System Trading
Now Reading
System Building Lessons continued
38

System Building Lessons continued

by ScottMarch 20, 2017

I keep getting distracted, but I’d like to move ahead quite rapidly now since Mole will be back on deck soon enough. Today’s post has enough information for you to go ahead and build working mean reversion trading systems right now, with not that much work involved.

I think we’ve covered in enough detail the idea that the best systems are based around a simple and clearly articulated idea, which can be tested for veracity.

The problem with complicated ideas is that our brains are built to believe all kinds of bullshit that isn’t true. Look at the recent election for a perfect example, we are a walking stew of cognitive biases that fuck with us relentlessly.

For an example of how I’ve personally been taken in by this kind of fraudulent bullshit let me examine the Top Down System. Ivan has a system with 13 different buy and sell setups, which happen on average every 1.6 bars. Overall they are nether a positive nor a negative edge, but there are significant times they outperform and they appear at almost every turning point, leading to significant confirmation bias. Ivan’s top down idea stacks a bunch of stupid ideas together to render them effectively untestable. When he gets his students to build systems he insists of ever more layers of complexity stacked up on top of the already complicated ball of wax. Which is why he’s broke, not to put too fine a point on it, and why I’m continually fielding emails from his bitter students asking me to put them on the right path.

The system works like this (there are a few variations but its the same concept) Look at the daily and 8 hour charts. When you are supposed to be in a long setup (according to his rules) you drop down to a lower timeframe like 15m, 60m, and 240m and search for setups in the long direction (if the system is long on a higher timeframe).

It sounds logical at first, and I admit I was taken in by it. But how to test the assumptions here? We have some critical assumptions

  • That the system as a whole is an edge, so trading in the direction of “the system” is going to improve the edge
  • That all timeframes are equal, ie that setups have equal edge and validity on any chart you want to pull up
  • That if there is a discrepancy between timeframes the higher timeframe is the “dominant one”
  • That all of the 13 setups are just as good as each other
  • That all the setups are just as good long as short
  • That one campaign management is appropriate for both rangebound and trending markets
  • That you should exit a long position when a short appears

Taken together, it is quite literally impossible to test all these assumptions together. I proceeded to produce some impressive backtests, comprising a lot of work, that showed an expectancy of .2 or above in the short term.

Long story cut short, it didn’t work at all. It wasn’t an edge, and the fault was mine. I did not understand how fragility affected trading systems, and thought you could keep adding more and more rules ad infinitum.

The best systems are very simple. Simple ideas, and simple mechanisms.

Most of the systems you will build are variants on trend following, breakout, volatility breakout, momentum and mean reversion systems.

These are the low hanging fruit. When I see people want to get fancy with fancy ideas I see it as an affectation, like wearing a bowtie. Showing the world how smart you are, except you just look like a dick when you wear a bow tie. And you trade like a dick when you design systems with too many moving parts and too many untested assumptions.

Today I’d like to deep dive a little on mean reversion systems, and show you some of the classics, which have strong results, and provide you a cookbook for building your own systems. Stock and index futures mean reversion systems are dramatically easier than other kinds (which require real maths and not just the sort of “I can barely follow along” maths that I have)

Mean reversion systems are fundamentally different than trend following systems. Here’s where I have to eat a little humble pie.

I’d always been dismissive of those who traded without stops. Even when traders I deeply admire, like Victor Neiderhoffer, don’t believe in them, I thought that was why he blew up.

I was wrong. Ernest Chan explained it very well (and I’m running Ernest’s mean reversion systems in one of my own accounts to great effect) that if I am buying a breakout or a trend it makes logical sense to have a stop, because only a minority of trends ever pan out like we hope. However if we think mean reversion is probable with a 3 standard deviation move, logically it should be even more probably with a 4 standard deviation move, therefore a stop is illogical for a mean reversion system.

