FilippoGuerrieri26/cross_sectional_momentum.ipynb

## cross_sectional_momentum.ipynb
{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "202249b2-7da3-4449-971c-5263220cc789",
   "metadata": {},
   "source": [
    "# Cross Sectional Momentum"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "37cecf60-c6fd-4064-a505-f149043e81c1",
   "metadata": {},
   "source": [
    "The majority of momentum studies have used cross-sectional momentum as the basis for security selection, choosing stocks on the basis of their relative performance over some prior period <br>\n",
    "Cross-sectional momentum is based on price trends between different markets or securities in the cross-section. Cross-sectional momentum looks at the relative strength of a cross-section of markets. Securities are ranked based on their relative strength momentum to determine which markets or stocks have gained more and which have gained less.\n",
    "<br>\n",
    "You may find the link to the paper of Asnes et al. \"Value and Momentum Everywhere\" here: <br>\n",
    "https://pages.stern.nyu.edu/~lpederse/papers/ValMomEverywhere.pdf"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "88896b2b-f4f8-459f-bc71-d692ca346a60",
   "metadata": {},
   "source": [
    "## 1. Define constants and basic functions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "82601437-4d1f-4c5a-8648-5c59ad621277",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load packages\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "684251fe-1f7f-46a4-be1b-0dfb4815fcc4",
   "metadata": {},
   "source": [
    "On following, I am going to define some basic constants that allow us to to deal with data frequency and resampling, together with a few basic functions to run the backtest on the strategy and visualize the results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "b96b3b2c-fd87-4a7e-ba39-ca582ce2b739",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define constants to handle data frequency\n",
    "days_per_month = 22\n",
    "days_per_year = 252\n",
    "weeks_per_year = 52\n",
    "months_per_year = 12\n",
    "quarters_per_year = 4\n",
    "\n",
    "daily = 'D'\n",
    "weekly = 'W'\n",
    "monthly = 'M'\n",
    "quarterly = 'Q'\n",
    "yearly = 'Y'\n",
    "\n",
    "frequencies = {\n",
    "    daily: days_per_year,\n",
    "    weekly: weeks_per_year,\n",
    "    monthly: months_per_year,\n",
    "    quarterly: quarters_per_year,\n",
    "    yearly: 1\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "ac27871c-ddf9-4029-9ba2-972e26927d00",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define function to compute simple returns\n",
    "def simple_returns(series):\n",
    "    \"\"\"\n",
    "    Computes simple returns from prices\n",
    "    \"\"\"\n",
    "    return series.pct_change().dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "9830164d-cd7d-4f39-8ce9-71eaa7aa27f2",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define a simple strategy backtster\n",
    "def backtester(returns, weights):\n",
    "    \"\"\"\n",
    "    Runs a simple backtest from returns and weights series\n",
    "    \"\"\"\n",
    "    returns_df = returns.to_frame() if isinstance(returns, pd.Series) else returns.copy()\n",
    "    weights_df = weights.to_frame() if isinstance(returns, pd.Series) else weights.copy()\n",
    "    return (returns_df * weights_df.shift(1)).sum(axis=\"columns\",  min_count=1).dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "4a418594-4905-40e7-8797-a222ddaa214e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define function to plot the Equity Line\n",
    "def plot_equty_line(returns):\n",
    "    plt.figure(figsize=(18, 8))\n",
    "    plt.plot((returns + 1).cumprod())\n",
    "    plt.title(\"Equity Line\")\n",
    "    plt.grid()\n",
    "    plt.xlabel(\"Date\")\n",
    "    plt.ylabel(\"Wealth\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2b199209-794a-4593-802e-d1e74cf11f50",
   "metadata": {},
   "source": [
    "## 2. Load Sample Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "feef8115-d051-410b-bc22-7ad5ee2427fd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>GE</th>\n",
       "      <th>IBM</th>\n",
       "      <th>MSFT</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2018-01-02</th>\n",
       "      <td>103.178185</td>\n",
       "      <td>113.086746</td>\n",
       "      <td>80.562042</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-01-03</th>\n",
       "      <td>104.153717</td>\n",
       "      <td>116.195221</td>\n",
       "      <td>80.936966</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-01-04</th>\n",
       "      <td>106.334343</td>\n",
       "      <td>118.548584</td>\n",
