harry/ForexBot2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
63 Commits 3 Branches 0 Tags
0593e455bc7542db972cb8de26a88c45c520a3c8
Commit Graph

5 Commits

Author SHA1 Message Date
harwinder b7ec5341cf Tune 5M signals, fix XAU regression, add signal dedup cooldown 
EUR/USD 5M: raise min_entry_score 28→35, block hours 4/19/21
  → 83.4% WR, 145 trades, +9.68R, PF 1.42 (120-day)

XAU/USD 5M: fix B-grade exclusion regression in setup_grades,
  add breakeven trail (trigger 0.15R, buffer 0.05R)
  → 84.9% WR, 4810 trades, +164.54R, PF 1.23 (730-day)

EUR/USD M15: tighten defaults (SL 1.5x ATR, TP 1.0x, min_rr 0.5,
  block ranging+transitioning, BE trigger 0.2R)

Backtest: multiprocess fork parallelism, vectorized pre-filter,
  CUDA preload fix, per-pair BE trigger routing

Telegram bot: add signal deduplication — suppress repeated
  same-direction messages within 5-bar cooldown per pair+TF.
  Resend on direction flip, quality upgrade, or cooldown expiry.
  Manual scans always ungated.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-05-19 20:19:11 -04:00
harwinder 9e5410d617 GPU parallel EMA + fix backtest/live parity bugs 
- Add CUDA parallel prefix scan (Blelloch) for EMA: 16 EMAs in 3 batched kernel launches
- Eliminate CPU↔GPU array bouncing; keep arrays on-device until final cache build
- Auto-detect pip-installed CUDA libs for CuPy kernel compilation
- Add --gpu-only and --quick (30-day) CLI flags
- Fix missing _adx_slope in GPUTechnicalEngine (was suppressing transitioning regime)
- Fix ROC early-entry: guard was pos < n+1, should be pos < n+4 to match live engine
- Fix weekend filter: use proper forex weekend (Fri 22:00–Sun 22:00 UTC) instead of weekday >= 5

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-05-19 13:26:12 -04:00
harwinder 08d7c9ade1 Optimize EUR/USD to 78.7% WR on 2-year M15 backtest 
Three-layer optimization:

1. Entry filters (signal_aggregator.py section 6e):
   - Block ranging regime
   - Only A+/A/B quality grades
   - min_entry_score=38, min_entry_confidence=60
   - Block RSI > 70 for BUY, RSI < 30 for SELL

2. Trade setup (config.py EurUsdStrategyConfig):
   - RR=0.50 with uniform quality scale
   - SL floor 1.2 ATR, TP 1.0 ATR

3. Breakeven trail (backtest/gpu_backtest.py):
   - When MFE reaches 0.3R, move SL to entry + 0.05R buffer
   - Converts 4 of 14 losses to +0.05R small wins
   - Bar-by-bar simulation integrated into simulate_trades()

Results (EUR/USD M15, 2024-05-18 to 2026-05-18):
  47 trades | 78.7% WR | +1.81R | PF 1.18 | MaxDD 3.35R
XAU/USD unchanged: 77.8% WR on 30-day, 68.7% WR on 2-year.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-05-18 14:00:59 -04:00
harwinder 74b723ba06 Tune EUR/USD trade setup: quality-scaled TP and tighter SL 
EUR/USD A-grade signals had inverted quality curve (-1.65R) because all
trades got RR≈0.50 and mature_move logic penalized high-score entries.

Fix: add per-pair trade setup params (sl_atr_floor=1.2, min_rr=1.0,
mature_move_threshold=35) and apply quality_scale to both tp_mult and
min_rr so A-grade gets wider TP targets. Also wire EUR config into
backtest via PAIR_PRODUCERS registry.

Result: A-grade now +1.24R (was -1.65R), total EUR/USD +10.06R (was +4.20R).
XAU/USD unchanged at +13.01R.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-05-18 12:56:34 -04:00
harwinder 0e6f5d74a7 Add backtest scripts to version control 
Track gpu_backtest.py, diagnose_filters.py, and instructions.
Data files (CSVs, parquet cache) remain gitignored.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-05-15 19:49:30 -04:00