Trends and mean reversion are fundamentally different in every way, it stands to reason that stops are no different

In the real world we might choose to have stops in our systems, but we should do so knowing that virtually any mean reversion system we can build will be adversely affected by the presence of even a very wide stop.

So how do the professionals deal with this? They deal by trading for what you and I would probably regard as tiny, insignificant size.

For example this is Ernest Chan’s system on one my accounts for yesterday, on a roughly $100K account it took a few trades making or losing $20 a time. Hardly life changing stuff, is it? But the sharpe ratio is kept artificially high by taking enormous numbers of small trades.

2017-03-20_17-01-37

2017-03-20_17-04-31

And yet, the long term results are more than acceptable. This is the secret sauce of mean reversion systems. I’ve looked at a lot of them now, and they share the same basic ingredients.

  • A metric fuckton of trades
  • Very wide or no stops
  • Tiny targets
  • Win rates > 65%
  • Very carefully chosen markets

If you are interested in learning more about these systems I hope you are a member. This isn’t a charity and professionals get paid. You can get plenty of free stuff from the dumbasses at that “bear blog”, the latest wave counts and pretty charts and so on.

evil_separator

It's not too late - learn how to consistently bank coin without news, drama, and all the misinformation. If you are interested in becoming a subscriber then don't waste time and sign up here. The Zero indicator service also offers access to all Gold posts, so you actually get double the bang for your buck.

Please login or subscribe here to see the remainder of this post.


About The Author
Scott
  • http://evilspeculator.com Sir Mole III

    Happy Monday everybody! :0)

  • http://www.captainboom.com/ captainboom

    The discussion of statistics and standard deviation set me to thinking of a physics class I had many moons ago. The prof was insistent on us using Average (or Mean) Deviation, vs Standard Deviation. At the time, we students thought it was a pain in the ass, and grumbled that we couldn’t just punch the Std Dev button on the calculator.

    Fast forward to this morning, and I find myself once again wondering why he wanted us to use Avg Deviation vs Std Deviation. A short search later, and I come up with this article:
    http://www.leeds.ac.uk/educol/documents/00003759.htm
    Which does a nice job of describing the difference, and why Mean (average) Deviation may actually be better for empirical data, especially that which isn’t a perfect Normal Distribution.

    I think I’m going look at using MD vs SD as I do my research.

  • BobbyLow

    Mornin Folks. Another outstanding, understandable post and a great way to begin the week.

    Not to bang simplicity to death, but I’ve seen a lot of charts that look like a plate of spaghetti with lines going every way imaginable that I can’t make any sense out of at all. Then there are other systems that are about as easy to understand as a Rubik’s Cube. I’m not going to say that these systems can’t work for those who use them because I don’t know that.

    However, I would suggest that if you can’t design your own system than perhaps you could pick one of Moles and then follow it from entry to exit with your only control being the size of your position. Just a suggestion. :)

    Another suggestion is that from time we’ll have posters (other than Mole and Scott) who get hot and into a really good run of trades. If your new to the business, you might think it’s a good idea to follow them into a trade. This is most likely a very BAD idea because you probably do not have the same lens, time frame or risk tolerance of the person talking about a given trade.

    I have 3 open trades at this moment and they are Long Nutty Gas and Long Silver that were held over the weekend. I also opened a new long miner position this morning (NUGT).

  • BobbyLow

    Math was not my forte in school. I used to ace the touchy feely classes though. :)

    However if I could take a wild guess as to why the mean deviation might work better, I would say that the SD by itself gives too much weight to outliers?

  • http://www.captainboom.com/ captainboom

    Yes, among other things. It’s also often taught to throw out outliers when using SD. As we know, outliers are going to happen in the markets, and in fact may be where we make our money. Personally, I think that data needs to be included in any analysis.

  • http://gerb-reloaded.blogspot.com/ Gold_Gerb

    I like outliers. I think of it as reality where ‘sh!t happens’.

    An interesting article I read a while back summarized “if your standard deviation is exceed by far, your model may not reflect reality”.

