Skip to content

FVL-07 — Predictive Performance Engine #8

Description

@Sekiph82

Tracker: docs/FORMULAB_V1_TASK_TRACKER.md#fvl-07--predictive-performance-engine

Supervised ML (NOT an LLM) trained on real historical formulation + experiment data (FVL-05/FVL-06) to predict measurable performance. 16 tasks (FVL-07.001..016).

Acceptance criteria: explicit INSUFFICIENT_DATA eligibility gate; baseline model compared before any ML candidate; full model registry (dataset hash, feature-schema version, metrics, applicability domain); predictions carry uncertainty + applicability-domain warning; no regulatory/safety override by prediction; per-product-family models, never one universal model.

Dependencies: FVL-05.

Scope freeze rule: see docs/FORMULAB_V1_FINAL_SCOPE.md — zero LLM in this engine.

Metadata

Metadata

Assignees

No one assigned

    Labels

    formulab-v1FormuLab v1 completion scope (frozen)mlPredictive/ML work (FVL-07..FVL-10)

    Projects

    No projects

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions