Tools being used by your trading competition

[VSntchr]

You know them personally and seen the results/rewards of their successful trading? and that's all they do? Or know some people on the internet who say that's what they do? Hmm I would say 5 - 10 years, more like 10 though.

Yes I know a couple of traders personally that have been successful over a 10yr+ period. There is also at least one ASF poster that made the transition from trader to investor after enough success. My point being that there are plenty of traders out there that are doing better than 'just getting by', at least in my own opinion.

I also know a lot more that have been successful over much shorter time frames (<3yrs) - so the indication that success over short periods is far more common has merit. I would, however, expect this to hold true in many ventures which require ongoing self-motivation and growth mindset. I also know many other business owners that were successful for a year or two before giving up (cafes, swimwear, imports, graphic design, etc etc...).

Part of retaining an edge in the market involves constantly adapting. Floor traders from the past had to adapt to electronic trading..the ones who were motivated to succeed did the work and made the transition, others probably didn't and moved on to something else. Perhaps electronic discretionary traders will have to adapt to incorporate more quantitative work into their process in order to retain edge going forward.

 

[howardbandy]

Greetings --

My posting was intended to show the extent to which artificial intelligence and machine learning is being used by large trading houses. I am surprised by the messages posted in response. They cover a wide range, and many imply denial. Let me make a few comments.

None of my comments are intended to be critical of individuals or their trading and investing techniques. If something works for you, ignore me and keep it up.

1. Some comments suggest that fundamental analysis is more important than quantitative / technical / statistical analysis.

In the 1990s I was hired by a company based in a southern US state. They wanted a stock selection and signal generation program that could be sold to individual investors / traders that used fundamental data for the stock selection portion. I was vice-president for research and in charge of the project. Years earlier -- late 1960s and early 1970s -- one of my projects as a graduate student had been a stock selection computer program, based on artificial intelligence, that worked. So I thought we might succeed. We tried everything we could think of, including analysis of a variety of corporate fillings. It was during this period that my analysis of the use of fundamental data crystallized. A recent version of that has been published several times, and is an appendix to the "Foundations" book. The paper can be downloaded from the book's website:
http://www.blueowlpress.com/wp-content/uploads/2016/10/FT-Fundamental-Analysis-Appendix-A.pdf

During that period, a professional colleague was working for a highly respected research organization that published (at a very high subscription rate) buy / hold/ sell recommendations. His mother lived in a retirement home in my community. On his regular visits to her, he stopped in my office and we talked about my project. His summary when I asked him "What works?" was "Nothing we have found. That is, nothing outside the board room."

My group could not find anything either, and the stock selection portion of that project was dropped.

2. The world's richest person uses buy and hold. I am assuming the reference is to Warren Buffett.

Mr. Buffett is as much the president of a conglomerate corporation as he is an investor. By his own assessment, he is not a trader. The price of the Buffett-led Berkshire Hathaway stocks (BRK-A and BRK-B) dropped over 50% from early 2008 to the lows in 2009. In my opinion, holding resources through losses that large is more a characteristic of a corporation than of an investor or a trader.

The 50% drawdown was recovered. In my opinion, the recovery in equities, bonds, and real estate from that "crisis" has been the result of low interest rates set by central banks. There is a very high risk that as interest rates rise, the majority of those gains in all three areas will be lost. We are already seeing some of the effect of rising interest rates on bonds.

3. Productivity gains will improve company profits and raise all boats.

Several political economists have pointed out that the "developed" countries benefited from recovery following world war II, which provided strong growth and rising values of all investments beginning about 1945. That increasing globalization has recently been spreading the effects throughout the world, and that we (the US, at least) should not expect strong growth in the 21st century.

Some of the gains in productivity are due to automation. Those profits accrue to stock holders, but not to workers. Investors may benefit, inequality may increase.

4. Some comments suggest that AI/ML is unnecessary -- that simple techniques work.

I was a senior research analyst at a commodity trading company (a hedge fund) in the 1990s. The company had been one of the pioneers in development and use of trend-following quantitative systems. Their specialty was breakouts -- buy new highs and other "turtle-like" techniques. We watched, literally day by day, as those techniques stopped working. In my opinion, they will never work again. Trends are shorter in duration and price movement. Systems that take counter-trend positions are quicker to fade the trends, breaking them into smaller pieces which are less easily identified and less profitable. That company returned all investor money and ceased operation.

