Tag Archives: RenTec

Inside the money machine: RenTec HFT

Inside the money machine: RenTec HFT

This is the closest you will ever get inside this highly secretive HFT firm

Sixty miles east of Wall Street, a spit of land shaped like a whale’s tail separates Long Island Sound and Conscience Bay. The mansions here, with their long, gated driveways and million-dollar views, are part of a hamlet called Old Field. Locals have another name for these moneyed lanes: the Renaissance Riviera.

Go here the extra details.
Also, the schedule of the Interactive Brokers API workshop has been posted for Quant Elite members.

The schedule can be found here which starts on Tuesday NOV 22. That is today at 3PN EDT!

My ELITE member can log in here

Thanks Bryan

NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!

RenTec uses NLP wanna be seduction artists aka PUA for billion dollar trading secrets?

RenTec uses NLP wanna be seduction artists aka PUA for billion dollar trading secrets?

I got this response after I sent this:

Early Rentec HFT secret on machine learning?

hah you ought to read about his model train debacle.

The fact that they hire NLP guys is not secret, its a shame there isn’t more info on how this is deployed though.

NLP? You mean those bozo wannabe so-call seduction artists? …

 

Sorry give me a minute. Actually give me an hour as I compose myself after that heart  attack of laughter.

I think that is a little different from writing software for voice recognition.

The other question about not being released. Just re-read the last link above as there is tonnes of topics released especially as PHD research papers.

Join my FREE newsletter if you want to continue earning how I algo trade with automation

NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!

Early Rentec HFT secret on machine learning?

Early Rentec HFT secrets on machine learning?

Have I found the potential secrets of what makes Renaissance Technologies billions of dollars. If so it revolves around computer linguistics which leads into modern machine learning. It all comes from their co-CEO from Robert Mercer.

 

Check out this history of how I found out about this person

 

Check out my resources of his early research from his days of IBM Watson research lab

Demo of working Python script to identify stock pair to arbitrage

 

I have just posted probably of one the most powerful Python scripts yet but I’ve written. This can scan any HOT market sector of your choosing to pull down Yahoo Finance data to calculate a long and short arbitrage opportunity. The funny thing in this video is it will show 100% of any random market sectors that I think have potential growth for an arbitrage opportunity.

 

Check out this video here

 

Now can you imagine if I unleash this into my automated trading system. Well think again! I will be committing this script as part of my entire arbitrage trading system. It can also be used for market data trading signals. They can work also for any region in the world which will also work on stocks, ETF, mutual funds, or indices. It can also be very flexible to your needs. This is the power of controlling your own source code. Honestly I hope you see the benefit of it.

 

As a result, this has already been posted to all my Quant Elite Members.

 

You can get immediate asked to this now! Go here for it

 

Learn more about this membership here

 

If you’re ultimately happy with what I send you, you may want to check out my annual special deal that I have going on right now. Many people think it is a deal of the century so check it out here

 

Thanks for reading

 

Bryan

 

PS. Don’t forget I am intending to run a entire series of live seminars on this entire system in coming weeks. This will be an extra benefit of joining my membership.

 

NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!

Early Rentec HFT secrets on machine learning?

Early Rentec HFT secrets on machine learning?

After posting about Robert Mercer of RenTech, I decided to dig for any juicy early potential research before he co-founded with James Simmons. This was the first article:

Meet the HFT RenTech programmer funding Ted Cruz

I can conclude that this person studied computer linguistics in applying voice recognition for machine learning. It is still considered one of the hardest applications when it comes machine learning. It sounds like he is beyond Godlike genius who walks on water.

