Version: 1.0.0 Status: Production Ready Date: January 28, 2026
NIJA MMIN transforms the trading bot from a single-market system into a global autonomous trading intelligence that operates across multiple asset classes simultaneously.
MMIN is an advanced multi-market intelligence system that enables:
┌─────────────────────────────────────────────────────────────────┐
│ MMIN ENGINE │
│ (Orchestration Layer) │
└─────────────────────────────────────────────────────────────────┘
│ │ │ │
▼ ▼ ▼ ▼
┌──────────────┐ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐
│ Multi-Market │ │ Correlation │ │ Macro Regime │ │ Transfer │
│ Data │ │ Analyzer │ │ Forecaster │ │ Learning │
│ Collector │ │ │ │ │ │ Engine │
└──────────────┘ └──────────────┘ └──────────────┘ └──────────────┘
│ │ │ │
└──────────────┴──────────────┴──────────────┘
│
▼
┌──────────────────────┐
│ Global Capital │
│ Router │
└──────────────────────┘
│
▼
┌───────────────────────────────────────────┐
│ CRYPTO │ FOREX │ EQUITIES │ BONDS │
│ (Coinbase, Kraken, Binance, Alpaca, etc) │
└───────────────────────────────────────────┘
Location: bot/mmin/data_collector.py
Collects and normalizes data from multiple asset classes:
Features:
Location: bot/mmin/correlation_analyzer.py
Analyzes correlations between different asset classes:
Features:
Use Cases:
Location: bot/mmin/macro_regime_forecaster.py
Forecasts global macro economic regimes:
Regimes Detected:
Trading Implications: Each regime comes with specific trading recommendations:
Location: bot/mmin/transfer_learning.py
Enables pattern transfer across different asset classes:
Features:
Example:
Crypto breakout pattern (90% success)
→ Transfer to equity market
→ Applied with 75% adjusted confidence
Location: bot/mmin/global_capital_router.py
Intelligently routes capital across markets:
Allocation Strategies:
Allocation Factors:
Location: bot/mmin/mmin_engine.py
Main intelligence engine that coordinates all components:
Analysis Loop:
MMIN is already integrated into NIJA. No additional dependencies required.
from bot.mmin import MMINEngine
# Initialize MMIN
engine = MMINEngine()
# Run market analysis
analysis = engine.analyze_markets(
timeframe='1h',
limit=500
)
# Results
print(f"Macro Regime: {analysis['macro_regime']['regime'].value}")
print(f"Signals: {len(analysis['signals'])}")
print(f"Capital Allocation: {analysis['capital_allocation']}")
# Get status
status = engine.get_status()
print(f"Intelligence Level: {status['intelligence_level']}")
Run the comprehensive test suite:
python test_mmin.py
This tests all MMIN components and validates the full system.
