Back to Community
Bootstrapping volatility-standardized asset weights

This is a replication of some of the work alluded to in Robert Carver's new book Systematic Trading, bootstrapping reasonable asset weights based purely on volatility-standardized returns and correlations (ie: no mention of Sharpe ratios or expected returns at all).

I am somewhat surprised by how much weight was given to Gold, but perhaps I shouldn't be...

Loading notebook preview...
Notebook previews are currently unavailable.
17 responses

Most of 17 assets in the list are highly and positively correlated.
If you will leave just 2 but negatively correlated assets you will get:
more return,
less draw down,
never been under water.
Correlation does matter.

Loading notebook preview...
Notebook previews are currently unavailable.

Yeah, but you've introduced a big wad of future snooping by picking VDC which has done great the last few years. I do not think this is an improvement.

Backtest of an algo which uses these principles. Naturally you can turn up the leverage if you want, and/or add your own forecasts if you have predictors. I might try that next.

Clone Algorithm
29
Loading...
Backtest from to with initial capital
Total Returns
--
Alpha
--
Beta
--
Sharpe
--
Sortino
--
Max Drawdown
--
Benchmark Returns
--
Volatility
--
Returns 1 Month 3 Month 6 Month 12 Month
Alpha 1 Month 3 Month 6 Month 12 Month
Beta 1 Month 3 Month 6 Month 12 Month
Sharpe 1 Month 3 Month 6 Month 12 Month
Sortino 1 Month 3 Month 6 Month 12 Month
Volatility 1 Month 3 Month 6 Month 12 Month
Max Drawdown 1 Month 3 Month 6 Month 12 Month
# Backtest ID: 56248d4695b8af10f6d24c98
There was a runtime error.

Here is another pair without VDC

Loading notebook preview...
Notebook previews are currently unavailable.

Sure, you could also pick BRK or IBB or any one of hundreds of stocks that have done well in the last 8 years.

Here is the same thing but backtested by algo on VTI-TLT.including bear and bull market.Not only bull as yours.

Clone Algorithm
35
Loading...
Backtest from to with initial capital
Total Returns
--
Alpha
--
Beta
--
Sharpe
--
Sortino
--
Max Drawdown
--
Benchmark Returns
--
Volatility
--
Returns 1 Month 3 Month 6 Month 12 Month
Alpha 1 Month 3 Month 6 Month 12 Month
Beta 1 Month 3 Month 6 Month 12 Month
Sharpe 1 Month 3 Month 6 Month 12 Month
Sortino 1 Month 3 Month 6 Month 12 Month
Volatility 1 Month 3 Month 6 Month 12 Month
Max Drawdown 1 Month 3 Month 6 Month 12 Month
# Backtest ID: 56256e53b8f13d110de7f221
There was a runtime error.

Again, the US stock market has done great for the last few years. I feel like I am repeating myself.

As I remember period 2007-2009 was not great for stock market (Bear market).
So my backtest has both legs : bear (2007-2009) and bull 2009-2015).
Here is another backtest : bull (2003-2007) and bear (2007-2009).

Clone Algorithm
35
Loading...
Backtest from to with initial capital
Total Returns
--
Alpha
--
Beta
--
Sharpe
--
Sortino
--
Max Drawdown
--
Benchmark Returns
--
Volatility
--
Returns 1 Month 3 Month 6 Month 12 Month
Alpha 1 Month 3 Month 6 Month 12 Month
Beta 1 Month 3 Month 6 Month 12 Month
Sharpe 1 Month 3 Month 6 Month 12 Month
Sortino 1 Month 3 Month 6 Month 12 Month
Volatility 1 Month 3 Month 6 Month 12 Month
Max Drawdown 1 Month 3 Month 6 Month 12 Month
# Backtest ID: 56257667a177621102a87f7f
There was a runtime error.

Super, thanks.

And bonus: pure bear market 2007-2009 performance

Clone Algorithm
35
Loading...
Backtest from to with initial capital
Total Returns
--
Alpha
--
Beta
--
Sharpe
--
Sortino
--
Max Drawdown
--
Benchmark Returns
--
Volatility
--
Returns 1 Month 3 Month 6 Month 12 Month
Alpha 1 Month 3 Month 6 Month 12 Month
Beta 1 Month 3 Month 6 Month 12 Month
Sharpe 1 Month 3 Month 6 Month 12 Month
Sortino 1 Month 3 Month 6 Month 12 Month
Volatility 1 Month 3 Month 6 Month 12 Month
Max Drawdown 1 Month 3 Month 6 Month 12 Month
# Backtest ID: 56257c2c4bdd03110686fa07
There was a runtime error.

FWIW, your backtests are not true to his system, because you didn't recalculate the diversification multiplier given your new set of assets.

This is yours algo I just changed symbols and if it is not true to his system you can fix it or take it as is.

Indeed, you did. Adding value wherever you go.

Thanks Simon.

Have you ever shared an algo of your own, or do you just spend your time adding cognitive biases to other peoples' and complaining about stability and consistency metrics?

nice!! Thanks Simon (..and Vladimir)

Portfolio Analysis using pyfolio

Loading notebook preview...
Notebook previews are currently unavailable.