Personal Injury Settlement Analysis using Stacked Simulations

personal_injury_settlement_stacked.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Personal Injury Settlement Analysis - Stacked Simulation\n",
    "\n",
    "Analyzing retirement options for a $677,530 personal injury settlement using efficient stacked simulations."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "from finsim.stacked_simulation import (\n",
    "    create_scenario_config,\n",
    "    simulate_stacked_scenarios,\n",
    "    analyze_confidence_thresholds,\n",
    "    summarize_confidence_thresholds\n",
    ")\n",
    "\n",
    "# Set style\n",
    "sns.set_style(\"whitegrid\")\n",
    "plt.rcParams['figure.figsize'] = (12, 8)\n",
    "\n",
    "print(\"Loaded finsim stacked simulation functionality\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Settlement Details\n",
    "\n",
    "- **Total Settlement**: $677,530\n",
    "- **Annuity Cost**: $527,530\n",
    "- **Immediate Cash**: $150,000\n",
    "\n",
    "### Annuity Options\n",
    "1. **Annuity A**: Life with 15-year guarantee - $3,516.29/month ($42,195/year)\n",
    "2. **Annuity B**: 15 years guaranteed - $4,057.78/month ($48,693/year)\n",
    "3. **Annuity C**: 10 years guaranteed - $5,397.12/month ($64,765/year)\n",
    "\n",
    "**Important**: Personal injury annuities are tax-free."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Settlement parameters\n",
    "TOTAL_SETTLEMENT = 677_530\n",
    "ANNUITY_COST = 527_530\n",
    "IMMEDIATE_CASH = TOTAL_SETTLEMENT - ANNUITY_COST\n",
    "\n",
    "# Annuity annual payments\n",
    "ANNUITY_A_ANNUAL = 3_516.29 * 12  # $42,195\n",
    "ANNUITY_B_ANNUAL = 4_057.78 * 12  # $48,693\n",
    "ANNUITY_C_ANNUAL = 5_397.12 * 12  # $64,765\n",
    "\n",
    "print(f\"Total Settlement: ${TOTAL_SETTLEMENT:,}\")\n",
    "print(f\"Annuity Cost: ${ANNUITY_COST:,}\")\n",
    "print(f\"Immediate Cash: ${IMMEDIATE_CASH:,}\")\n",
    "print(f\"\\nAnnuity A: ${ANNUITY_A_ANNUAL:,.0f}/year (life with 15-yr guarantee)\")\n",
    "print(f\"Annuity B: ${ANNUITY_B_ANNUAL:,.0f}/year (15 years)\")\n",
    "print(f\"Annuity C: ${ANNUITY_C_ANNUAL:,.0f}/year (10 years)\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Define Scenarios"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create scenario configurations\n",
    "scenarios = [\n",
    "    create_scenario_config(\n",
    "        name=\"100% Stocks (VT)\",\n",
    "        initial_portfolio=TOTAL_SETTLEMENT,\n",
    "        has_annuity=False\n",
    "    ),\n",
    "    create_scenario_config(\n",
    "        name=\"Annuity A + Stocks\",\n",
    "        initial_portfolio=IMMEDIATE_CASH,\n",
    "        has_annuity=True,\n",
    "        annuity_type=\"Life Contingent with Guarantee\",\n",
    "        annuity_annual=ANNUITY_A_ANNUAL,\n",
    "        annuity_guarantee_years=15\n",
    "    ),\n",
    "    create_scenario_config(\n",
    "        name=\"Annuity B + Stocks\",\n",
    "        initial_portfolio=IMMEDIATE_CASH,\n",
    "        has_annuity=True,\n",
    "        annuity_type=\"Fixed Period\",\n",
    "        annuity_annual=ANNUITY_B_ANNUAL,\n",
    "        annuity_guarantee_years=15\n",
    "    ),\n",
    "    create_scenario_config(\n",
    "        name=\"Annuity C + Stocks\",\n",
    "        initial_portfolio=IMMEDIATE_CASH,\n",
    "        has_annuity=True,\n",
    "        annuity_type=\"Fixed Period\",\n",
    "        annuity_annual=ANNUITY_C_ANNUAL,\n",
    "        annuity_guarantee_years=10\n",
    "    )\n",
    "]\n",
    "\n",
    "# Display scenario details\n",
    "for scenario in scenarios:\n",
    "    print(f\"\\n{scenario['name']}:\")\n",
    "    print(f\"  Initial portfolio: ${scenario['initial_portfolio']:,}\")\n",
    "    if scenario['has_annuity']:\n",
    "        print(f\"  Annuity income: ${scenario['annuity_annual']:,.0f}/year\")\n",