    LTCM anyone?
    https://investingcaffeine.com/tag/long-term-capital-management/

    like Mole said, the smartest ones shouldn’t be in this Biz.
    😉

  • Grant

    Scott, do you find that the need for a stop is the result of too much being risked on the trade or is it that you are taking trades where large standard deviation moves have a high % to revert to the mean and simply do not need a stop?

  • Scott Phillips

    No, its not like that at all.

    The trade risk on a mean reversion system is typically about .1 the size of a pattern based setup.

    You aren’t picking market direction in the sense you understand, its just a high probability of an extremely small move.

  • Scott Phillips

    You can build a system to take into account this distribution.

    By their very nature a “black swan” is unpredictable, you won’t see it coming.

    But if you understand that eventually you WILL get a black swan, all that is required to profit is that you have a mechanical entry which guarantees you get in on any major trend. Both bollingers/keltners/donchians can be tweaked to do this.

  • Scott Phillips

    For example, trading a $100,000 account, I would expect to be winning or losing approximately $500 on a “normal” system.

    With a mean reversion system on the same account I’m expecting to be winning or losing $20 or $30.

    The position sizing is literally that small, to enable “without a net” trading. So they don’t use the traditional R value stop calculation at all. It’s about average wining trade in $ – average losing trade in $.

    The advantages are:

    – System building process is dramatically simplified
    – Rules are simple – fewer mistakes
    – Backtesting is dramatically simplified to the point where retail idiots can do it just like Mole
    – Mean reversion is by definition negatively correlated with trend following, so combining two systems reduces drawdowns
    – Win rates are by definition high, upwards of 65% so drawdowns are by definition small and short lived. These are “steady stacking paper” systems with very low drawdowns but objectively only average returns. CAGR’s 20-25% PA are all you can get.

  • Scott Phillips

    Heavy math isn’t necessary. What we both know

    Pro trading is:

    Having a system, with an edge, and trading that system mistake free for correct position sizing, keeping proper records and reviewing them regularly.

    If you do that right now, don’t change, just keep doing.

  • Yoda

    LOL you are making friends today XD

  • Yoda

    Bulls had an opportunity to steal the ball at the positive divergence on 5 min zero (3pm EST), and make a run for it. But that attempt fell back on its arse so far.

  • Yoda

    Great move switching to long NG last week. I am in UNG and a happier camper today. Also L GDXJ and SDS.

  • Scott Phillips

    I know I might have come across as harsh to Grant the other day, but would you have preferred me to sugar coat it?

    He’s a serious guy, he’s done more work than 99% of the people reading this blog. If hard work was all it took, he deserves to succeed.

    There is literally zero chance that his system will make him money over the long term. I’m sorry for his wasted work, and believe me I wasted more time than that doing the exact same things, but crying about that won’t change it.

    Nor will sticking his head in the sand and saying “but I BELIEVE this shitty system works if only you start trading it the second you see an outside period”

    It’s fundamentally dishonest for me to sit back and say that “all opinions are created equal” about this stuff. I think I’ve clearly articulated why that view is correct over the last few weeks.

    Ivan knows a *lot* about price action and teaches best practice trading.

    However his system building approach is fatally flawed, which is why none of his students are successful. None, zero, zip, and why Ivan himself is broke.

    I’m unwilling to sugar coat that simply because I learned good stuff from him. Better Grant peels the band aid off now, and I really do wish him every success.

    “A losing trader can do little to transform himself into a winning trader. A losing trader is not going to want to transform himself. That’s the kind of thing winning traders do.” Ed Seykota

  • Yoda

    Boy, how the almighty Ivan has fallen down. From genius to broke ass hobo.

