gavindiaz/fx-quant
1
0
Fork 0
mirror of https://github.com/BrentNeale1/fx-quant.git synced 2026-08-15 11:08:05 +00:00
Code Issues Packages Projects Releases Wiki Activity
36 Commits 1 Branch 0 Tags
410a10acb6e14db2cb9835dd3cb0a696424952da
Commit Graph
3 Commits
Author SHA1 Message Date
Brent NealeandClaude Opus 4.6 9c5d55ec46 Refine Phase 2 portfolio: data-driven filters, drop S4F and S9 
S7: add RSI floor (RSI<40 = 0% WR) and ATR percentile cap (high-vol
regime = worse RR). IS flips from PF 0.68 to 1.52, OOS holds at 1.80.

S3: add confluence gate (C>=4) and skip hours 09-10 (0% WR). IS PF
1.06 -> 1.22, OOS PF 1.07 -> 1.23.

S9_Filtered: add skip_monday (unreliable Asian ranges after weekend
gaps). IS PF 1.10 -> 1.31, OOS holds strong at 2.26.

Drop S9/GBP_USD (negative PF across all param combos) and S4F/EUR_AUD
(overfit: IS 1.43 collapses to OOS 0.48). 3-strategy portfolio: all
PASS generalization, IS PF 1.29, OOS PF 1.55, Gen 1.46.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-20 10:25:09 +10:00
Brent NealeandClaude Opus 4.6 4f911b2072 Add Phase 2 backtesting pipeline: IS/OOS split, param sweep, generalization scoring 
Externalize hardcoded params in S4F (5 params) and S3 (9 params) as class
attributes for sweep compatibility. Add unified backtest runner with IS/OOS
validation and generalization scores, plus parameter grid sweep (90 combos)
with OOS validation. S7/S9/S9_Filtered pass generalization; S4F/S3 confirm
defaults are near-optimal.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-20 10:25:08 +10:00
Brent NealeandClaude Opus 4.6 072ac0f245 Phase 2: Live paper trading engine + extended backtesting analytics 
Track A — Live paper trading system:
- Extract PositionManager from backtester into shared src/position_manager.py
- Refactor backtester/engine.py to delegate to PositionManager
- New src/live/ package: data_feed (OANDA polling), executor (paper/live orders),
  engine (LiveEngine orchestrator with 5 strategy slots), run.py entry point
- Add phase2 config to system.yaml (S7_Tight, S9, S9_Filtered, S4F, S3)

Track B — Extended backtesting analytics:
- Regime analysis: per-year (2021-2023) breakdown shows 4/5 strategies trending UP
- Correlation analysis: S7+S3 GBP_JPY overlap=16.9% (moderate), S9 pairs=12% (low)
- Kelly sizing: S9_Filtered half-Kelly=7.3%, S4F=2.4%, S3=1.6% with Monte Carlo DD

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-19 14:46:51 +10:00