DJames617 MLA-C01 / Domain 2 / 26%
ML Model Development
Model selection, training, tuning, evaluation, and refinement.
Official Task Statements
| Task | What to prove |
|---|---|
| MLA-2.1 | Choose a modeling approach. |
| MLA-2.2 | Train and refine models. |
| MLA-2.3 | Analyze model performance. |
Concepts You Need to Understand
- Model choice, built-in algorithms, custom containers, training jobs, hyperparameter tuning, evaluation metrics, bias, and explainability.
AWS services involved
- SageMaker AI
- SageMaker Training
- SageMaker Experiments
- SageMaker Clarify
- SageMaker Debugger
Important configurations
- Training instance type.
- Input channels.
- Tuning ranges.
- Evaluation metric.
- Experiment tracking.
Exam Decision Patterns
Least operational overhead
Prefer managed and serverless services when they satisfy the requirement. Exceptions appear when the scenario needs host control, unsupported runtimes, specialized network behavior, or exact migration compatibility.
Highly available
Identify the failure boundary. One instance is not HA. Multiple instances in one AZ help capacity but not AZ failure. Multi-AZ handles regional AZ faults. Multi-Region handles regional events but adds complexity and cost.
Durable
Durability is about preserving data. Use replication, versioning, backups, point-in-time recovery, and tested restore plans. A durable backup does not guarantee a low RTO.
Decouple the application
Use SQS for buffering work, SNS for fanout, EventBridge for event routing, and Step Functions for visible workflow state. Add retries, DLQs, and idempotent consumers.
Least privilege
Prefer roles and temporary credentials, scope actions/resources/conditions, watch explicit denies, and remember that resource policies may also be required.
Most cost-effective
Read usage pattern, duration, access frequency, scaling behavior, data transfer, and operations. Cheapest unit price is not always lowest total cost.
Lowest latency
Move content or compute closer to users, cache aggressively, choose the right database access pattern, and avoid unnecessary cross-Region or NAT paths.
Private connectivity
Use private subnets, VPC endpoints, PrivateLink, VPN, Direct Connect, Transit Gateway, and tight DNS/routing design instead of public exposure.
Minimum downtime
Separate deployment downtime, failure recovery, and data restore time. Use blue/green, canary, Multi-AZ, replication, and tested rollback where appropriate.
Automatic remediation
Pair a reliable signal with EventBridge or CloudWatch, a scoped Systems Manager Automation or Lambda action, and a validation step.
Common Mistakes
- Optimizing accuracy when precision, recall, latency, or cost is the real requirement.
- Ignoring class imbalance.
Example Architecture
Hands-On Activity
Choose evaluation metrics for fraud, image labeling, and recommendation scenarios.
For an AWS-account lab, use one of the linked mini labs and keep cleanup steps visible before you start.
Task-by-Task Study Notes
MLA-2.1 - Choose a modeling approach.
This task statement is asking whether you can turn a scenario into a decision. Start by identifying the workload requirement, the control or service family involved, and the tradeoff AWS is testing in this domain.
- Translate the wording into requirements: security, operations, cost, availability, latency, governance, or data behavior.
- Choose the service or configuration that directly satisfies those requirements with the least unnecessary complexity.
- Reject options that are technically possible but miss the domain goal or increase risk without a requirement.
MLA-2.2 - Train and refine models.
This task statement is asking whether you can turn a scenario into a decision. Start by identifying the workload requirement, the control or service family involved, and the tradeoff AWS is testing in this domain.
- Translate the wording into requirements: security, operations, cost, availability, latency, governance, or data behavior.
- Choose the service or configuration that directly satisfies those requirements with the least unnecessary complexity.
- Reject options that are technically possible but miss the domain goal or increase risk without a requirement.
MLA-2.3 - Analyze model performance.
This task statement is asking whether you can turn a scenario into a decision. Start by identifying the workload requirement, the control or service family involved, and the tradeoff AWS is testing in this domain.
- Translate the wording into requirements: security, operations, cost, availability, latency, governance, or data behavior.
- Choose the service or configuration that directly satisfies those requirements with the least unnecessary complexity.
- Reject options that are technically possible but miss the domain goal or increase risk without a requirement.
Review Checklist
Sources and Review Metadata
This independent training application is not affiliated with or endorsed by Amazon Web Services. AWS, Amazon Web Services, and AWS certification names are trademarks of Amazon.com, Inc. or its affiliates.