Optimizing or curvefitting

Discussion in 'Strategy Building' started by indahook, Mar 22, 2004.

  1. Obviously one of the most important things to consider before
    running a trading system is determining the type of mkt you are
    trading i.e trending up, down or sideways. Which leads me to this question. When backtesting a
    long/short strategy do any of you use a broad mkt directional filter
    as one of your first rules? When I run a backtest of a certain
    strategy I have written over the past 4 years I get mediocre-poor
    returns..barely beating the mkt after commission. And an unacceptable
    risk reward. But if I use a filter to determine if we are in Bull
    or Bear territory before going long or short the returns are great,
    whipping the mkt averages 10-15% and risk reward well over 3-1. Do any system traders have any thoughts on this? Can this be considered curze fitting?

    BTW, these are longer term strategies the avg hold for winners is 63 days and losers 70.

    sorta new at this system building stuff,
  2. saxon


  3. I read Pardo's book in 1994 or 1995. It was one of the most useless books on trading that I have ever read. Of course, this is a personal opinion. However, I find it difficult to believe that consistently successful traders actually trade this way. (If I am wrong, it won't be the first time.) I think it is selling a relative shortcut to hard work and years of study, which is probably its appeal to people new to the markets. I think that shifting the focus away from the actual markets and towards computing technology is a critical error. My view is that there is more to gain by studying the actual market action itself rather than perusing test run summaries.

    But don't take my word for it. Read the book and then share your comments.
  4. I appreciate the input. I am just looking for anything that will help me along this new path.
  5. ...just a personal opinion, but I think the Babcock book is the best system development book.

    No disrespect to Thunderdog, but there are only three variables in trading (time, price, and volume), so with sufficient algorithm development skill IMO there is no hypothesized pattern in market action which cannot be coded and tested.

  6. I also read Babcock's system development book in 1998. It was far better than Pardo's, however, it had some shortcomings. These are discussed in William Gallacher's excellent book, Winner Take All. Gallacher trades fundamentally, whereas I only employ price and volume. However, he provides critical insight that I think would benefit true system traders.

    Hypostomus, if you were able to circumvent the tedium of studying market action, bar by bar, over an extended period, then my hat is off to you. If you were able to become consistently profitable (without debilitating periodic drawdowns) by simply hypothesizing and then doing computer test runs, then you are head and shoulders above the likes of me.
  7. http://www.elitetrader.com/vb/showthread.php?s=&threadid=28858&perpage=6&pagenumber=10

    When under backtest such indicators seem to perform well, it's almost due to persistency of trend (see Arcsinus law: distinguishing trend from persistency of chance http://www.elitetrader.com/vb/showt...tency+and+trend) that is to say that they are meaningless inferentially speaking as for pertaining to their performance in the future ! That's why the backtest on these indicators are flawed from their very ground and all datas about returns and decorations to appear "scientific" are just cosmetics that won't erase that ! Only those who confuse EMPIRICAL statistics which concerns past performance only and ignore the INFERENTIAL statistics would be fooled.

    So pure MECHANICAL SYSTEM based SOLELY on these kind of indicators are due to be DOOMED SOONER or LATER. Of course there is always a chance that they don't fail but it is due to chance, for example such a system for daily scale could outperform during the past 20 years of Bull market but on the next "sampling" of twenty years you don't know. Being impressed by such a performance, especially if it is compounded, is to be fooled by probability fallacies.

  8. ...I am just a happy idiot. By no means did I mean to disparage the joys of tediously speculating on market action bar-by-bar. That is exactly what I do to distract myself from impetuous action while I am in a trade. I test each delusional idea as it occurs to my febrile mind, which wants only to escape from the tension of holding a position. I have tested scores of worthless ideas in the past two years and have only five (apparently) working systems to show for it. I never cease to be amazed at how certain I am that this or that pattern works, only to find that it is a loser overall, and that memory retains only the rare wins.
    #10     Mar 22, 2004