But assume that some simple indicator does work today. Take Stephen Simmons comment about J. P. Morgan employing thousands of individuals to develop trading systems as literal and think through the implications. We know from many articles that research personnel are highly educated -- one-third or more have PhD degrees in scientific disciplines -- and highly compensated -- say $100,000 base salary on average. 1000 people at $100,000 per year is an annual salary cost of $100,000,000. Add office space, support staff, benefits, etc and the sum grows. Morgan will not build those departments and pay those costs unless the trading results are adequate to fund them.

A trading company does not need 1000 people and a department budget of several hundred million dollars to tell them to buy when the 5 day moving average rises up through the 20 day moving average.

Anyway -- thanks for listening,

Best regards, Howard

 

[CanOz]

Thanks Howard, great topic and fascinating discussion!

 

[jjbinks]

I think what howard is saying is true and inevitably becomes more true everyday.

I think we continue to trade because we feel that there a gaps left by the bigger players (maybe trades which are "too small" for them or for some other reason). My feeling is that the reason us small fries can trade is because the wins we make is different to the wins big guys trading hundreds of millions of dollars are try to achieve.

THe other thing which i think wil change the landscape is if neural networks gets implemented into trading. For those of you who follow artificial intelligence, you may be aware of how google developed a AI to beat the worlds greatest "go" player. My simple understanding was was that the computer was programmed to recognise patterns in game play and develop successful strategies. With this kind of technology i think discretionary trading could be simulated better. If any of you have played go and understand how complex it can be you will understand why I say this.


Anyway that's my 2c

Also if people are interested in learning pandas for python:
https://courses.edx.org/courses/course-v1:Microsoft+DAT210x+6T2016/info
Its a good starter course. (assumes basic python knowledge though)

 

[Gringotts Bank]

4. Some comments suggest that AI/ML is unnecessary -- that simple techniques work.

I was a senior research analyst at a commodity trading company (a hedge fund) in the 1990s. The company had been one of the pioneers in development and use of trend-following quantitative systems. Their specialty was breakouts -- buy new highs and other "turtle-like" techniques. We watched, literally day by day, as those techniques stopped working. In my opinion, they will never work again. Trends are shorter in duration and price movement. Systems that take counter-trend positions are quicker to fade the trends, breaking them into smaller pieces which are less easily identified and less profitable. That company returned all investor money and ceased operation.

But assume that some simple indicator does work today. Take Stephen Simmons comment about J. P. Morgan employing thousands of individuals to develop trading systems as literal and think through the implications. We know from many articles that research personnel are highly educated -- one-third or more have PhD degrees in scientific disciplines -- and highly compensated -- say $100,000 base salary on average. 1000 people at $100,000 per year is an annual salary cost of $100,000,000. Add office space, support staff, benefits, etc and the sum grows. Morgan will not build those departments and pay those costs unless the trading results are adequate to fund them.

I believe what you say about many edges eroding, but that doesn't mean you can't trade using a highly intuitive approach. You can bet there would have been some people at that company who would have had a sense of "I feel like this might not last, but I don't know why" well before the statistics showed up losses. They would have been well ahead of the curve.

In current day terms, highly intuitive traders may just 'feel' like they need to broaden their discretionary time frame, because it 'feels' safer. If you asked them to quantify that, they might give you some sentences that describe a general trend, but not necessarily be able to turn that into an equation.

So I think both approaches are viable. If I had to match a highly intuitive trader versus a machine I'd back human intuition every time. Such geniuses are rare, but they exist - we may even have a few here.

 

[Gringotts Bank]

To put it another way, the human brain is by far the greatest machine on earth. I believe a seasoned chartist (say 5-10 yrs experience) can look at a chart and know in a split second what's going to happen next. What gets in the way of accessing that knowledge is fear and greed. Everyone knows how easy it is to perform spectacularly well on a demo account.

Not to take anything away from those who can program machines at a high level. That's spectacular in its own way. I won't ever be able to compete with those guys in the future... hence the interest in improving my discretionary skills.

 

[minwa]

My posting was intended to show the extent to which artificial intelligence and machine learning is being used by large trading houses. I am surprised by the messages posted in response. They cover a wide range, and many imply denial. Let me make a few comments.

I don't see anyone denied that they are being used by LARGE TRADING HOUSES. Denials are of your claim that charts/longterm don't work for individuals anymore and will get eaten for lunch. That's the impression that I and others got from your first post.

