Files
QuantEngineByItz/spec/strategy/anti_late_entry_pullback_gate_v4.yaml
kjh2064 ee3e799de1 feat: 리밸런싱 엔진 V1 + GAS 버그 수정 (2026-06-13)
주요 변경:
- tools/build_rebalance_engine_v1.py: REBALANCE_ENGINE_V1 신규
  * account_snapshot 직접 합산(_build_snap_position_map) → 소수주 분리 행 병합
  * 레짐 소스 macro.REGIME_PRELIM 최우선 (GAS 와 동일)
- src/gas_adapter_parts/gdf_06_rebalance.gs: runRebalanceSheet_() 신규
  * Logger.log / getSpreadsheet_() 로 run_all 연동 수정
- src/gas_adapter_parts/gdc_01_fetch_fundamentals.gs
  * _mergePositionRecord_(): 소수주 중복 행 합산 신규
  * parseInt → parseFloat (qty, availQty)
- src/gas_adapter_parts/gdf_01_price_metrics.gs
  * 미보유 종목 SELL_READY → WATCH_EXIT_SIGNAL
- spec/41_release_dag.yaml: build_rebalance_sheet 노드 추가 (step_count 63)
- spec/51_formula_lifecycle_registry.yaml: REBALANCE_ENGINE_V1 등록

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-13 13:20:14 +09:00

55 lines
2.0 KiB
YAML

schema_version: 2026-06-03-anti-late-entry-pullback-gate-v4
formula_id: ANTI_LATE_ENTRY_GATE_V2_CALIBRATED
purpose: 뒷박(late-chase) 매수 차단 — T+5 실측 기반 보정 루프.
required_fields:
- prediction_match_rate_pct
- t5_direction_accuracy_pct
- buy_after_5d_runup_without_pullback_count
# ── velocity 버킷 기반 실측 보정 (SCAFFOLDED_PENDING_LIVE_DATA) ─────────────
# [SCAFFOLDED_PENDING_LIVE_DATA: late_chase_attribution_samples=0, target>=30]
calibration:
formula_id: ANTI_LATE_ENTRY_GATE_V2_CALIBRATED
status: SCAFFOLDED_PENDING_LIVE_DATA
current_samples: 0
target_samples: 30
velocity_buckets:
- id: LOW
range: "velocity_1d < 1.0%"
t5_win_rate: null
t5_avg_return: null
sample_count: 0
label: "[UNVALIDATED_LIVE: n=0]"
- id: MID
range: "1.0% <= velocity_1d < 3.0%"
t5_win_rate: null
t5_avg_return: null
sample_count: 0
label: "[UNVALIDATED_LIVE: n=0]"
- id: HIGH
range: "velocity_1d >= 3.0%"
t5_win_rate: null
t5_avg_return: null
sample_count: 0
label: "[UNVALIDATED_LIVE: n=0]"
gate: GATE1_BLOCK
gate_basis: EXPERT_PRIOR
gate_threshold:
velocity_1d_block_pct: 3.0
threshold_source: EXPERT_PRIOR
threshold_note: "[UNVALIDATED: 실측 표본 30건 누적 전까지 EXPERT_PRIOR(3%) 유지]"
calibration_allowed: false # 표본 < 30 → 자동 적용 금지, 데이터 충족 후 수동 적용
chase_entry_rate:
formula: "(velocity_1d>=3% 진입건 / 전체 BUY)"
current: null
target: "<= 10%"
label: "[UNVALIDATED_LIVE: n=0]"
output:
- late_chase_attribution_v4.json.samples
- operational_report.json.summary.chase_entry_rate_pct
python_tools:
- tools/build_late_chase_attribution_v1.py
- tools/build_alpha_lead_threshold_optimizer_v3.py
gs_coverage: "gas_apex_alpha_watch.gs:calibrateAntiLateEntryV2_()"
validator: "tools/validate_no_late_chase_buy_v2.py"