Futures Arbitrage

[donaldkagan 10]

I am curious as to whether any members of this forum have used pair trading methodology in the futures market. I have used statistical arbitrage to great success with equities, and my limited backtesting seems to suggest that futures offer an attractive opportunity.

 

Thanks for your time,

 

D.K.

[waveslider 10]

are you talking about spreading between contract months?

or between two different markets?

[donaldkagan 10]

Between different markets. Gold and platinum for instance. Anything that has clear historical correlation and exhibits mean reversion.

[Kiwi 16]

I've thought about this donald but wouldn't you want to make sure that there was causation as well as correlation. Otherwise you risk a sophisticated curve fit.

 

I suppose you could also look cutouts for situations where a trend develops and reversion fails.

[donaldkagan 10]

Certainly when pair trading it is critical to make sure that the instruments are linked in some way beyond mere price action. A pair that I have traded very profitably for a long time is

PBR / PBR.A. It's quite clear why these two stocks would show correlation overtime.

After I create a basket of stocks from similar industries I further filter for obvious fundamental issues, mergers etc, I then use a combination of correlation and covariance to finalize the selection.

I'm not sure why the same process wouldn't work with futures. I need to think about how contract expiration would impact the overall system.

[UrmaBlume 10]

Welcome Donald.

 

There is indeed considerable statistical arb pair trading in the futures markets.

 

Our bread and butter is tracking such trade. Nice to see some real quant talk for a change. By far the vast majority of members/posters here are unable to correctly and precisely define the statistical arbitrage in an alpha neutral strategy that uses mean reversion to trade equity pairs. For sure a very select few can - but not many.

 

We do considerable work tracking traders who operate alpha neutral mean reversion methodologies in the statistical arb of pair trading in equity index futures.

 

At the micro level where the amplitudes of departure from the mean of the pair price more resembles a hum than a spike you can easily spot the commercial, auto-executed, mean reversion trades by viewing indicators of the intensity of commercial trade.

 

The chart below shows such spikes. You can see that there were out of sequence spikes in all 3 major US equity futures at precisely the same time. That indicator is further discussed here

 

 

 

[FulcrumTrader 10]

Running my "accordion" trade entry and management method, I have worked a few ES LONG and DAX SHORT trades the past few days at various times.....there has been some good set ups in the past few days with the decreased volatility.

 

There was two good trades today in the ES I had entered with collapsing time between trades and well above rolling ten day average order flow rates (while tracking commercials order flow activities).

[donaldkagan 10]

Thanks for the welcome Urma, I tend to agree with you regarding the paucity of traders who have a solid grasp of stat arb. I have had many a frustrating conversation with professional traders who like to ask "why don't you just trade one side of the pair?"

 

I found your chart to be very interesting, although I'm sure it's a gross simplification and perhaps fundamentally wrong, that indicator seems as though it's a highly granular realtime record of open interest.

 

Have you had any experience with a macro arbitrage strategy with futures? Are there any instrument specific challenges that wouldn't be found in equities?

[TradeRunner 10]

By far the vast majority of members/posters here are unable to correctly and precisely define the statistical arbitrage in an alpha neutral strategy that uses mean reversion to trade equity pairs. For sure a very select few can - but not many.

 

Hi Urma

 

You are so right and it’s funny because only the other day I was thinking the same thing. No wonder so many fail.

 

By the way did you see this post by Don Miller: Don Miller Trading Journal: Monday Notes - MATD, KISS, & More

 

That guy is such a loser! Can you believe he sometimes trades with just a laptop? Unbelievable, personally I think he is fraud.

 

Anyway I've got to go. I'm trying to decide on my trade station setup. Currently I only have dual monitors and as you know that's just totally inadequate for a professional trader. I’m thinking 10 monitors would be ok, but I'm sure I could make more if I just plump for the 16 now. What do you think?

 

Best wishes.

 

 

TradeRunner

[UrmaBlume 10]

Thanks for the welcome Urma, I tend to agree with you regarding the paucity of traders who have a solid grasp of stat arb. I have had many a frustrating conversation with professional traders who like to ask "why don't you just trade one side of the pair?" I found your chart to be very interesting, although I'm sure it's a gross simplification and perhaps fundamentally wrong, that indicator seems as though it's a highly granular realtime record of open interest.Have you had any experience with a macro arbitrage strategy with futures? Are there any instrument specific challenges that wouldn't be found in equities?

 

The specific challenge is also the opportunity in that the leverage is bigger by several orders of magnitude.

 

What this forum lacks in depth of content is more than made up by how friendly and open MOST members really are. The only credible higher frequency quants that I have talked to from this board are members who never post.

 

Just a bit of research of the same kind that found the equity pairs that served you so well will serve you well here too. Try it, you'll like it, and, again, welcome aboard.