4. Some comments suggest that AI/ML is unnecessary -- that simple techniques work.

I was a senior research analyst at a commodity trading company (a hedge fund) in the 1990s. The company had been one of the pioneers in development and use of trend-following quantitative systems. Their specialty was breakouts -- buy new highs and other "turtle-like" techniques. We watched, literally day by day, as those techniques stopped working. In my opinion, they will never work again. Trends are shorter in duration and price movement. Systems that take counter-trend positions are quicker to fade the trends, breaking them into smaller pieces which are less easily identified and less profitable. That company returned all investor money and ceased operation.

That system must've been short term fitted to rigid rules that worked well in that period. Ed Seykota says all mechanical systems expire, and he's probably right.

Dunn Capital is the most famous fund for break out trend following. His fund is 30 years+ and today is still alive and well.

Larry Williams won the trading contest in late 80's. 10 years later in late 90's his daughter won it again. Another 10 years later another of his student won again. Today I still use his principals. We read charts and some hold for long term. Core trading principals don't change.

We know from many articles that research personnel are highly educated -- one-third or more have PhD degrees in scientific disciplines -- and highly compensated -- say $100,000 base salary on average. 1000 people at $100,000 per year is an annual salary cost of $100,000,000. Add office space, support staff, benefits, etc and the sum grows. Morgan will not build those departments and pay those costs unless the trading results are adequate to fund them.

A trading company does not need 1000 people and a department budget of several hundred million dollars to tell them to buy when the 5 day moving average rises up through the 20 day moving average.

Completely agree - for a large trading firm. But most of individuals trading from our ADSL at home in our tiny accounts do not have to play the the same game as the large guys. They have to average in massive amounts of funds/orders. We get filled in an instant. We can go cash in an instant. We take a position into anything in an instant. It is the BEST advantage of the small guys.

Just because large funds are using all that doesn't necessarily mean we have to. Do you like the odds of going against a team of thousands of high IQ people with hardwares & softwares most of us can't even dream of to beat/mirror them in their game ? A few pure genius can probably do it..most of us can't.

Thanks for your response.

 

[minwa]

hot topic in the trading world of recent times.

HFT - an example of a trading fad that's seen its glory days gone.

 

[OmegaTrader]

Oh my have you really thought about this?



Buffett BUYS COMPANIES---all of the company.
Then transforms them and if you think he does this WITHOUT the input of a team of Quants then think again!



The world is run by Quants.

Aerospace
Aeronautics
Medicine
Technology
Engineering
Climate control and the lack of it
Mining
Energy production
Military

FINANCE

The point Howard (Captain Cook) is making is that all of those looking out at the vast sea in front of them
can rest assured that the world isn't flat and he knows as unlike those staring out at the sea in front of them
he has been there --- that's where he lives---he sails it.




Examples are all around you.
The problem is most are so blind they cannot see.
Just because you cant see it doesn't mean its not there doing exactly what its supposed to do for exactly the reason its supposed to and for exactly the people its meant to serve.

Ever been on a plane?
Seen a Bank make 10 Billion?
Driven over a bridge?
Heard of the name Zuckerberg?
Seen the growth of google?
Watched an invasion?

Yeh Quants rule the world.
The richest men in the world are surrounded by Quants
They employ 1000s of them.
----and pretty soon you'll be able to join them---even you Thingamiggy
There is a vast wave of Howard Bandies on the horizon.

I will be clear.

I am not saying Quant analysis is not useful or profitable by itself or with other indicators

I am not saying Quants will not eventually win or have not won.

I am not saying that Quant analysis is meshed with everyday life.

But what I am saying is that Buffet is not a Quant.

He does not use sophisticated algorithms or advanced computers.

Sure he uses data and figures, but I would not consider this to be a Quant.

First year university students learn DCF models and how to read balance sheets,

That is not being a Quant that is basic finance.

Right back at you!!!

Oh my have you really thought about this?


Investing in a Quant field does not make your investment strategy quantitative.

No disrespect to you

 

[tech/a]

Oh my have you really thought about this?

Yes.

 

[Wysiwyg]

Supply/demand and sentiment drive prices, not computer programs.

 

[tech/a]

Supply/demand and sentiment drive prices, not computer programs.

Wysi

How is it your missing the whole point here.
Its about data analysis
Machine learning of changes and anomalies in data.

Would you rather hand fly a plane all night over the Atlantic or set on Auto Pilot?
Jet engines propel planes not computers!

This is the next stage in financial analysis?

