (2009). Optimising learning using flashcards: Spacing is more effective than cramming. Applied Cognitive Psychology, 23(9), 1297-1317. doi.org/10.1002/acp.1537
- Kang, S. H. K. (2016). Spaced repetition promotes efficient and effective learning: Policy implications for instruction. Policy Insights from the Behavioral and Brain Sciences, 3(1), 12-19. doi.org/10.1177/2372732215624708
- Janes, J. L., Dunlosky, J., Rawson, K. A., & Jasnow, A. (2020). Successive relearning improves performance on a high-stakes exam in a difficult biopsychology course. Applied Cognitive Psychology, 34(5), 1118-1132. doi.org/10.1002/acp.3699
Additional resources
Explore Related Cybersecurity Resources
DecipherU is independent of Amazon Web Services. Certified Machine Learning - Specialty (MLS-C01, retired March 31, 2026) is a trademark of Amazon Web Services. DecipherU is not endorsed by, sponsored by, or affiliated with any certifying body.