 

cheers

 

UB

[UrmaBlume 10]

Hi UrmaYou are so right and it’s funny because only the other day I was thinking the same thing. No wonder so many fail.

By the way did you see this post by Don Miller: Don Miller Trading Journal: Monday Notes - MATD, KISS, & MoreThat guy is such a loser! Can you believe he sometimes trades with just a laptop? Unbelievable, personally I think he is fraud.Anyway I've got to go. I'm trying to decide on my trade station setup. Currently I only have dual monitors and as you know that's just totally inadequate for a professional trader. I’m thinking 10 monitors would be ok, but I'm sure I could make more if I just plump for the 16 now. What do you think?Best wishes.TradeRunner

 

No I missed Mr Miller's post and every other post made by him and others of his ilk. Believe it of not but most here are still involved with topics like profiles, candles, VSA & Wyckoff with little or no idea of the new era of smart data consolidation and visualization that is fast approaching.

 

As to the desktops - below is a shot of the desks we use for our in-house traders. This particular shot is of my own desk. We operate a mini-pit with 4 more setups just like it.

 

As to the number of monitors we find 8 is as much as most people can handle.

 

While to us Information = Equity is a mantra, we are working on the consolidation of different graphs into the HUD.

 

 

cheers

 

UB

[james_gsx 16]

No I missed Mr Miller's post and every other post made by him and others of his ilk. Believe it of not but most here are still involved with topics like profiles, candles, VSA & Wyckoff with little or no idea of the new era of smart data consolidation and visualization that is fast approaching.

 

 

:beer:

 

I completely agree, it took a few years for me to realize this (well, more so the last 6 months).

[DugDug 10]

Urma - I always gave you a little more credit - but to say

"Believe it of not but most here are still involved with topics like profiles, candles, VSA & Wyckoff with little or no idea of the new era of smart data consolidation and visualization that is fast approaching." comes across as pretty condescending.

Especially given that most peoples trading problems is not in the visualisation input provided by a computer screen.

[UrmaBlume 10]

Urma - I always gave you a little more credit - but to say

"Believe it of not but most here are still involved with topics like profiles, candles, VSA & Wyckoff with little or no idea of the new era of smart data consolidation and visualization that is fast approaching." comes across as pretty condescending.

Especially given that most peoples trading problems is not in the visualisation input provided by a computer screen.

 

You are right. The real problem with bars, profiles, candles, VSA, market delta & Wyckoff is the lack of intelligent processing before the data is visualized.

 

Condescending or not, most members here are strictly retail, long term losers as traders and less than 5% of the members are even remotely familiar with state of the art trade decision support technologies and methods as practiced by the likes of Goldman Sachs and Renaissance Capital.

 

Mention topics like candles, VSA, market profiles, market delta and Wyckoff to any group of up to standard quants you get laughed out of the room and the profile, candles, VSA, market delta and Wyckoff fanatics don't even know the difference.

 

My posts are not directed at the lowest common denominator here and that's my

[MidKnight 12]

UB,

 

So what if they get laughed out of the room. Quant trading isn't the only way to make money. Are you implying that it is?

 

With kind regards,

MK

[Dinerotrader 10]

Condescending or not, most members here are strictly retail, long term losers ....

 

My posts are not directed at the lowest common denominator here and that's my

 

You'll find with a little intelligent thought before posting that it is quite easy to participate in the forum giving useful knowledge to those interested without also coming across as condescending. However if you are trying to be condescending, because of some emotional motivation, you have succeeded. Hopefully this thread gets back to discussing the topic at hand instead of what "quants" think about other trading methods.

[FulcrumTrader 10]

UB,

 

So what if they get laughed out of the room. Quant trading isn't the only way to make money. Are you implying that it is?

 

With kind regards,

MK

 

No sir.....the "Smart Guys" or quants of the world lost BILLIONS in these past years due to fractured mentalities (that their MATH skills and trade systems were unable to overcome). In the end, regardless of the strategies developed many quant groups and institutional level players got KILLED by their mentalities. The second a human being or group of human beings think they are better than another group, they are on the universal path to self destruction. Thoughts of invincibility due to ego or perceived systems of perfection, leave the managers of such groups psychologically vacant from what could ultimately protect them from themselves.

 

Well developed trade systems or methodologies still need honorable and psychologically mature humans to operate those systems for continued potential profitability. Those who think they have the BEST, still need to THINK the best, to have any CHANCE at the best.....I have seen this all throughout my life in aviation and trading. Honorable and mature mentalities, very well aligned with the realities of their own capabilities, can frequently defeat the supposed "Smart Guys" in the room.....day after day.

