{
“cells”: [
{

“cell_type”: “markdown”, “id”: “b5tv1pn1yfm”, “metadata”: {}, “source”: [

“# CVaR Optimizationn”, “n”, “This notebook solves a mean-CVaR (Conditional Value-at-Risk) allocationn”, “problem on a small ETF universe. CVaR directly targets tail losses rather thann”, “variance, making it well-suited for portfolios where downside risk matters most.n”, “n”, “We compare the CVaR frontier against the classical mean-variance frontier.”

]

}, {

“cell_type”: “code”, “execution_count”: 1, “id”: “6bdps7piz5q”, “metadata”: {

“execution”: {

“iopub.execute_input”: “2026-03-30T19:38:16.622816Z”, “iopub.status.busy”: “2026-03-30T19:38:16.622473Z”, “iopub.status.idle”: “2026-03-30T19:38:17.293293Z”, “shell.execute_reply”: “2026-03-30T19:38:17.292998Z”

}

}, “outputs”: [], “source”: [

“import numpy as npn”, “import pandas as pdn”, “import matplotlib.pyplot as pltn”, “from pyvallocation import PortfolioWrapper”

]

}, {

“cell_type”: “markdown”, “id”: “rb4miki8fsq”, “metadata”: {}, “source”: [

“## Load ETF return scenariosn”, “n”, “We use the most recent 750 trading days from the bundled ETF dataset.”

]

}, {

“cell_type”: “code”, “execution_count”: 2, “id”: “eyvqtmfn1fw”, “metadata”: {

“execution”: {

“iopub.execute_input”: “2026-03-30T19:38:17.294642Z”, “iopub.status.busy”: “2026-03-30T19:38:17.294541Z”, “iopub.status.idle”: “2026-03-30T19:38:17.303694Z”, “shell.execute_reply”: “2026-03-30T19:38:17.303490Z”

}

}, “outputs”: [

{

“name”: “stdout”, “output_type”: “stream”, “text”: [

“Assets : [‘DBC’, ‘GLD’, ‘SPY’, ‘TLT’]n”, “Scenarios: 750n”

]

}

], “source”: [

“from pathlib import Pathn”, “n”, “_candidates = [n”, “ Path("examples/ETF_prices.csv"),n”, “ Path("../examples/ETF_prices.csv"),n”, “ Path("../../examples/ETF_prices.csv"),n”, “ Path("../../../examples/ETF_prices.csv"),n”, “]n”, “_csv = next((p for p in _candidates if p.exists()), None)n”, “if _csv is None:n”, “ raise FileNotFoundError("ETF_prices.csv not found")n”, “prices = pd.read_csv(_csv, index_col="Date", parse_dates=True)n”, “prices = prices.dropna(how="all").ffill()n”, “returns = prices.pct_change().dropna(how="any").iloc[-750:]n”, “n”, “probabilities = np.full(len(returns), 1.0 / len(returns))n”, “n”, “print(f"Assets : {list(returns.columns)}")n”, “print(f"Scenarios: {len(returns)}")”

]

}, {

“cell_type”: “markdown”, “id”: “3j1tn27l63o”, “metadata”: {}, “source”: [

“## Build the CVaR frontiern”, “n”, “We use from_scenarios with uniform probabilities and trace a 7-pointn”, “CVaR frontier at the 5% tail level.”

]

}, {

“cell_type”: “code”, “execution_count”: 3, “id”: “ofrykaf30pd”, “metadata”: {

“execution”: {

“iopub.execute_input”: “2026-03-30T19:38:17.304770Z”, “iopub.status.busy”: “2026-03-30T19:38:17.304692Z”, “iopub.status.idle”: “2026-03-30T19:38:17.428917Z”, “shell.execute_reply”: “2026-03-30T19:38:17.428624Z”

}

}, “outputs”: [

{

“name”: “stderr”, “output_type”: “stream”, “text”: [

“Estimating mu and cov from scenarios (no explicit values provided).n”

]

