Developing & Backtesting Systematic Trading Strategies

Discussion in 'Automated Trading' started by jack, Jul 4, 2017.

  1. jack

    jack Administrator Staff Member

    Joined:
    Mar 29, 2013
    Messages:
    2,402
  2. jack

    jack Administrator Staff Member

    Joined:
    Mar 29, 2013
    Messages:
    2,402
     
  3. shopster

    shopster Well-Known Member

    Joined:
    Jun 17, 2013
    Messages:
    531

    Back-testing.

    I hate it — it’s just optimizing over history. You never see a bad back-test. Ever. In any strategy.

    Josh Diedesch(2014)


    trade the bleeding right edge.

    s
     
  4. jack

    jack Administrator Staff Member

    Joined:
    Mar 29, 2013
    Messages:
    2,402
    Personally I do a lot of walk-forward tests to vet ideas.. and I know you're not a fan of backtesting.

    What does your process look like? Full discretion and using experience to know when to make adjustments?
     
  5. shopster

    shopster Well-Known Member

    Joined:
    Jun 17, 2013
    Messages:
    531
    jack,

    at your level of trading, you should no longer be wasting time on this opto back or forward testing bull crap.

    your process should be cast in stone.

    each day is the same .
    get up , slay a few dragons, walk away.

    the shit goes up, down and sideways.

    period.

    s
     
  6. vtrader21

    vtrader21 New Member

    Joined:
    Jul 9, 2017
    Messages:
    3
    You can't trade "the hard right edge" without trading history. You know everything that is comes before on that chart?! You wouldn't know WTF to do where to take the trade.
     
  7. shopster

    shopster Well-Known Member

    Joined:
    Jun 17, 2013
    Messages:
    531
    " You can't trade "the hard right edge" without trading history..."

    V21,

    take the name off the top of the bar chart.
    they all go up, down and sideways.

    why dont you show us " unwashed minions " how back testing and curve fitting past behavior will improve the hard right edge and post up some real $ stats to prove your hypothesis.

    s
     

Share This Page