root/trading_bot_v4
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update copilot-instructions: Mark Q≥95 strategy as DEPLOYED with backtest validation

Browse Source
This commit is contained in:
mindesbunister
2025-12-18 09:40:25 +01:00
parent 634738bfb4
commit f1c4548dca
1 changed files with 12 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
.github/copilot-instructions.md vendored
View File

@@ -1167,6 +1167,11 @@ Frequency penalties (overtrading / flip-flop / alternating) now ignore 1-minute
## 🎯 Validated Profitable Strategy (Dec 18, 2025 - QUALITY >= 95 OPTIMIZATION) ## 🎯 Validated Profitable Strategy (Dec 18, 2025 - QUALITY >= 95 OPTIMIZATION)
**⚠️ STATUS: DEPLOYED TO PRODUCTION (Dec 18, 2025 00:45 UTC)**
- Git Commit: `634738b`
- Container: Restarted and running with new thresholds
- Config Verified: `MIN_SIGNAL_QUALITY_SCORE_LONG=95`, `MIN_SIGNAL_QUALITY_SCORE_SHORT=95`
**Context:** Despite achieving 66.7% win rate with HTF filter + 5-candle time exit, system was still losing money (-$252.12 on 24 trades). Root cause analysis revealed asymmetric risk/reward: average win $24.34 vs average loss -$91.65 (0.27 win/loss ratio = need 4 wins to recover 1 loss). Winners were 3.8× smaller than losers. **Context:** Despite achieving 66.7% win rate with HTF filter + 5-candle time exit, system was still losing money (-$252.12 on 24 trades). Root cause analysis revealed asymmetric risk/reward: average win $24.34 vs average loss -$91.65 (0.27 win/loss ratio = need 4 wins to recover 1 loss). Winners were 3.8× smaller than losers.
**Optimization Methodology:** **Optimization Methodology:**
@@ -1174,6 +1179,13 @@ Frequency penalties (overtrading / flip-flop / alternating) now ignore 1-minute
- **Approach:** SQL-based backtesting testing quality thresholds (50-100), HTF alignment filters, time-based exits, instant reversal blocking, ADX thresholds, time-of-day patterns - **Approach:** SQL-based backtesting testing quality thresholds (50-100), HTF alignment filters, time-based exits, instant reversal blocking, ADX thresholds, time-of-day patterns
- **Key Insight:** Dramatically increasing entry quality filters out catastrophic losers while preserving profitable trades - **Key Insight:** Dramatically increasing entry quality filters out catastrophic losers while preserving profitable trades
**BACKTEST VALIDATION (28 days actual trading data):**
- **Original Strategy:** 32 trades, 43.8% WR, -$516.82 loss (-529.80% return, -18.921% daily)
- **New Q≥95 Strategy:** 13 trades, 69.2% WR, +$449.99 profit (+461.29% return, +16.475% daily)
- **Improvement:** +$966.81 swing (+991%), +25.5% hit rate improvement
- **Average per trade:** $37.50 profit (was -$16.15 loss)
- **Filters removed:** 18 toxic Q<95 trades, 1 instant reversal
**Validated Strategy Components:** **Validated Strategy Components:**
1. **Quality Score Threshold: Q >= 95** (vs current LONG>=90, SHORT>=80) 1. **Quality Score Threshold: Q >= 95** (vs current LONG>=90, SHORT>=80)