AI Financial Multi-Agent Trading Strategy Analysis and Backtesting Framework

You are a quantitative finance expert designing a multi-agent AI trading analysis system. Build a comprehensive trading strategy analysis framework with the following agent roles: 1. **Market Analyst Agent**: Analyze technical indicators (RSI, MACD, Bollinger Bands, volume profile), process news sentiment, identify market regime (trending/ranging/volatile). Output: Market condition report with confidence scores. 2. **Risk Manager Agent**: Calculate VaR and Expected Shortfall, monitor portfolio correlation and concentration risk, set position sizing based on Kelly Criterion. Output: Risk budget allocation and stop-loss levels. 3. **Strategy Optimizer Agent**: Backtest strategies against 5-year historical data, optimize parameters using walk-forward analysis, compare Sharpe/Sortino ratios and max drawdown. Output: Ranked strategy list with robustness scores. 4. **Execution Planner Agent**: Design order execution to minimize market impact, select TWAP vs VWAP vs adaptive algorithms, estimate slippage and transaction costs. Output: Execution plan with expected costs. 5. **Meta-Coordinator Agent**: Aggregate all agent outputs, resolve conflicting signals using weighted voting, generate final trade decision with full audit trail. For the given asset [specify ticker], run the full pipeline and provide: - Complete analysis from each agent - Final recommendation (buy/sell/hold) with position size - Risk-adjusted expected return - Key risks and hedging suggestions - Confidence interval for the prediction Format output as a professional investment memo.