Next came these:

He worked at IBM Research at IBM T.J. Watson Research Center : http://www.aclweb.org/anthology/J93-2003

 

Some research:

The state transition probabilities are set to be uniform. The traditional HMM is extended to allow a broader range of mapping configurations. Specifically, the null transition is used to represent skipping a state without consuming any observations. The skilled artisan will be familiar with the null transition from Lalit Bahl, Frederick Jelinek, and Robert Mercer, A Maximum likelihood approach to continuous speech recognition, IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. PAMI-5, No. 2, 1983, Pages 179-190; nevertheless, this Bahl et al reference is expressly incorporated herein by its entirety for all purposes. This allows one-to-null mapping. The null state is introduced so it can emit those observations without any correspondence states. This allows null-to-one mapping. The combination of null transition and null state allows many-to-many and many-to-one configurations as well. In an exemplary embodiment, the valid state transition is constrained to be from left to right with self loop, and with a maximum jump of three states as well as a null state and a null transition. Other embodiments could use other approaches; for example, the maximum jump could have another value such as four or five (or any other suitable value).

http://www.google.com/patents/US9176936

 

Slide 4

MT Summit IX Two parts –Panel Discussion Have we found the Holy Grail? –At the TMI-92 Conference in Montreal, Robert Mercer, one of the leading researchers on the IBM Candide project, provocatively asserted that “rationalist methods in MT will be on the scrapheap five years from now.” –Although Candide performed surprisingly well in the DARPA competition organized in the mid 1990’s, it did not actually surpass SYSTRAN. –At this year’s NIST competition, on the other hand, statistical MT (SMT) systems similar to Candide did outperform all the participating commercial off-the-shelf systems, according to the NIST score. –Paper J. Hutchins: Has machine translation improved? Some historical comparisons.

http://slideplayer.com/slide/8763491/

Brown, P.; J. Cocke, S. Della Pietra, V. Della Pietra, F. Jelinek, R, Mercer and P. Roossin (1988). “A statistical approach to language translation”. In Dénes Vargha, ed. Coling 88: Proceedings of the 12th conference on Computational linguistics, volume 1. Budapest: John Von Neumann society for computing sciences. pp. 71–76. doi:10.3115/991635.991651. ISBN 963-8431-56-3.

https://en.m.wikipedia.org/wiki/Frederick_Jelinek

Cool stuff from above:

http://www.aclweb.org/anthology/C/C88/C88-1016.pdf

http://dl.acm.org/citation.cfm?doid=991635.991651

http://www.ee.columbia.edu/~sfchang/course/svia-F03/papers/brown-machine-translate-93.pdf

BINGO!  This is is him:

Robert L. Mercer now is co-CEO of Renaissance Technologies.

https://www.aclweb.org/website/node/437

He attended this:

ICTAI ’96 Proceedings of the 8th International Conference on Tools with Artificial Intelligence http://dl.acm.org/citation.cfm?id=853584

His research has lead into other research papers like:

https://books.google.ca/books?id=wxL3uMGA1P8C&pg=PA55&lpg=PA55&dq=computational+linguistics+mercer&source=bl&ots=Un6YG8H4y6&sig=wlMqM0q0ZwZ6RzDg91g4xBauMrU&hl=en&sa=X&ved=0ahUKEwjPsd6pzbrKAhVGnoMKHfMJAcM4ChDoAQgYMAA#v=onepage&q=computational%20linguistics%20mercer&f=false

http://www.mitpressjournals.org/doi/pdf/10.1162/coli.2006.32.4.527

Read a personal comment he posted here: http://www.linuxforums.org/articles/why-ubuntu-got-it-all-wrong_241.html

Is thie same Dr Robert Mercer?  Does not look like it but sort of a coincidence

He seems to work at Western University in London On http://www.csd.uwo.ca/faculty/mercer/

http://ir.lib.uwo.ca/cgi/viewcontent.cgi?article=1794&context=etd

http://www.mitpressjournals.org/doi/pdf/10.1162/COLI_r_00102

http://ir.lib.uwo.ca/cgi/viewcontent.cgi?article=1794&context=etd

He seems to work at Western University in London On

Join my FREE newsletter to learn more about our digging into Rentec’s secrets 

 

NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!

