i am using bounded mathematics now days and loving it. 1.)the trend is not your friend far from it. 2.)if you don't get positive slippage your trading the wrong direction! 3.)if most everyone on et likes you ur a loser. 4.)you can make money with the stupidest stuff - i am proof. 5.)back testing data is seriously flawed and so the results will follow. 6.)humans are the worst traders - computers rule. 7.)gambling theory is a must. 8.)no substitute for experience. 9.)most can't learn trading cause they run out of fuel on takeoff. 10.)where r all the clients lambo's? piece (lol)- mb
Re: betting theory Once you start with the basics from the original sources, it's pretty easy to stay on the right track. TSGann... great post. FYI: Not related, just good info for modelling and portfolio management-- I've been reading "Risk and Asset allocation" by Meucci and I love the format of this book. Here's another website that I really enjoy that deals with statistical data mining http://www.autonlab.org/tutorials/
Are you saying that if trading using TA/PA, trading manually would be more efficient? My take was that you say that it certainly can be modeled but there may be better results trading manually? Correct? Am curious, from your perspective is there a distinct disadvantage to using PA/TA for trading models as opposed to other forms? Thanks-
Automating PA is just like any other trading model. It's a matter of having clarity over your trading to a point where you can code it and have it automated. Some concepts of PA requires a lot of resources to implement. Considering the cost vs. performance ('pute power and liquidity limit) , some PA concepts are best left alone as a manual routine. Basically, some PA tendencies get harder into what a High Frequency would do... A brief and over-simplified example would be filtering / ranking the significance of different pieces of information. Good discretionary daytraders filter/rank/adapt/re-evaluate PA aspects on a DOM tick basis. This routine is a major hastle when running something similar in a 'pute.
Currently, I am learning / researching / testing / confirming what's been mentioned by Maestro, dtrader and others in the following thread: http://www.elitetrader.com/vb/showthread.php?s=&postid=2645481#post2645481 As part of my research, I've been running some tests regarding random data... distribution... and opposingly technical tendencies... There's not much of an output so I'm not going to bother posting any csv or xls but here's a few things... Actually, the model generation and the tests were automated so there not much I can output without capping the file size limit... Anyways... the basic/over-simplified tests I've done is: 1. First, I would take the tick data for ES tick data(year) and get the distribution (simply the average and std dev.) taking different aspects of the data (price change via points, %, sequence... etc. etc.... basically, my slip-forward routine) Finally, I used the Mersenne Twister and adjust the values so that it sticks within the range of the ES data range. After having about 20 types of data... I would run a bunch of models on them to see how well the models performed... Finally after that... I would check how the models performed out-sampling for an year. Plus, I added a few more factors to help me gain a better view of how I should deal with them. 2. Obviously, there's going to be an obvious relationship between the models and performance so to add some flavors to the test, I had some of the models to be developed using other sources like S&P 500 Rebalance (I have a few tests and results so maybe I should post them sometime... hrmmm), VIX, Market Sentiments (PREM, ADV, DEC... etc. etc.) Finally, I added a few static models that are not auto-generated. My results and conclusions: 1. Just based off this simple test... you can categorize models to 2 types. Distribution dependent models and those that aren't. 2. Most (87%) technical models that use market price as their sole source of information (like trend-following, RTM, swings) are distribution dependent. Taking it further, it hurts more than helping the performance by using technical analysis. As an example, I have a trend-following model that uses some chart based breakouts and I have another model that takes the distribution of the market character in hand (ex. ORB and EOD Vola.), the simple outlier Vola. performed better... Meaning there's no point of using a bunch of indicators and patterns... Within this type of models, simple = better. Also, it's safe to say that almost all models that utilize market prices are dist. dependent in some way. 3. If you have walk-forward optimization considered, the important parameter to consider is the duration of the sustainability of the exisiting distribution. This is easy get... Run test >>> get the kurtosis and skewness value of the distribution. >>> Find the upper/lower bounds of the values >>> get the frequency and duration. 4. Outliers... outliers... outliers... You can go ahead and create a sub-category between normal distribution reliant and the outlier friendly ones. - The tricky part is the non-dependent ones: 5. It's either that haven't grasped the market character that corresponds to the model or it's an edge. And... what people consider edges usually gets placed in here. Personally, 80% of the edge-based trading get thrown in here and they get missed due to their nature. 6. Problem? 97% of the 12.46% (non-dependents) are curve-fits. The success rate of these are models sustaining the out-sample is extremely low relative to the 26% of the dependents. I still haven't found any pure mathematical / computational logic to extract them. Which ends up with me using my own logic and rationalism. Even if the concepts behind the models are sound to me personally, that doesn't guarantee high rate of success. (Haven't tested... don't know how...) 7. So... I took the better performing models for the ES that provided Zero relevance with the pseudo-random datas and ran them on different markets. This actually helped filter "some" of the good systems. But it easily managed to dismiss the better performing models in the out-sample.
OK... I was being a bit confusing... so I'll reword things... 1. Most, but not all, models are dependent on some kind of distribution of a model's corresponding market tendency. So whatever the model is... it exposes some kind of distribution and largely affected by it. This is pretty much common sense and mentioning in this thread (title of the thread)... sucks... 2. "Non-dependent" models do exist. Though, it's very likely that they are due to Statistical Bias like "Omitted-variable bias", "Systemic Bias"... 3. The most influential aspect of having a profitable model(s) is how well you understand the data you are trading with. * In all different levels, more than what I have mentioned... Trading systems, rules and models are just a bunch of flies swarming around the "market" trying to pick out some shit without getting squatted down. Really...
Thanks TSGannGalt. So it sounds like after a certain level of market proficiency using PA, trading discretionarily achieves better results because the human brain is a better execution/management system as compared to a computer given the algorithm complexity and computational power required to execute real-time. Is that correct?
Nope. (in a soft tone...) They're both the same. Seemingly, from the past 2 posts you've made in here... you seem to WANT, to make me say, "Discretionary trading is better than systematic trading". If my assumptions are correct in anyway, what I can tell you is to seriously, take a step back and stop looking for comfort and put some effort into acquiring what you "know" you need to do. Seriously... you're in the "Automated Trading" forum and you're asking these questions... You must have some doubts inside you that you are already aware of... Now... can I stop giving therapy and take some time posting some "rather irrelative" #s.
You posted testing results in which discretionary trading outperformed several automated trading systems albeit over a short timeframe. I took interest in the results/post and so attempted to ask/clarify if from those results (and your experience in general) you carried the opinion that discretionary trading outperformed systemic trading in that particular context (short term PA). So no, I wanted only your opinion and when it wasnât clear to me, I asked follow up questionsâ¦..oh well, Iâll return to the less smart forums then so as not to dilute/sidetrack. John would be proud.