Repository Public
1{"job": {"id": "6f1deb47-745a-4f30-9d5e-48e72185853c", "tool": "portfolio_optimization", "params": {"symbols": ["AAPL", "MSFT", "NVDA"], "risk_free_rate": 0.02, "min_weight": 0, "max_weight": 1, "data_period": 504, "generate_frontier": true, "frontier_points": 10}, "status": "done", "startedAt": 1795041199312, "finishedAt": 1795041202365, "error": null, "code": "import numpy as np\nimport pandas as pd\nfrom scipy.optimize import minimize\nfrom fmpClient import get_historical_prices\n\n# Portfolio assets\nsymbols = [\"AAPL\",\"MSFT\",\"NVDA\"]\nrisk_free_rate = 0.02\n\n# Fetch historical data for all symbols\nprices_dict = {}\nfor symbol in symbols:\n print(f\"Fetching data for {symbol}...\")\n hist_data = get_historical_prices(symbol)\n prices = [h['close'] for h in reversed(hist_data['historical'])]\n dates = [h['date'] for h in reversed(hist_data['historical'])]\n prices_dict[symbol] = pd.Series(prices, index=pd.to_datetime(dates))\n\n# Create DataFrame and calculate returns\nprices_df = pd.DataFrame(prices_dict).dropna()\nreturns_df = prices_df.pct_change().dropna()\n\n# Calculate mean returns (annualized) and covariance matrix\nmean_returns = returns_df.mean() * 252\ncov_matrix = returns_df.cov() * 252\n\nprint(\"\\nExpected Annual Returns:\")\nfor symbol, ret in mean_returns.items():\n print(f\" {symbol}: {ret*100:.2f}%\")\n\n# Portfolio optimization function\ndef portfolio_stats(weights):\n portfolio_return = np.sum(weights * mean_returns)\n portfolio_std = np.sqrt(np.dot(weights.T, np.dot(cov_matrix, weights)))\n return portfolio_return, portfolio_std\n\ndef negative_sharpe(weights):\n ret, std = portfolio_stats(weights)\n return -(ret - risk_free_rate) / std\n\n# Constraints and bounds\nconstraints = {'type': 'eq', 'fun': lambda x: np.sum(x) - 1}\nbounds = tuple((0, 1) for _ in range(len(symbols)))\ninit_guess = np.array([1/len(symbols)] * len(symbols))\n\n# Optimize for maximum Sharpe ratio\nresult = minimize(negative_sharpe, init_guess, method='SLSQP',\n bounds=bounds, constraints=constraints)\n\noptimal_weights = result.x\nopt_return, opt_std = portfolio_stats(optimal_weights)\nsharpe = (opt_return - risk_free_rate) / opt_std\n\nprint(\"\\nOptimal Portfolio (Maximum Sharpe Ratio):\")\nfor i, symbol in enumerate(symbols):\n print(f\" {symbol}: {optimal_weights[i]*100:.2f}%\")\nprint(f\"\\nExpected Return: {opt_return*100:.2f}%\")\nprint(f\"Volatility: {opt_std*100:.2f}%\")\nprint(f\"Sharpe Ratio: {sharpe:.4f}\")", "result": {"success": true, "symbols": ["AAPL", "MSFT", "NVDA"], "parameters": {"num_assets": 3, "risk_free_rate": 0.02, "min_weight": 0, "max_weight": 1, "data_points": 504, "data_period_days": 504}, "asset_statistics": {"AAPL": {"expected_return": 25.93, "volatility": 28.93, "sharpe_ratio": 0.8272}, "MSFT": {"expected_return": 13.03, "volatility": 29.52, "sharpe_ratio": 0.3737}, "NVDA": {"expected_return": 11.42, "volatility": 44.72, "sharpe_ratio": 0.2107}}, "correlation_matrix": {"AAPL": {"AAPL": 1, "MSFT": 0.3145, "NVDA": 0.2862}, "MSFT": {"AAPL": 0.3145, "MSFT": 1, "NVDA": 0.4023}, "NVDA": {"AAPL": 0.2862, "MSFT": 0.4023, "NVDA": 1}}, "optimal_portfolios": {"max_sharpe_ratio": {"description": "Portfolio with maximum Sharpe ratio", "allocation": {"AAPL": 86.44, "MSFT": 13.56, "NVDA": 0}, "expected_return": 24.18, "volatility": 26.54, "sharpe_ratio": 0.8358, "optimization_success": true}, "min_volatility": {"description": "Portfolio with minimum volatility", "allocation": {"AAPL": 48.92, "MSFT": 44.23, "NVDA": 6.84}, "expected_return": 19.23, "volatility": 23.52, "sharpe_ratio": 0.7326, "optimization_success": true}, "equal_weight": {"description": "Equal weight portfolio (benchmark)", "allocation": {"AAPL": 33.33, "MSFT": 33.33, "NVDA": 33.33}, "expected_return": 16.8, "volatility": 25.92, "sharpe_ratio": 0.5708}}, "efficient_frontier": {"returns": [0.11422803894358093, 0.13034943661874612, 0.1464708343341693, 0.16259223202307066, 0.17871362972092125, 0.19483502740690484, 0.210956425141376, 0.22707782279154654, 0.24319922158947346, 0.25932061818081875], "volatilities": [0.4471675686197531, 0.2796159932785401, 0.26044548929779654, 0.24612725351192669, 0.23754033612234177, 0.23531300131255095, 0.23962270644740477, 0.25019922698820607, 0.26705643305987364, 0.2893021322476049], "sharpe_ratios": [0.2107219878096913, 0.39464636956163407, 0.4855942588030811, 0.5793435305861446, 0.6681544377338006, 0.7429892374483926, 0.7969045503761113, 0.8276517289212401, 0.8357754914648791, 0.8272342008734022]}, "interpretation": {"diversification_benefit": 9.25, "notes": ["Max Sharpe portfolio optimizes risk-adjusted returns", "Min Volatility portfolio minimizes risk", "Equal Weight portfolio is the naive 1/N allocation", "Diversification benefit shows risk reduction vs. equal weighting", "Correlations range from 0.29 to 1.0"]}}}}