       "      <td>81.649330</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-01-05</th>\n",
       "      <td>106.391731</td>\n",
       "      <td>119.127762</td>\n",
       "      <td>82.661644</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018-01-08</th>\n",
       "      <td>104.899727</td>\n",
       "      <td>119.846268</td>\n",
       "      <td>82.746010</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                    GE         IBM       MSFT\n",
       "Date                                         \n",
       "2018-01-02  103.178185  113.086746  80.562042\n",
       "2018-01-03  104.153717  116.195221  80.936966\n",
       "2018-01-04  106.334343  118.548584  81.649330\n",
       "2018-01-05  106.391731  119.127762  82.661644\n",
       "2018-01-08  104.899727  119.846268  82.746010"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Read sample Adjusted Close price data for 3 stocks: GE, IBM, MSFT\n",
    "prices = pd.read_excel(\"../sample_data.xlsx\")\n",
    "prices.set_index(\"Date\", inplace=True)\n",
    "prices.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b4f1d066-64e1-49cc-9c0e-9dc55073b444",
   "metadata": {},
   "source": [
    "## 3. Define a class to run a Cross Sectional Momentum Strategy"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1ed96589-135c-460e-ba82-969e381a8274",
   "metadata": {},
   "source": [
    "Within asset class (e.g. equity, fixed income etc) for n assets, the steps to be followed in order to compute portfolio weights are:\n",
    "1. Calculate the average return for each of the assets for the last year, excluding the last month\n",
    "2. Rank the returns 1,..,n\n",
    "3. Subtract the mean rank from the ranks and divide by n\n",
    "4. Repeat at each rebalancing date"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "28edd88b-72f0-4dfa-a7da-e6ccb2ee132f",
   "metadata": {},
   "outputs": [],
   "source": [
    "class CrossSectionalMomentum:\n",
    "    \"\"\"\n",
    "    Define a Cross Sectional Momentum strategy.\n",
    "    The strategy uses weekly returns, automatically computed by feeding prices in.\n",
    "\n",
    "    Weight = (rank - average of ranks) / n° of securities\n",
    "\n",
    "    Parameters\n",
    "    ----------\n",
    "    prices: Pandas Time Series dataframe of prices\n",
    "\n",
    "    Returns\n",
    "    -------\n",
    "    backtest: strategy returns as pandas Dataframe\n",
    "    \"\"\"\n",
    "\n",
    "    def __init__(self,\n",
    "                 prices: pd.DataFrame,\n",
    "                 frequency=weekly):\n",
    "        self.prices = prices\n",
    "        self.frequency = frequency\n",
    "        self.w_length = {\"D\": 230,\n",
    "                         \"W\": 48,\n",
    "                         \"M\": 11}\n",
    "        self.shift_ = {\"D\": 22,\n",
    "                       \"W\": 4,\n",
    "                       \"M\": 1}\n",
    "        self.returns, self.weights = self.strategy()\n",
    "\n",
    "    def strategy(self) -> (pd.DataFrame, pd.DataFrame):\n",
    "        p_week = self.prices.resample(self.frequency).last()\n",
    "        returns = simple_returns(p_week)\n",
    "        mean_ret = returns.shift(self.shift_[self.frequency]\n",
    "                                 ).rolling(window=self.w_length[self.frequency]).mean().dropna()\n",
    "\n",
    "        rank = mean_ret.rank(axis=1, ascending=False)\n",
    "        weights = rank.sub(rank.mean(axis=1), axis=0) / rank.shape[1]\n",
    "\n",
    "        return returns, weights\n",
    "\n",
    "    def backtest(self) -> pd.DataFrame:\n",
    "        return backtester(self.weights, self.returns)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "a59b09c3-324e-4805-b33b-d919afec2d62",
   "metadata": {},
   "outputs": [],
   "source": [
    "csm = CrossSectionalMomentum(prices=prices.dropna(axis=1), frequency=weekly)\n",
    "\n",
    "strategy_ret = csm.backtest()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "9f4900d5-fd9a-419d-8f24-5d86e1310699",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Date\n",
       "2019-01-06    0.009453\n",
       "2019-01-13    0.026844\n",
       "2019-01-20    0.025912\n",
       "2019-01-27   -0.011447\n",
       "2019-02-03    0.005350\n",
       "Freq: W-SUN, dtype: float64"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "strategy_ret.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "e4bea33a-ed6f-4c69-b1ba-86042b8624d5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1296x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_equty_line(strategy_ret)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d3eda803-395b-45c4-a904-f4b73847d644",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}