Would You Trade This System?

F

feng456

For a $5000/contract ES setup:

max dd = 4000

(determined after 10,000 runs in Monte Carlo sim where 4000 was at 20th percentile for max DD)

expected profit per year = 50% of that 5000

(determined through 10,000 runs in Monte Carlo sim where 50% was around the 20th percentile for expected profits)

Using the above information and assuming perfect execution fills etc. (bear with me please), would you trade this?
 
Quote from feng456:
... where 4000 was at 20th percentile for max DD...
More...

By this do you mean that 20% of the MCs had a worse drawdown, and 80% were better?
 
can you please post your yearly numbers from the backtest. so if you did backtest over 5 years, yearly returns and max dd every year and yearly profit factors.

Also, what is the holding period for these trades and how many trades per year?

All these are important questions that give a better picture of how sustainable the strategy will be in future. The information you have shared is valuable still kind of incomplete to come up with a good decision whether to trade it or not. Thanks.
 
A possible 90% drawdown for the chance at 50% profitability seems pretty risky, but I know you mentioned that that was from the Monte Carlo simulation.

I'm not sure I would personally put it into production. Maybe if I had other systems and this wasn't my only system just to spread the risk across my portfolio.
 
NO WAY!

I would never be as irresponsible with my money as to trade a 90% DD system. I suggest you adjust your parameters.
 
Quote from abattia:

By this do you mean that 20% of the MCs had a worse drawdown, and 80% were better?
More...
I would think the common sense thing to do would be to use the 50% percentile values.
 
Quote from kut2k2:

I would think the common sense thing to do would be to use the 50% percentile values.
More...

I'd rather be safe than sorry. That's why I use 20th percentile...the extra cushion is always good.
 
Quote from gmst:

can you please post your yearly numbers from the backtest. so if you did backtest over 5 years, yearly returns and max dd every year and yearly profit factors.

Also, what is the holding period for these trades and how many trades per year?

All these are important questions that give a better picture of how sustainable the strategy will be in future. The information you have shared is valuable still kind of incomplete to come up with a good decision whether to trade it or not. Thanks.
More...

I am able to answer some of those questions partly due to indiscretion in the past, partly also I don't know the answer to a couple of them:

LIVE max DD has stayed within backtested results

backtested over 5 years worth of data.

holding period is on average 1 hour. averaging ~0.7 trades per day.

Live results from 2012 was around 110% returns. 2013 is looking very poor..like breakeven.

All results were before commissions but having taken into account slippage.
 
Quote from feng456:

Yes that is correct.
More...
Thanks.

OK, assuming you re-run the backtests:
a) with commissions
b) realistic execution assumptions
c) etc

… and that you get the same backtest performance and MC-test results (and that we all agree objectively that i) the test results are meaningful given the historical price data and methodology you use, and ii) the results are also good, etc) …

… then this is essentially a position sizing question, no? i.e. Would you trade that strategy with that position size in view of the backtested/MC-tested draw down results?

There are many ways to position size. IMHO, it’s valid to make the calculation whereby:

Minimum capital/contract = margin required by broker + (backtested or MC-tested max drawdown * safety factor)

How does 20th MC percentile of max draw down compare with say 2 x max backtested drawdown?

And what is your broker’s margin per contract for the instrument you are trading?
 
You must log in or register to reply here.
Back
Top