{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "8bea070e",
   "metadata": {},
   "source": [
    "<div style=\"background-color:#000;\"><img src=\"pqn.png\"></img></div>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "59b6b6e4",
   "metadata": {},
   "source": [
    "This code performs a multifactor analysis on monthly stock returns, applying the Fama-French three-factor model for financial analysis. It fetches historical factor data, calculates active returns of selected stocks, and estimates their sensitivities to the Fama-French factors. The code also performs rolling regression to analyze the stability of factor exposures over time. Lastly, it calculates and prints the marginal contributions to risk from each factor."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "84290a88",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2ec2de24",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas_datareader as pdr\n",
    "import yfinance as yf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "06d39571",
   "metadata": {},
   "outputs": [],
   "source": [
    "import statsmodels.api as sm\n",
    "from statsmodels import regression\n",
    "from statsmodels.regression.rolling import RollingOLS"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bc2a7be0",
   "metadata": {},
   "source": [
    "Fetch Fama-French factors data starting from 2000-01-01 and select the SMB and HML factors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5aff0b52",
   "metadata": {},
   "outputs": [],
   "source": [
    "factors = pdr.get_data_famafrench(\n",
    "    'F-F_Research_Data_Factors',\n",
    "    start='2000-01-01'\n",
    ")[0][1:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "65938e3e",
   "metadata": {},
   "outputs": [],
   "source": [
    "SMB = factors.SMB\n",
    "HML = factors.HML"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8528b4ce",
   "metadata": {},
   "source": [
    "Download monthly adjusted close prices for specified stocks starting from 2000-01-01"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8518efcf",
   "metadata": {},
   "outputs": [],
   "source": [
    "data = yf.download(\n",
    "    ['SPY', 'MSFT', 'AAPL', 'INTC'], \n",
    "    start=\"2000-01-01\", \n",
    "    interval=\"1mo\"\n",
    ")['Adj Close']"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "439951e5",
   "metadata": {},
   "source": [
    "Calculate the monthly returns and convert them to period-based returns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9b300366",
   "metadata": {},
   "outputs": [],
   "source": [
    "monthly_returns = data.pct_change().to_period(\"M\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "246d309b",
   "metadata": {},
   "source": [
    "Extract the benchmark returns (SPY) and calculate active returns against the benchmark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f71342e4",
   "metadata": {},
   "outputs": [],
   "source": [
    "bench = monthly_returns.pop(\"SPY\")\n",
    "R = monthly_returns.mean(axis=1)\n",
    "active = R - bench"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ff54a6cb",
   "metadata": {},
   "source": [
    "Create a DataFrame with active returns and Fama-French factors SMB and HML"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d8ed7a12",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.DataFrame({\n",
    "    'R': active,\n",
    "    'F1': SMB,\n",
    "    'F2': HML,\n",
    "}).dropna()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3201423a",
   "metadata": {},
   "source": [
    "Perform Ordinary Least Squares (OLS) regression to estimate sensitivities to the factors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d5e1b15c",
   "metadata": {},
   "outputs": [],
   "source": [
    "b1, b2 = regression.linear_model.OLS(\n",
    "    df.R, \n",
    "    df[['F1', 'F2']]\n",
    ").fit().params"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f621be1f",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(f'Sensitivities of active returns to factors:\\nSMB: {b1}\\nHML: {b2}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2eab25c3",
   "metadata": {},
   "source": [
    "Perform rolling OLS regression to estimate how factor sensitivities change over time"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c2489be4",
   "metadata": {},
   "outputs": [],
   "source": [
    "exog_vars = [\"SMB\", \"HML\"]\n",
    "exog = sm.add_constant(factors[exog_vars])\n",
    "rols = RollingOLS(df.R, exog, window=12)\n",
    "rres = rols.fit()\n",
    "fig = rres.plot_recursive_coefficient(variables=exog_vars)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f4a1b059",
   "metadata": {},
   "source": [
    "Calculate covariance between factors and marginal contributions to active risk (MCAR) for each factor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ad0355a8",
   "metadata": {},
   "outputs": [],
   "source": [
    "F1 = df.F1\n",
    "F2 = df.F2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6b0126e7",
   "metadata": {},
   "outputs": [],
   "source": [
    "cov = np.cov(F1, F2)\n",
    "ar_squared = (active.std())**2\n",
    "mcar1 = (b1 * (b2 * cov[0,1] + b1 * cov[0,0])) / ar_squared\n",
    "mcar2 = (b2 * (b1 * cov[0,1] + b2 * cov[1,1])) / ar_squared\n",
    "print(f'SMB risk contribution: {mcar1}')\n",
    "print(f'HML risk contribution: {mcar2}')\n",
    "print(f'Unexplained risk contribution: {1 - (mcar1 + mcar2)}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "96df69b9",
   "metadata": {},
   "source": [
    "<a href=\"https://pyquantnews.com/\">PyQuant News</a> is where finance practitioners level up with Python for quant finance, algorithmic trading, and market data analysis. Looking to get started? Check out the fastest growing, top-selling course to <a href=\"https://gettingstartedwithpythonforquantfinance.com/\">get started with Python for quant finance</a>. For educational purposes. Not investment advise. Use at your own risk."
   ]
  }
 ],
 "metadata": {
  "jupytext": {
   "cell_metadata_filter": "-all",
   "main_language": "python",
   "notebook_metadata_filter": "-all"
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}