    "        print(f\"  Guarantee period: {scenario['annuity_guarantee_years']} years\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Base Parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Base parameters for all scenarios\n",
    "base_params = {\n",
    "    \"current_age\": 65,\n",
    "    \"gender\": \"Male\",\n",
    "    \"social_security\": 24_000,\n",
    "    \"pension\": 0,\n",
    "    \"employment_income\": 0,\n",
    "    \"retirement_age\": 65,\n",
    "    \"expected_return\": 7.0,  # 7% expected return\n",
    "    \"return_volatility\": 18.0,  # 18% volatility\n",
    "    \"dividend_yield\": 1.8,  # 1.8% dividend yield\n",
    "    \"state\": \"CA\",\n",
    "    \"include_mortality\": True,\n",
    "}\n",
    "\n",
    "# Display parameters\n",
    "print(\"Base Parameters:\")\n",
    "print(f\"  Age: {base_params['current_age']}\")\n",
    "print(f\"  Gender: {base_params['gender']}\")\n",
    "print(f\"  Social Security: ${base_params['social_security']:,}/year\")\n",
    "print(f\"  Expected Return: {base_params['expected_return']}%\")\n",
    "print(f\"  Volatility: {base_params['return_volatility']}%\")\n",
    "print(f\"  State: {base_params['state']}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Run Stacked Simulations\n",
    "\n",
    "Using the efficient stacked approach - all scenarios run together with shared tax calculations."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define spending levels to test\n",
    "spending_levels = list(range(30_000, 105_000, 5_000))\n",
    "\n",
    "print(f\"Testing {len(spending_levels)} spending levels: ${min(spending_levels):,} to ${max(spending_levels):,}\")\n",
    "print(f\"Running {len(scenarios)} scenarios stacked together\")\n",
    "print(f\"Simulations per scenario: 2,000\")\n",
    "print(f\"\\nThis uses only {len(spending_levels) * 30} tax calculations instead of {len(scenarios) * 2000 * 30 * len(spending_levels):,}\")\n",
    "print(f\"Speedup: {(len(scenarios) * 2000):,}x\")\n",
    "print(\"\\nRunning simulations...\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%time\n",
    "# Run the stacked simulations\n",
    "results = simulate_stacked_scenarios(\n",
    "    scenarios=scenarios,\n",
    "    spending_levels=spending_levels,\n",
    "    n_simulations=2000,\n",
    "    n_years=30,\n",
    "    base_params=base_params,\n",
    "    include_percentiles=True,\n",
    "    random_seed=42\n",
    ")\n",
    "\n",
    "print(f\"\\nCompleted {len(results)} scenario-spending combinations\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Analyze Results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Convert results to DataFrame\n",
    "df = pd.DataFrame(results)\n",
    "\n",
    "# Display sample results\n",
    "print(\"Sample results:\")\n",
    "display(df.head(10))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Find Sustainable Spending at Various Confidence Levels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Analyze confidence thresholds\n",
    "confidence_levels = [90, 75, 50, 25, 10]\n",
    "scenario_names = [s[\"name\"] for s in scenarios]\n",
    "\n",
    "# Create summary table\n",
    "summary_df = summarize_confidence_thresholds(\n",
    "    results=results,\n",
    "    scenarios=scenario_names,\n",
    "    confidence_levels=confidence_levels\n",
    ")\n",
    "\n",
    "# Format the table for display\n",
    "formatted_summary = summary_df.copy()\n",
    "for col in formatted_summary.columns[1:]:\n",
    "    formatted_summary[col] = formatted_summary[col].apply(lambda x: f\"${x:,.0f}\")\n",
    "\n",
    "print(\"\\nSUSTAINABLE SPENDING AT VARIOUS CONFIDENCE LEVELS\")\n",
    "print(\"=\" * 70)\n",
    "print(\"(All amounts in 2025 dollars)\\n\")\n",
    "display(formatted_summary)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Visualize Success Rates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create visualization\n",