[UrmaBlume 10]

UB,

 

So what if they get laughed out of the room. Quant trading isn't the only way to make money. Are you implying that it is?

 

With kind regards,

MK

 

I am not implying anything, I am stating that most traders here do not make money and that they trade and espouse methodologies that the people who do make most of the money from these markets laugh at.

Edited March 12, 2010 by UrmaBlume

[UrmaBlume 10]

No sir.....the "Smart Guys" or quants of the world lost BILLIONS in these past years due to fractured mentalities (that their MATH skills and trade systems were unable to overcome). In the end, regardless of the strategies developed many quant groups and institutional level players got KILLED by their mentalities. The second a human being or group of human beings think they are better than another group, they are on the universal path to self destruction. Thoughts of invincibility due to ego or perceived systems of perfection, leave the managers of such groups psychologically vacant from what could ultimately protect them from themselves.Well developed trade systems or methodologies still need honorable and psychologically mature humans to operate those systems for continued potential profitability. Those who think they have the BEST, still need to THINK the best, to have any CHANCE at the best.....I have seen this all throughout my life in aviation and trading. Honorable and mature mentalities, very well aligned with the realities of their own capabilities, can frequently defeat the supposed "Smart Guys" in the room.....day after day.

 

 

Chris,

 

You are correct some quants lost a lot of money but not the ones at Goldman or Renaissance. More than 60% of all equity trading in the US is done by quant derived methodologies such as the stat arb of mean reversion pair trading which is the original topic of this thread.

 

It is the best of those that make the most of the money from these markets, they are the "Smart Guys" in the room. Some of them are members here and of those that are members here that I have talked to, none of them ever post and none of them use market delta or consider market delta or VSA, Wyckoff......

 

Some of those successful, highly educated quants that are members here and never post have joined me in creating and registering UrmaBlume T1, LLC which is a private hybrid cross of a prop shop and a hedge fund.

 

All due respect Chris as I know you are a great proponent of market delta and if it makes you money - right on.

 

We, however, operate on the principle that recent advances in intelligent data mining, data processing, data visualization and higher frequency automated systems have moved beyond such methods of trade decision support as candles, profiles, market delta, etc.

 

cheers

 

UB

[Cory2679 11]

We, however, operate on the principle that recent advances in intelligent data mining, data processing, data visualization and higher frequency automated systems have moved beyond such methods of trade decision support as candles, profiles, market delta, etc.

 

UB,

 

Just curious...would you classify support and resistance on a chart in the same category as "candles, profiles, market delta, etc."?

 

Cory

[UrmaBlume 10]

UB,

 

Just curious...would you classify support and resistance on a chart in the same category as "candles, profiles, market delta, etc."?

 

Cory

 

Hi Cory - Yes I would.

 

cheers

 

UB

[FulcrumTrader 10]

Chris,

 

You are correct some quants lost a lot of money but not the ones at Goldman or Renaissance. More than 60% of all equity trading in the US is done by quant derived methodologies such as the stat arb of mean reversion pair trading which is the original topic of this thread.

 

It is the best of those that make the most of the money from these markets, they are the "Smart Guys" in the room. Some of them are members here and of those that are members here that I have talked to, none of them ever post and none of them use market delta or consider market delta or VSA, Wyckoff......

 

Some of those successful, highly educated quants that are members here and never post have joined me in creating and registering UrmaBlume T1, LLC which is a private hybrid cross of a prop shop and a hedge fund.

 

All due respect Chris as I know you are a great proponent of market delta and if it makes you money - right on.

 

We, however, operate on the principle that recent advances in intelligent data mining, data processing, data visualization and higher frequency automated systems have moved beyond such methods of trade decision support as candles, profiles, market delta, etc.

 

cheers

 

UB

 

Yes, I do agree with the level of capabilities that some of these groups have and how they use their developed abilities to create advantages for themselves in the markets each day. I also know how various equity member firms of the CME track order flow, volume distributions, and open interest in futures products for their trading desk ops. I think digging into the granular information within the traded order flow is a smart direction to go for developing trading systems (which I have done myself with fund systems data experts/fund systems programmers).

 

It is very interesting how Commercial trading entities, at the very sophisticated level, can track order flow precisely to the point as to measure when resting inventory in a specific area of price is about to be fully capitulated (and used as an exit for winning position covering order flow). It is also very fascinating to now see the visualization and complete difference of dramatic order flow acceleration from capitulation versus Commercials initiated trade activity. The difference in order flow rate frequencies can now be visualized through proper data flow analysis, to see the separate stories all being told simultaneously within even 1 second of order flow time.......yes, I agree this is all very good information to have.