More on most profitable in HFT among market making, event driven and stat arb? C++ vs C# vs Matlab vs Java and RenTec low latency

 

More on most profitable in HFT among market making, event driven and stat arb? C++ vs C# vs Matlab vs Java and RenTec low latency

 

there were discussion about c++ or matlab and java/c#. Everybody accepted that matlab is powerful to solve issues of numeric and statistic, etc. But when they use it in HFT situation, it’s recognized very slow. Then some people thought c++ was better and others thought a combination of matlab and java or c# could get speedier. I thought many were doubtful about connectivity between the two. A few were successful and said they used their own one for HFT. What do you think of this discussion?

 

 

==

could you please expand the concept of predatory algorithms?
Is it just normal bid offer size manipulation that you are talking about?

 

==

About statarb there is a problem of decreasing profitability over time as more and more players do the same. I am talking about plain simple pair trading (any asset class) not more complex relationships with fundamentals.

 

==

http://cyborgtrading.com/institutional/app/files/media/brochures/anti_gaming_for_tsx_market%20Makers.pdf

 

—

MATLAB is great for developing and algo and testing In my experience they are powerful yet do not go hand in hand with HFT. If you have something you feel works, get it developed in another environment. Which environment? Well, it all depends on what you are trying to accomplish. If a program is written by a highly skilled C++ programmer (and I mean HIGHLY skilled), then yes it can be extremely fast. But is it scalable? How does it work on one processor vs 30 processors? How long will development take? How easily can you modify it? You need to consider all these things before giving a proper answer.

We program with C# in a .NET environment because it is extremely fast, highly scalable and what would take a good programmer 3 months in C++, takes us days to do the same thing because Microsoft has already pre-built a lot in C#. Everything in C++ has to be built from the ground up. We also have a PHD student working on a project that will prove F# is a far better language to scale algorithms with.

If you can’t win, change the rules of the game.

I hope this makes some sense!

 

—

thanks for information. I did not know that F# is that better.

—

it could be the case that the profitability of stat arb is decreasing. It’s a rat race. You have to always optimize parameters as mentioned that the ability to change your parameters to tweak your algorithms real time is crucial. If your watching asset classes be more widened, you could find another arbitrage opportunities, i.g. stocks and FX, stocks and bonds, etc.

 

—

A colleague used to work at RenTec. From what I gathered, they use a blend of market making combined with predictive algos. So when they don’t have an edge in predicting price they act like market maker, going for ticks. However, when they get a “predictive” signal, then they take directional exposure.
Some more facts…they are the largest user of Mini SP contract by a huge margin. Two russian ex employees quit and tried to start their own fund. Jim Simons hired lawyers to stop them. I never found out if they ultimately did, but considering they Russian I’d bet they eventually did. The annual research budget for RenTec is 200-300million. One ex employee described some of RenTec strategies as borderline “software hacking”.
RenTec holds the patent for parts of code that is used for some execution software.

Getco,tradebot is just brute force. They make more money because they have lower latency. That’s almost all of their game.

RenTec is light years ahead of them. They have slower connections but still outrade.

 

—

great comment! I would have never guessed RenTec is behind in the latency game.

BTW, what do you mean by borderline “software hacking”?

Also if they hold patents, then they must be publicly listed on the US patent website. Would be interesting to look them up…

 

—

I wouldn’t say RenTec is behind in latency game, they just don’t solely rely on low latency unlike the others. When you have a predicitive edge over everyone else, you don’t have to rely as much on brute speed. RenTec staff is still composed of mainly researchers not just programmers and IT staff. That pretty much says it all.

The ex employees said “software hacking”. They could just be angry, but who knows. Nothing would surprise me.

They still ahead of everyone else, no matter how you slice it.

The real takeaway is that there have been other shops with multi milion budgets and staff that never made it. It proves that it’s half art, half science.

The original article started here:

https://quantlabs.net/blog/2011/11/which-do-you-think-is-the-most-profitable-in-hft-among-market-making-event-driven-and-stat-arb/

 

NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!