MMIN configuration is in bot/mmin/mmin_config.py
# Enable/disable MMIN
MMIN_ENGINE_CONFIG = {
'enabled': True,
'mode': 'adaptive', # 'conservative', 'balanced', 'adaptive', 'aggressive'
'intelligence_level': 'god_mode', # 'basic', 'advanced', 'god_mode'
'cross_market_signals_required': 2, # Require N market confirmations
}
# Markets to monitor
MARKET_CATEGORIES = {
'crypto': ['BTC-USD', 'ETH-USD', 'SOL-USD', ...],
'equities': ['SPY', 'QQQ', 'AAPL', ...],
'forex': ['EUR/USD', 'GBP/USD', ...],
'commodities': ['GLD', 'SLV', ...],
'bonds': ['TLT', 'IEF', ...],
}
# Capital allocation strategy
CAPITAL_ALLOCATION_CONFIG = {
'allocation_strategy': 'adaptive', # Recommended
'min_allocation_per_market': 0.05, # 5% minimum
'max_allocation_per_market': 0.50, # 50% maximum
}
MMIN requires signals to be confirmed across multiple markets:
Example:
- BTC-USD shows bullish setup (crypto)
- Correlation analyzer finds BTC ↔ NASDAQ (0.85 correlation)
- NASDAQ also shows bullish momentum
- Signal confidence increased due to cross-market confirmation
Adapt strategy based on global economic regime:
Scenario: MMIN detects "Risk Off" regime
- Bonds rising, equities falling, crypto falling
- Action: Reduce crypto/equity exposure
- Action: Increase bond/USD allocation
- Action: Tighten stop losses
- Action: Focus on defensive strategies
Learn from one market, apply to another:
Pattern learned from crypto:
- RSI oversold + volume surge + breakout = 85% win rate
Pattern transferred to equities:
- Same setup recognized in SPY
- Adjusted confidence: 72% (accounting for transfer risk)
- Trade executed with smaller position size
Dynamic allocation based on opportunity + regime:
Current State:
- Macro regime: Growth
- Crypto: 8 opportunities, Sharpe 2.1
- Equities: 12 opportunities, Sharpe 1.8
- Forex: 3 opportunities, Sharpe 1.2
Allocation:
- Crypto: 45% (high performance + growth regime)
- Equities: 40% (many opportunities + growth regime)
- Forex: 15% (fewer opportunities)
MMIN tracks comprehensive performance metrics:
status = engine.get_status()
{
'performance': {
'total_signals': 247,
'successful_signals': 156,
'cross_market_confirmations': 189,
'regime_changes': 12,
},
'data_quality': {
'cached_symbols': 45,
'missing_data_count': 3,
'total_updates': 1024,
},
'learning_stats': {
'total_patterns': 89,
'transfer_routes': 6,
'transfer_performance': {...},
}
}
.env (never committed)class MMINEngine:
def __init__(self, broker_manager=None, config=None)
def analyze_markets(self, timeframe='1h', limit=500) -> Dict
def get_status() -> Dict
def enable()
def disable()
class MultiMarketDataCollector:
def collect_market_data(market_type, symbols, timeframe, limit) -> Dict
def collect_all_markets(timeframe, limit) -> Dict
def get_synchronized_data(symbols_map, limit) -> pd.DataFrame
def get_quality_metrics() -> Dict
class CrossMarketCorrelationAnalyzer:
def calculate_correlations(data) -> Dict
def find_correlated_pairs(corr_matrix, threshold) -> List
def detect_lead_lag(data, sym1, sym2, max_lag) -> Dict
def get_diversification_score(portfolio, corr_matrix) -> float
class MacroRegimeForecaster:
def forecast_regime(market_data) -> Dict
def get_regime_transitions(lookback) -> List
class TransferLearningEngine:
def extract_features(df, market_type) -> np.ndarray
def learn_pattern(data, market_type, pattern_type, outcome) -> Pattern
def find_similar_patterns(data, market_type, pattern_types, min_confidence) -> List
def transfer_pattern(pattern, target_market) -> Dict
class GlobalCapitalRouter:
def calculate_allocation(market_metrics, correlations, macro_regime, total_capital) -> Dict
def score_opportunity(opportunity) -> float
def suggest_rebalance(current, target, threshold) -> Dict
Solution: Check broker connections and API credentials
Solution: Adjust min_score_threshold in configuration
Solution: Increase cross_market_signals_required for stricter filtering
For questions or issues:
test_mmin.py)mmin_config.pyNIJA MMIN represents the next evolution of autonomous trading:
✅ Cross-Market Learning - Patterns transfer across asset classes ✅ Transfer Learning - Knowledge compounds across markets ✅ Macro Forecasting - Global regime awareness ✅ Global Capital Routing - Intelligent allocation ✅ Correlation Intelligence - Multi-market confirmation
NIJA is now a GLOBAL AUTONOMOUS TRADING INTELLIGENCE
“The future of trading is not single-market bots. It’s global intelligence that learns, adapts, and operates across all markets simultaneously.”
Version: 1.0.0 Author: NIJA Trading Systems Date: January 28, 2026