 

All this micro level analysis is just fine for the potential when moment to enter a trade, but I still find there are additional very robust methods of analyzing traded order flow distributions to know higher probability where areas of price to look to enter trades. Blending the where locations of price to enter trades with the precise moment of when to initiate trade is the advantage in my opinion. But heck, all those smart quant guys think they are the only ones who are smart in the room.....and I love the fact they think that way.

 

 

Enjoy the Vegas weather and keep up the great work!

 

Christopher

[DugDug 10]

Urma -Dont forget - Goldmans is a market making firm according to Lloyd..... it might actually possibly loose money from its trading decisions as opposed to its market making???

additionally I think this (old) article is clearly wrong.....given the two people you mentioned.

 

Quakes In Quantitative Trading: Nothing New Under the Financial Sun -- Seeking Alpha

 

If I recall goldmans was bailed out....???? And it probably only missed worse by being better business managers and by being able to grab a chair and sit down just prior to the music stopping. Will we every really know?

 

However while there are lots of ways to make money..... I think any one particular group that laughs at another just shows arrogance.... never a particularly appealing trait.

Particularly when I think you would find that a lot of people from some quant/broking/trading houses actually loose money and become part of the 95% of losers when they branch out on their own. It makes you wonder how many people rely on the order flow, low transactions costs, leverage, free funding and other spreads offered by the larger firms. A lot of retail guys leave and go under due to poor capitalisation, loss of interest, lack of time, education etc. Surely as a quant you must be able to look at the 95% of traders quote and realise that its a lie, lie and dammn statistic to be able to draw conclusions from. Maybe you are one of the smartest around, thats fine - some of the best traders I have seen are not that smart, and thats probably their strength and they know it. These guys know that sometimes luck plays a part and that they dont know everything. You should be greatful there are people that make you look good.

Yes there are exceptions, however I just took exception to (and always have and always will) your comment. I think given the reaction a few others did also....Thats all. There are plenty of dogmatic views on these sites as well - the cult of some indicator, so I cant disagree with you there.

I am probably old school in that I believe that the most expensive words in the English language are "this time its different".

Edited March 12, 2010 by DugDug

[james_gsx 16]

If I recall goldmans was bailed out....???? And it probably only missed worse by being better business managers and by being able to grab a chair and sit down just prior to the music stopping. Will we every really know?

 

I think the term "bailed out" is slightly over used. In reality, almost every bank in the country was bailed out whether they needed the money or not. A lot of Goldman's potential landmines were CDS with AIG. Overall, from the slight (meaning don't take my word 100%) they did a much better job managing their toxic debt before everything blew up.

 

But nonetheless, Goldman continues to make money from their trading floor. Bailed out or not, they are obviously doing something right. And let's be honest, would you think twice if GS offered you a job and told you their trading was made up of VSA, candlestick analysis, and market profile? You'd probably walk out laughing too. Eventually, technical analysis will probably (if it already hasn't) become a thing of the past - much like pretending to gain a fundamental edge by reading the WSJ every morning. People still do that, which tells me retail traders will be studying technical analysis for many years to come and trying to find their edge (some definitely will find an edge).

 

As far as UB being condescending, I think that's just part of the business. It's not nice, but this business isn't nice. Let's face reality, in games like poker your objective is to win, and you do so by taking your opponents money - same thing with trading.

 

With all that said, I'm glad this is a civil forum and we can have meaningful conversations regardless of how different ones opinion may be. There are some very intelligent traders who have gained their edge through wyckoff, VSA, etc, and I hope they continue to share their knowledge with others. But at the same time, we should all face the reality that this game is rapidly changing (already has), and the more aware you are, the better prepared you will be regardless of your style of trading.

[subterfuge 10]

Eventually, technical analysis will probably (if it already hasn't) become a thing of the past

 

Interesting. Its been around for a long time and despite TA seeming to get a bad rep among trading forums at the moment (funny how these topics work in cycles), I know its making money for some. I guess anything's possible though, and maybe your right in that it could become a 'thing of the past'.

 

Although, isn't UB's trading just technical analysis aswell? Hasn't a chunk of his method already been re-created by some guys on this very forum for use with ninjatrader in the other thread? I think that sometimes people dont want to be lumped in with the rest of the crowd, maybe associated with gambling, and kid themselves that they are seperate.

 

I dont doubt that Goldman and the like are playing a different game though. I imagine alot of their stuff is through market making etc. You just cant compare them with ANY retail trader, no matter how special one considers themselves. If they can profit from bid-ask spreads all day and have super computers scanning the market for tiny inefficienies faster than anyone else and rake in the money, they dont need to worry about candlestick formations! Its not even 'trading' in some peoples defiinition of the word.

 

As for NonTA strategies that the retail trader CAN employ, well thats also the other issue. Any alternative offered is always so vague from posters who claim not to use it.

 

Cheers.

Sub