  • BobbyLow

    You too! I’m glad you said something about NG. This was a case where I didn’t think it made any sense fundamentally but my lens said go long so I went long. Of course this stuff is called “Nutty Gas” for a reason so tomorrow might be a different story. But I’ll enjoy today because NG seems to be a good fit for me so far probably because I can be kinda nutty too. :)

  • Scott Phillips

    Keep banging on simplicity. Now I’ve been exposed to the systems of actual professionals, working in actual hedge funds and quant teams, I can see clearly that complexity is laziness.

    Whats my ideas for trading systems?

    – Trends tend to continue
    – Mean reversion off bollinger bands happens sometimes
    – Short squeezes are typically violent and fast

    You don’t have to go fancy, with esoteric theories.

  • Scott Phillips

    He’s a genius in his own way, a very smart man. Certainly at price action he knows everything for what that’s worth. An amusing parlour trick indeed.

    But the facts remain, his approach is incorrect. None of the systems I every built with his approach, nor any systems built by any of his students (they all wash up on my shore eventually) have any chance of working.

    And his stories about being an institutional trader don’t hold water when I think about them. I was trading his current state of the art system in 2009, which is unsophisticated compared to his current system, and was not just a slight negative edge but a dramatic negative edge.

    I traded it correctly and lost a lot of money doing so. The fault was mine for trusting a guru and trading a system without fully investigating it, but I can’t condone the fake guru on the mountain bullshit.

    His best student is Dudeplunger (who used to be here) who is actually a far better mechanical trader than myself, and I’m privileged to work with him.

    I’m quietly pissed off that I get a stream of people contacting me saying “I’m considering a mentorship with him, because he said he taught you everything you know, is that true?” Which I guess is partially true.

    And then he pops up here every few months to hang shit on me, and try and cadge a few students like a tick hanging off evilspeculator.

    I’m through being polite about it. I never mentioned to anyone how broke he is out of respect before.

    Professional traders make money from the markets. Professionals get paid, even street whores, which is why they are called “pros”.

    You shouldn’t learn from broke traders, is the moral of the story

  • Scott Phillips

    Take a look at my comment where I gave the rules for Seykota’s system in yesterday’s post.

    Pick any outlier move you like, any one at all, anything that qualifies as a black swan from the rise of bitcoin, to the collapse of crude, or any bubble popping in 2008.

    I absolutely guarantee Seykota’s system got every last one of those, and what’s more rode them a fair way to the beach.

    This is what I mean

  • Yoda

    Ha! that makes at least three of us. 😉
    Re. NG, I’ll take some position off the table either before of after Thursday EIA NG report depending on the price action by then.

  • http://evilspeculator.com Sir Mole III

    “I’m considering a mentorship with him, because he said he taught you everything you know, is that true?

    Complete bullshit mate – you are lightyears ahead of Ivan at this point. It’s no fucking contest – he’s not even in your league.

    Sorry Ivan but the truth shall set you free.

  • Yoda

    Your last sentence knocked it for six.

  • Yoda
  • Scott Phillips

    Outliers aren’t a bug but an inherent feature of markets. Throwing them out is like sticking your head in the sand.

    Why? Because we all have these crippling cognitive biases from the plesioctene. We don’t like to be wrong, we don’t like to change our minds, losing is more emotionally painful than winning, we want the safety of the herd.

    So when we are wrong, our fucked up primate wiring causes us to all panic in the same stupid ways, no different than a herd of antelope faced with a lion.

    In so many ways, trading is just another exercise in advanced primate social dynamics.

    Monkey want banana?

  • Scott Phillips

    Exactly so. Make or break time, and the subject of my next post.

    Look at that chart, and answer “Is it a trend?” You can make a case for a trend, but truthfully you aren’t quite sure, are you?

    Any sort of doubt probably means it is not a trend, and a market where sudden reversals and bullshit chop is the order of the day.

    I smell fuckery afoot in this market.

  • Scott Phillips

    We are both ahead of where we were because of continual reinvention and continuous learning.

