v0.2: Remove V5/V10 labels, consolidate to Version 0.2 with adaptive learning

This commit is contained in:
Marc Blatter 2026-07-07 22:00:28 +02:00
parent d36e07d999
commit 888e0f32dd
1 changed files with 118 additions and 13 deletions

131
README.md
View File

@ -1,18 +1,123 @@
# BrainDock Trading Bot V5
# Trading Bot V0.2 — Adaptive Strategy Learning
Multi-crypto ML-powered trading bot with auto-exit strategies.
**Production-ready Crypto Trading Bot with Live P&L Dashboard**
## Features
### ✅ Core Trading
- **Adaptive Signal Generation**: Win-rate based strategy adjustment (5 levels)
- **Risk Management**: Stop Loss (-1.8%), Take Profit (+2.8%), Daily Loss Limit (-5%)
- **Smart Position Sizing**: Dynamic investment (50-55%) based on signal confidence
- **Trailing Stop**: +1.5% entry, 0.6% trail distance
- **Cooldown Protection**: 30min pause after 3 consecutive losses
### ✅ Adaptive Learning (Option 2)
- **Hourly Strategy Evaluation**: Automatically adjusts based on win rate
- **5 Strategy Levels**:
- 🚨 Emergency (<45% WR): Strict signals, minimal trades
- ⚠️ Conservative (45-50%): Reduced risk
- ✅ Standard (50-60%): Default settings
- 🟢 Aggressive (60-70%): Increased signal frequency
- 🔥 Full Throttle (>70%): Maximum trading
### ✅ Monitoring & Reporting
- **Live P&L Dashboard**: Real-time portfolio value, profit/loss, holdings
- **Performance Reports**: 3-hour summaries via Telegram
- **Telegram Alerts**: Strategy changes, trade notifications
## Architecture
- - ML bot engine with signal detection
- - Binance API wrapper & order execution
- - Real-time monitoring dashboard
- - ML model definitions
- - Telegram alerts
## Live Trading
- Capital: $135+ USDT
- Symbols: BTC, ETH, SOL, BNB, XRP
- Exit Strategy: +1% TP, -3% SL, trail stops, auto-SWAP <$15
### Files
- `src/main_ml.py`: Core trading bot (512 lines)
- `src/web_dashboard.py`: FastAPI dashboard (650+ lines)
- `README.md`: This file
## Status
✅ Production live 2026-07-04
### Endpoints
- **Bot**: Runs async trading cycle (5s loop)
- **Dashboard**: http://localhost:7000 (HTML) + `/api/state` (JSON)
- **Telegram**: Real-time alerts
## Configuration
### Strategy Parameters (Adaptive)
```python
SIGNAL_THRESHOLD: 5-10%
INVESTMENT_PERCENT: 50-55%
TAKE_PROFIT_PERCENT: 1.5-3.5%
STOP_LOSS_PERCENT: 1.0-2.2%
MAX_TRADES_PER_DAY: 5-25
MAX_OPEN_POSITIONS: 1-2
```
### Risk Controls
- Daily Loss Limit: -5%
- Max 3 consecutive losses → 30min cooldown
- Min notional: $5.00 per order
- Slippage buffer: PRICE_FILTER rounding
## Usage
### Start Bot
```bash
cd src
python3 main_ml.py
```
### Start Dashboard
```bash
cd src
uvicorn web_dashboard:app --host 0.0.0.0 --port 7000
```
### View Dashboard
```
http://bot.bizmark.cloud
```
## Performance
### Current State (2026-07-07)
- **Portfolio**: $135.99 USD
- **P&L**: -$1.83 (-1.3%)
- **Open Positions**: 1 (XRP 6.7 @ $1.15)
- **Status**: 🟢 LIVE
### Historical
- Total Trades: 10+
- Win Rate: 45-55% (adaptive mode active)
- Largest Win: +2.8% (TP hit)
- Largest Loss: -1.8% (SL hit)
## Version History
### V0.2 (Current) — 2026-07-07
- ✅ Adaptive strategy learning (Option 2)
- ✅ Live P&L dashboard integration
- ✅ 10s refresh rate (optimized)
- ✅ Hourly strategy evaluation
- ✅ Code cleanup (removed V5/V10 labels)
### V0.1 (Previous)
- Static strategy (7.5% signal, 50% investment)
- Basic P&L cart add reporting
## Troubleshooting
### Dashboard shows stale P&L?
- Check `/api/state` endpoint returns new data
- Verify bot is running (`systemctl status trading-bot`)
- Refresh page (clears 10s cache)
### Bot not trading?
- Check daily loss limit (-5% limit may be hit)
- Verify Binance API key has trading permission
- Check MIN_NOTIONAL ($5.00 minimum per order)
### Strategy not adapting?
- Need minimum 5 trades to trigger adaptation
- Strategy updates every hour (check logs)
- Win rate must be >5% points away to trigger new mode
## License
All trades at your own risk. Crypto is volatile.