According to you then I should only need my Abacus?
Throw away my calculator and forget a PC---not needed.

You sound like a pigeon who's heard that the telephone is the next big thing in communication.

Its going to help everyone not be their demise!!

 

[Wysiwyg]

Wysi

How is it your missing the whole point here.

To the contrary again. I understand the I.T. era (in trading - data mining for patterns if you like) is here but the same conditions that drive prices have not changed. Trading a million times per day on a nano second turn around doesn't appeal to me.

 

[tech/a]

To the contrary again. I understand the I.T. era (in trading - data mining for patterns if you like) is here but the same conditions that drive prices have not changed. Trading a million times per day on a nano second turn around doesn't appeal to me.

Ok.
Its not about that either.

Ill leave it there.

 

[Wysiwyg]

Ok.
Its not about that either.

Ill leave it there.

No please elaborate. An EOD trade example maybe.

 

[tech/a]

Just a snippet of what's out there.

Not associated in anyway and not endorsing either.

https://www.quantopian.com/

 

[ThingyMajiggy]

View attachment 69083

HFT - an example of a trading fad that's seen its glory days gone.

Over-saturation of everyone trying to do the same thing when there's only a certain amount of milliseconds available to be exploited, and probably why the "herd" are all onto it now in forums etc. always lagging behind, just like in trading? I don't doubt for a second that HFT profits have dropped, I'm not really on either side in this discretionary vs HFT/algo/AI debate, but you go to any trading forum and you'll find an AI/Algo/HFT thread in a matter of seconds, like it's some eye opening holy grail.

It would be good to see this machine learning in action in trading, seems to be plenty of tutorials and the like on it all over the web, yet those people are still making tutorials so it obviously didn't do anything special for them.

I'm just yet to see a successful trader maintain that success over a long period without turning to investing, I think investing is a different story because some people can get on a good thing as far as a company goes etc. Maybe the trader doesn't need to be successful over a long time because he made so much in the short term

 

[tech/a]

Sam

Petes proven it can be done
What do you need a room full of people
Trading for 10 yrs plus all with audited
Results in profit.

You need capital more than most think if you
Want to trade for a living.
You need application
You need to be business orientated---not for everyone.

You need to be different.

I've met you
Why don't you trade for a second income as we discussed?
I showed you how to do it and offered help.----?

 

[ThingyMajiggy]

Sam

Petes proven it can be done
What do you need a room full of people
Trading for 10 yrs plus all with audited
Results in profit.

You need capital more than most think if you
Want to trade for a living.
You need application
You need to be business orientated---not for everyone.

You need to be different.

I've met you
Why don't you trade for a second income as we discussed?
I showed you how to do it and offered help.----?

Pete? Where's he and what's he doing?

I have traded as a second income and still do occasionally and trading has bought me some toys and holidays, doesn't mean I know what I'm doing or feel confident in how I go about it to be certain that yep, I can do this for the rest of my working life or until I'm floating in my yacht around Santorini.

But no, I don't need a room full of audited people, even you don't trade for a living, you have a successful business outside of trading that dominates your time, hence why the help/advice faded(along with the desire to not hound you constantly because I'm an idiot) and you're developing a quant platform/system/whatever that I assume you're going to sell and have even less of a reason to trade? Not having a dig, you've done extremely well but I doubt trading is your main focus with your business doing so well, which is fair enough!

As I said previously, I'm not saying it can't be done, quite the opposite, I hope like hell it can be as I would still love to do it, I just haven't seen anyone sustain it, even what I thought were some of the best traders I've seen, which then begs the question what chance has stupid old me got? I'm all for trading and wish I was the modern day Livermore(minus the two blowups and eventual suicide), but just going from what I've seen, it seems to have plateaued.

As others have mentioned they have seen guys doing well apparently, so that's awesome. Traders that are actually profitable are hard to meet/know so you're priviledged to know of these guys

But this is all off topic in here, PM or email me if you want to keep the discussion going tech, especially if it's about me, people here wouldn't care for that.

 

[skyQuake]

I'm just yet to see a successful trader maintain that success over a long period without turning to investing, I think investing is a different story because some people can get on a good thing as far as a company goes etc. Maybe the trader doesn't need to be successful over a long time because he made so much in the short term

If a trader is truly successful, they run into liquidity issues. They can then choose to go wide eg. employ same strats using algos across more stocks/more markets (maybe even layer on diff strats) or go deep eg. investing. I think most people mellow out with age and kids etc so they go the investing route