trading-platform/docs/02-definicion-modulos/OQI-006-ml-signals/requerimientos/RNF-ML-001-no-funcionales.md
Adrian Flores Cortes 8f0235c096 [TASK-2026-02-06-ANALISIS-INTEGRAL-DOCUMENTACION] docs: Complete 6-phase documentation analysis
- FASE-0: Diagnostic audit of 500+ files, 33 findings cataloged (7P0/8P1/12P2/6P3)
- FASE-1: Resolved 7 P0 critical conflicts (ports, paths, dedup OQI-010/ADR-002, orphan schemas)
- FASE-2: Resolved 8 P1 issues (traces, README/CLAUDE.md, DEPENDENCY-GRAPH v2.0, DDL drift, stack versions, DoR/DoD)
- FASE-3: Resolved 12 P2 issues (archived tasks indexed, RNFs created, OQI-010 US/RF/ET, AGENTS v2.0)
- FASE-4: Purged 3 obsolete docs to _archive/, fixed MODELO-NEGOCIO.md broken ref
- FASE-5: Cross-layer validation (DDL→OQI 66%, OQI→BE 72%, BE→FE 78%, Inventories 95%)
- FASE-6: INFORME-FINAL, SA-INDEX (18 subagents), METADATA COMPLETED

27/33 findings resolved (82%), 6 P3 deferred to backlog.
18 new files created, 40+ modified, 4 archived.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-06 10:57:03 -06:00

39 lines
1.1 KiB
Markdown

---
id: RNF-ML-001
title: "Requerimientos No Funcionales - ML Signals"
type: "Non-Functional Requirement"
epic: OQI-006
version: "1.0.0"
created_date: "2026-02-06"
---
# RNF-ML-001: Requerimientos No Funcionales - ML Signals
## Rendimiento
- Signal generation < 5s per symbol
- Batch prediction (50 symbols) < 30s
- Model inference < 500ms per prediction
- Backtesting 1 year < 2 minutes
## Precision
- Signal accuracy target: > 60% hit rate
- Range prediction: 85%+ accuracy (verificado)
- TP/SL classification: 0.94+ AUC (verificado)
- AMD detection: validated against 10+ years historical
## Disponibilidad
- ML Engine: 99% uptime (non-critical path for trading)
- Graceful degradation: show stale signals if engine down
- Model versioning: rollback to previous model < 5 min
## Datos
- Training data: 10+ anos historicos por activo
- Supported assets: XAUUSD, EURUSD, GBPUSD, USDJPY (extensible)
- Feature refresh: cada candle close
- Model retraining: weekly scheduled
## Monitoreo
- Model drift detection (accuracy drop > 5%)
- Prediction confidence distribution tracking
- Signal P&L attribution