Model ensemble
Run independent predictors and combine them through a versioned aggregation rule.
Activity responsibilities
| Activity | Responsibility |
|---|---|
prepare-input | Execute the prepare input stage and publish its declared outputs for downstream activities. |
predict-a | Execute the predict A stage and publish its declared outputs for downstream activities. |
predict-b | Execute the predict B stage and publish its declared outputs for downstream activities. |
predict-c | Execute the predict C stage and publish its declared outputs for downstream activities. |
combine-predictions | Execute the combine predictions stage and publish its declared outputs for downstream activities. |
evaluate-ensemble | Execute the evaluate ensemble stage and publish its declared outputs for downstream activities. |
publish | Execute the publish stage and publish its declared outputs for downstream activities. |
Inputs
- Input dataset
- Component models
- Aggregation policy
Outputs
- Component predictions
- Ensemble output
- Evaluation
Provenance to preserve
- Component versions
- Aggregation weights
- Per-model logs
Source bundle
The executable workflow and its implementation files are maintained in the separate AkôFlow examples repository. The documentation intentionally keeps code, container recipes, generators, and validation scripts out of the narrative page.
Open the complete source bundle ↗Verified local execution
These captures and the output manifest were produced by the fixture's local Docker run and validator. They are published with the same bundle as the runnable files.
Execution considerations
Components may run in different environments. Transfer predictions when co-locating incompatible frameworks is more expensive.
AkôFlow boundary: the engine schedules, deploys, executes, transfers data, and records evidence. The ML or agent framework remains an implementation choice inside each activity.