  • BobbyLow

    I intend to “Keep it Simple” Scott. :) I think one of your posts or comments said something like if your system is robust then it has a good chance to put you in position to profit from an outlier event. I have gone back and forth from trading faster to longer time frames. Although I could not back test my hourly back as long as 10 or 15 years, I could however back test my daily over this period of time. One of the things that really blew me away is that prior to the Flash Crash of 2010, the market was already weak and I would have been short prior to May 6, 2010. The market was also weak prior to 9/11/2001 so I would have already been short as well.

    Now I know this is a lot of coulda, woulda, shoulda, but my back testing evidence does coincide with what you have been saying.

    But on the other side of coulda, woulda, shoulda, I wish the fuck I had never heard of Primary Wave 3 which was going to be the Grand Poo Ba of Primary Waves down. Of course this is not to be confused with Intermediate. Minor, Minute, Minuette, and Sub-Minuette Dominate Waves and all of the fucking Corrective A, B, and C Waves inbetween. My, my, didn’t EW appear to be the Golden Goose? It was sooooo complicated it had to work Right? Wrong. Instead of this Complicated Bloated Fucking Goose laying Golden Eggs, all it did was what all Geese do and that’s Shit all over the place including my trading accounts. :)

    I’ve been able to forgive myself for falling into the P 3 Trap. This was just part of an ongoing learning curve. I also know I wasn’t alone.

  • BobbyLow

    If I don’t get stopped out before the NG Report, I’ll hold through it and see what happens. Holding through the NG Report is similar to holding through the Crude Report and I realize that it can work both ways. Based on limited data, I believe there can be greater profitabilty over the longer run sitting tight rather than closing out before the report and possibly getting back in again.

    However, we have to trade in a way that is the best fit for our personalities. So in this particular case, there is no absolute right or wrong. Its just a trade. :)

  • Scott Phillips

    I also fell for the primary turd of a turd of a turd.

    I had strong feelings of shame when I filled out my tax return and claimed $1000 for cash I’d given to EWI for their “predictions”

    Pack of cunts

  • Mark Shinnick

    Yeah, so I’m short now my pilot positions for tza.

  • Mark Shinnick

    Yeah, seems to me that the more complexity is essentially the more derivative, or order of removal away from price itself….so damm dangerous.

  • Scott Phillips

    And insidious. A slippery slope indeed.

    “I’ve noticed it doesn’t work on xyz”

    “I’ve noticed that this happens after ABC”

  • sutluc

    How long have you been trading the mean reversion system?

  • sutluc

    I hear he charges enough that he shouldn’t be broke!

  • Scott Phillips

    He charges a lot, and in a weird way delivers a lot of value for what he charges. He will literally spend 4+ hours a day with his students for months on end.

    Like most of Ivan’s ex-students I am deeply conflicted about him. On one level he’s a total fraud, and he hasn’t traded successfully in the ENTIRE time I’ve known him, which is since 2002. On another level he is completely legit. He knows price action like very few people.

    The truth is somewhere in between, but the lack of objective results in his approach are because he doesn’t know how to build systems.

    If he did know how to build systems he would be fine. Or if you could add system building knowledge on top of what he teaches, you would be fine.

    Grant probably knows more than nearly everyone here, but has what all Ivan’s students suffer from, viewing things through the lens of Ivan. You have to get out and see how the people making actual money build their systems to see what a needlessly complicated Rube Goldberg machine system you were used to.

    I know Ivan posts impressive looking backtests from time to time here. Take it from me, they are all bullshit, and never ever match up to live trading. There is a reason why he’s never posted real results here.

    Ivan has one and only one priority in life, which is avoiding any kind of evidence that his life’s work isn’t what he cracks it up to be.

  • Dyellowflash

    Putting in a short on the Dax. For the past 3 trading sessions, on the hourly timeframe, every expansion of green candles got sold down and every contraction of green candles got sold down. Might be good for a day or two to hold some shorts until there is more evidence of either way.

  • Scott Phillips

    NEW POST