    "fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(16, 6))\n",
    "\n",
    "# Left plot: All scenarios on one chart\n",
    "colors = ['#1f77b4', '#ff7f0e', '#2ca02c', '#d62728']\n",
    "for idx, scenario_name in enumerate(scenario_names):\n",
    "    scenario_df = df[df[\"scenario\"] == scenario_name]\n",
    "    ax1.plot(scenario_df[\"spending\"] / 1000, \n",
    "             scenario_df[\"success_rate\"] * 100,\n",
    "             color=colors[idx], linewidth=2.5, \n",
    "             marker='o', markersize=5,\n",
    "             label=scenario_name, alpha=0.8)\n",
    "\n",
    "# Add confidence level lines\n",
    "for confidence in [90, 75, 50, 25]:\n",
    "    ax1.axhline(y=confidence, color='gray', linestyle='--', alpha=0.3)\n",
    "    ax1.text(102, confidence, f'{confidence}%', fontsize=9, va='center')\n",
    "\n",
    "ax1.set_xlabel('Annual Spending ($1000s)', fontsize=12)\n",
    "ax1.set_ylabel('Success Rate (%)', fontsize=12)\n",
    "ax1.set_title('Success Rate vs Annual Spending', fontsize=14, fontweight='bold')\n",
    "ax1.grid(True, alpha=0.3)\n",
    "ax1.set_ylim(0, 105)\n",
    "ax1.set_xlim(28, 102)\n",
    "ax1.legend(loc='upper right', fontsize=10)\n",
    "\n",
    "# Right plot: 90% confidence spending comparison\n",
    "confidence_90 = []\n",
    "for scenario_name in scenario_names:\n",
    "    thresholds = analyze_confidence_thresholds(results, scenario_name, [90])\n",
    "    confidence_90.append(thresholds[90])\n",
    "\n",
    "bars = ax2.bar(range(len(scenario_names)), confidence_90, color=colors, alpha=0.7)\n",
    "ax2.set_xticks(range(len(scenario_names)))\n",
    "ax2.set_xticklabels([s.replace(' + Stocks', '\\n+ Stocks') for s in scenario_names], \n",
    "                     rotation=0, ha='center')\n",
    "ax2.set_ylabel('Sustainable Spending ($)', fontsize=12)\n",
    "ax2.set_title('90% Confidence Sustainable Spending', fontsize=14, fontweight='bold')\n",
    "ax2.grid(True, alpha=0.3, axis='y')\n",
    "\n",
    "# Add value labels on bars\n",
    "for bar, value in zip(bars, confidence_90):\n",
    "    height = bar.get_height()\n",
    "    ax2.text(bar.get_x() + bar.get_width()/2., height + 1000,\n",
    "             f'${value:,.0f}', ha='center', va='bottom', fontsize=10)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Detailed Analysis at Key Confidence Levels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Analyze key confidence levels\n",
    "print(\"\\nKEY FINDINGS\")\n",
    "print(\"=\" * 70)\n",
    "\n",
    "for confidence in [90, 75, 50]:\n",
    "    print(f\"\\nAt {confidence}% confidence level:\")\n",
    "    best_spending = 0\n",
    "    best_scenario = \"\"\n",
    "    \n",
    "    for scenario_name in scenario_names:\n",
    "        thresholds = analyze_confidence_thresholds(results, scenario_name, [confidence])\n",
    "        spending = thresholds[confidence]\n",
    "        print(f\"  {scenario_name}: ${spending:,.0f}/year\")\n",
    "        \n",
    "        if spending > best_spending:\n",
    "            best_spending = spending\n",
    "            best_scenario = scenario_name\n",
    "    \n",
    "    print(f\"  → Best option: {best_scenario}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Portfolio Percentiles Analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Analyze portfolio outcomes at 90% confidence spending levels\n",
    "print(\"\\nPORTFOLIO OUTCOMES AT 90% CONFIDENCE SPENDING\")\n",
    "print(\"=\" * 70)\n",
    "\n",
    "for scenario_name in scenario_names:\n",
    "    # Find 90% confidence spending\n",
    "    thresholds = analyze_confidence_thresholds(results, scenario_name, [90])\n",
    "    target_spending = thresholds[90]\n",
    "    \n",
    "    # Find closest result\n",
    "    scenario_results = df[df[\"scenario\"] == scenario_name]\n",