}

], “source”: [

“wrapper = PortfolioWrapper.from_scenarios(n”, “ returns, probabilities=probabilitiesn”, “)n”, “n”, “cvar_frontier = wrapper.cvar_frontier(num_portfolios=7, alpha=0.05)”

]

}, {

“cell_type”: “markdown”, “id”: “xazl1mg17z”, “metadata”: {}, “source”: [

“## Extract the minimum-CVaR portfolio”

]

}, {

“cell_type”: “code”, “execution_count”: 4, “id”: “9bpl8qxy0xp”, “metadata”: {

“execution”: {

“iopub.execute_input”: “2026-03-30T19:38:17.430091Z”, “iopub.status.busy”: “2026-03-30T19:38:17.430031Z”, “iopub.status.idle”: “2026-03-30T19:38:17.432088Z”, “shell.execute_reply”: “2026-03-30T19:38:17.431898Z”

}

}, “outputs”: [

{

“name”: “stdout”, “output_type”: “stream”, “text”: [

“=== Minimum-CVaR Portfolio ===n”, “DBC 0.1453n”, “GLD 0.3338n”, “SPY 0.2218n”, “TLT 0.2991n”, “Name: Min Risk Portfolio, dtype: float64n”, “Expected return: 0.0306%n”, “CVaR (alpha=5%): 1.4032%n”

]

}

], “source”: [

“min_w, min_ret, min_cvar = cvar_frontier.min_risk()n”, “n”, “print("=== Minimum-CVaR Portfolio ===")n”, “print(min_w.round(4))n”, “print(f"Expected return: {min_ret:.4%}")n”, “print(f"CVaR (alpha=5%): {min_cvar:.4%}")”

]

}, {

“cell_type”: “markdown”, “id”: “f9pj3bkkbn5”, “metadata”: {}, “source”: [

“## Compare CVaR vs mean-variance frontiersn”, “n”, “We overlay both frontiers. The MV frontier uses volatility as the risk axis,n”, “while the CVaR frontier uses CVaR; here we plot them side by side for visualn”, “comparison of the return-risk trade-off.”

]

}, {

“cell_type”: “code”, “execution_count”: 5, “id”: “xcfwccdck4”, “metadata”: {

“execution”: {

“iopub.execute_input”: “2026-03-30T19:38:17.433184Z”, “iopub.status.busy”: “2026-03-30T19:38:17.433130Z”, “iopub.status.idle”: “2026-03-30T19:38:17.640690Z”, “shell.execute_reply”: “2026-03-30T19:38:17.640471Z”

}

}, “outputs”: [

{
“data”: {

“image/png”: “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”, “text/plain”: [

“<Figure size 1200x500 with 2 Axes>”

]

}, “metadata”: {}, “output_type”: “display_data”

}

], “source”: [

“mv_frontier = wrapper.variance_frontier(num_portfolios=20)n”, “n”, “fig, axes = plt.subplots(1, 2, figsize=(12, 5))n”, “n”, “# Left: Mean-Variancen”, “axes[0].plot(mv_frontier.risks, mv_frontier.returns, "o-", color="steelblue")n”, “axes[0].set_xlabel("Volatility")n”, “axes[0].set_ylabel("Expected Return")n”, “axes[0].set_title("Mean-Variance Frontier")n”, “n”, “# Right: Mean-CVaRn”, “axes[1].plot(cvar_frontier.risks, cvar_frontier.returns, "s-", color="darkorange")n”, “axes[1].scatter(min_cvar, min_ret, s=120, marker="*",n”, “ color="red", zorder=5, label="Min-CVaR")n”, “axes[1].set_xlabel("CVaR (alpha=5%)")n”, “axes[1].set_ylabel("Expected Return")n”, “axes[1].set_title("Mean-CVaR Frontier")n”, “axes[1].legend()n”, “n”, “fig.tight_layout()n”, “plt.show()”

]

}

], “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”: “3.12.9”

}

}, “nbformat”: 4, “nbformat_minor”: 5

}