Markowitz Risk/Reward outlook diverse portfolio

9 oct. 2024

Here's a allocated set of decimals based on 20,000 prandom portfolio constructs based on 14 years of data (since recovery after 2008-09 GFC)

This timeline gives us less noise and focuses on the momentum of the current trend.

The final ticker decimals represent % allocation based on optimal reward with minimal risk.

9 oct. 2024

Note

What Is a Good Sharpe Ratio?
Sharpe ratios above 1 are generally considered “good," offering excess returns relative to volatility. However, investors often compare the Sharpe ratio of a portfolio or fund with those of its peers or market sector. So a portfolio with a Sharpe ratio of 1 might be found lacking if most rivals have ratios above 1.2, for example. A good Sharpe ratio in one context might be just a so-so one, or worse, in another.

9 oct. 2024

Note

For developers:
import numpy as np
import pandas as pd
# import pandas_datareader.data as web
import matplotlib.pyplot as plt
import datetime
# from scipy.sparse.linalg import lsqr
import scipy.optimize as optimization
import yfinance as yf
from datetime import datetime

...

main:

data = download_data(stocks)
show_data(data)
returns = parse_returns(data)
plot_daily_returns(returns)
show_statistics(returns)
weights = stack_weights(stocks)
calculate_portfolio_return(returns,weights)
calculate_portfolio_variance(returns,weights)
preturns,pvariances = port_generate(weights,returns,stocks)

plot_portfolios(preturns,pvariances)
statistics(weights,returns)
#statistics(weights,preturns)
sharpe_max = sharpe_pass(weights,returns)
optimum = optimizations(weights,returns,stocks)
parse_portfolios(optimum, returns,stocks)
show_optimal_portfolio(optimum,returns,preturns,pvariances)