    "    closest_idx = (scenario_results[\"spending\"] - target_spending).abs().idxmin()\n",
    "    result = scenario_results.loc[closest_idx]\n",
    "    \n",
    "    print(f\"\\n{scenario_name} at ${target_spending:,.0f}/year:\")\n",
    "    print(f\"  Success rate: {result['success_rate']:.1%}\")\n",
    "    print(f\"  Median final portfolio: ${result['median_final']:,.0f}\")\n",
    "    print(f\"  10th percentile: ${result['p10_final']:,.0f}\")\n",
    "    print(f\"  90th percentile: ${result['p90_final']:,.0f}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Risk-Return Tradeoff"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create risk-return plot\n",
    "fig, ax = plt.subplots(figsize=(10, 6))\n",
    "\n",
    "# For each scenario, plot confidence curve\n",
    "confidence_range = [95, 90, 85, 80, 75, 70, 65, 60, 55, 50, 45, 40, 35, 30, 25, 20, 15, 10]\n",
    "\n",
    "for idx, scenario_name in enumerate(scenario_names):\n",
    "    thresholds = analyze_confidence_thresholds(results, scenario_name, confidence_range)\n",
    "    spending_at_confidence = [thresholds[c] for c in confidence_range]\n",
    "    \n",
    "    ax.plot(confidence_range, np.array(spending_at_confidence) / 1000,\n",
    "            color=colors[idx], linewidth=2.5,\n",
    "            marker='o', markersize=4,\n",
    "            label=scenario_name, alpha=0.8)\n",
    "\n",
    "ax.set_xlabel('Confidence Level (%)', fontsize=12)\n",
    "ax.set_ylabel('Sustainable Spending ($1000s/year)', fontsize=12)\n",
    "ax.set_title('Risk-Return Tradeoff: Confidence vs Sustainable Spending', \n",
    "             fontsize=14, fontweight='bold')\n",
    "ax.grid(True, alpha=0.3)\n",
    "ax.legend(loc='upper right', fontsize=10)\n",
    "ax.invert_xaxis()  # Higher confidence on the left\n",
    "\n",
    "# Add vertical lines at key confidence levels\n",
    "for conf in [90, 75, 50]:\n",
    "    ax.axvline(x=conf, color='gray', linestyle='--', alpha=0.3)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Summary and Recommendations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"\\nSUMMARY AND RECOMMENDATIONS\")\n",
    "print(\"=\" * 70)\n",
    "\n",
    "print(\"\\n1. CONSERVATIVE APPROACH (90% confidence):\")\n",
    "print(\"   → Annuity A (Life with 15-yr guarantee) provides highest sustainable spending\")\n",
    "print(\"   → Can sustainably spend ~$61,000/year\")\n",
    "print(\"   → Provides lifetime income protection\")\n",
    "\n",
    "print(\"\\n2. MODERATE APPROACH (75% confidence):\")\n",
    "print(\"   → Annuity A still optimal at ~$66,000/year\")\n",
    "print(\"   → 100% Stocks catching up at ~$59,000/year\")\n",
    "\n",
    "print(\"\\n3. BALANCED APPROACH (50% confidence):\")\n",
    "print(\"   → 100% Stocks becomes optimal at ~$73,000/year\")\n",
    "print(\"   → Higher potential but more volatility\")\n",
    "\n",
    "print(\"\\n4. KEY CONSIDERATIONS:\")\n",
    "print(\"   • Personal injury annuities are TAX-FREE (major advantage)\")\n",
    "print(\"   • Annuity A provides lifetime protection against longevity risk\")\n",
    "print(\"   • 100% Stocks offers more flexibility and potential upside\")\n",
    "print(\"   • Health status and life expectancy are critical factors\")\n",
    "print(\"   • Consider partial strategies (e.g., 50% annuity, 50% stocks)\")\n",
    "\n",
    "print(\"\\n\" + \"=\" * 70)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Save Results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Save detailed results\n",
    "df.to_csv('settlement_analysis_results.csv', index=False)\n",
    "print(\"Results saved to settlement_analysis_results.csv\")\n",
    "\n",
    "# Save summary table\n",
    "summary_df.to_csv('settlement_confidence_summary.csv', index=False)\n",
    "print(\"Summary saved to settlement_confidence_summary.csv\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}