Need help on position sizing/risk - 86% win rate - .5% per trade

Discussion in 'Risk Management' started by frostengine, Jun 17, 2021.

  1. I have a new automated strategy I am planning to go fully live with soon. I have been running it live with minimal capital since Feb. Stats are holding up well to historical, so now I am looking for some feedback on the best position sizing to utilize as I allocate a portion of my portfolio towards it.

    Here are the stats:
    86.44% winning trades
    +.5% per trade expectancy
    Returns 154% per year on average
    Largest drawdown 62.6%.. reached 40% drawdown 11 times over past 15 years
    Never had a losing year in the past 15...
    Only 18 losing months over that time period.

    I am not a big fan of stomaching a 62% drawdown on capital allocated to this strategy.

    My initial reaction is to allocate 3x the capital changing the returns as follows:
    - 51% annual returns (on allocated capital) on a 20% max drawdown and a high probability of seeing 13% drawdown in any given year

    I can live with those returns, however, I am looking for other thoughts. How would you recommend allocating capital to this strategy?
     
    shuraver and Blaze like this.
  2. SunTrader

    SunTrader

    What market(s) are these historical results based on?

    And what are the long/short splits?
     
    Last edited: Jun 17, 2021
  3. Tavurth

    Tavurth

    If you can program, you can use the Scipy optimize function.

    Basically input your profit, loss probability as an array and ask it in code to find you the best possible position size for the strategy that you aim to use.

    Then add a bit of mutation to the results so it's pretty similar to the market. (I would suggest digital position stepping, with floors)

    Given some parameters, and a little number crunching time, this should give you an exacting best(ish) case answer.
     
    mwahal likes this.
  4. deaddog

    deaddog

    What kind of risk control do you have to get a 62% drawdown with an 86% win rate?
     
  5. KevinBB

    KevinBB

    Starting with $1k (assumed, but probably not correct), 154% returns (average) over 15 years is a lot of moolah. You could pay the national debt of quite a few countries.
     
    drcruz, yerpderpington and tayte like this.
  6. fan27

    fan27

    Are the drawdowns correlated with your other strategy drawdowns? That needs to be factored into your decision.
     
  7. I'd run it at half the level you initially suggest (20% max drawdown) for 6 months and check the risk profile is as expected. I'm guessing your losers and bigger than your winners, i.e it's negative skew. So it's a potentially very dangerous strategy.

    GAT
     
  8. easymon1

    easymon1

    Sounds pretty exciting to me.
    How many automated strategies have you made money with so far?
    How long have they been in action?
     
  9. lindq

    lindq

    Sounds like you're selling puts and getting wacked pretty frequently. If so, this isn't something you'll enjoy living with.

    A bull market has supported you since February. But that can change in an instant.
     
    Last edited: Jun 18, 2021
  10. Curious minds want to know. :)
     
    #10     Jun 18, 2021
    murray t turtle likes this.