Corner of Berkshire & Fairfax Message Board

General Category => General Discussion => Topic started by: RuleNumberOne on November 09, 2019, 10:26:21 AM

Title: Are Renaissance Technologies just trend followers?
Post by: RuleNumberOne on November 09, 2019, 10:26:21 AM
From the book:

"In January 2000, Medallion made 10.5%. By March 2000, the fund was sitting on over $700 million of profits...Then came true trouble...The tech bubble burst on March 10....Medallion lost about $90 million in a single day in March; the next day it was $80 million more.

Medallion's losses now approached $300 million....Medallion trades about eight thousand stocks. There was no way they could quickly revamp the portfolio.

After several more all-nighters, a couple of researchers developed a theory about what was causing the problems: A once-trusted strategy was bleeding money. It was a rather simple strategy - if certain stocks rallied in previous weeks, Medallion's system had taught itself to buy more of the shares, under the assumption the surge would continue. For several years, this trending signal had worked, as the fund automatically bought Nasdaq shares that were racing still higher. Now the system's algorithms were instructing Medallion to buy more shares, even though a vicious bear market had begun."
Title: Re: Are Renaissance Technologies just trend followers?
Post by: RuleNumberOne on November 09, 2019, 10:35:29 AM
I think their returns just came from writing software for momentum trading. By automating trend following, they were able to do it more thoroughly than other hedge funds doing it the old-fashioned manual way.

I think it also allowed them to change directions very rapidly compared to the manual approach.

Which also means their returns must have gone down in recent years compared to the past as other automated trend-following funds came into existence.

Looks like they traded EVERY stock in the market. Out of the 8000 stocks they traded in 2000, I think 7000 would have prices moved by a big fund like Medallion/Renaissance alone. When other automated trend following funds entered who were also able to change directions instantaneously, their returns should have gone down.

It makes sense that 90% of the trading in the stock market is done by "algos".
Title: Re: Are Renaissance Technologies just trend followers?
Post by: RuleNumberOne on November 09, 2019, 06:52:18 PM
Greg Zuckerman, the author of the Jim Simons book says the people at Medallion believed the individual investor who did a buy-and-hold was not losing to Medallion, but instead it was other hedge funds that were on the losing end of Medallion trades.

Medallion made 98% in 2008. You needed a machine to make 98% in the 2008 rollercoaster. And I think it is the emotional individual investor who loses to the machines.


Title: Re: Are Renaissance Technologies just trend followers?
Post by: muscleman on November 09, 2019, 07:52:49 PM
From the book:

"In January 2000, Medallion made 10.5%. By March 2000, the fund was sitting on over $700 million of profits...Then came true trouble...The tech bubble burst on March 10....Medallion lost about $90 million in a single day in March; the next day it was $80 million more.

Medallion's losses now approached $300 million....Medallion trades about eight thousand stocks. There was no way they could quickly revamp the portfolio.

After several more all-nighters, a couple of researchers developed a theory about what was causing the problems: A once-trusted strategy was bleeding money. It was a rather simple strategy - if certain stocks rallied in previous weeks, Medallion's system had taught itself to buy more of the shares, under the assumption the surge would continue. For several years, this trending signal had worked, as the fund automatically bought Nasdaq shares that were racing still higher. Now the system's algorithms were instructing Medallion to buy more shares, even though a vicious bear market had begun."

Which book are  you referring to?
Title: Re: Are Renaissance Technologies just trend followers?
Post by: RuleNumberOne on November 09, 2019, 07:59:46 PM
The Man Who Solved the Market: How Jim Simons Launched the Quant Revolution
by Gregory Zuckerman

From the book:

"In January 2000, Medallion made 10.5%. By March 2000, the fund was sitting on over $700 million of profits...Then came true trouble...The tech bubble burst on March 10....Medallion lost about $90 million in a single day in March; the next day it was $80 million more.

Medallion's losses now approached $300 million....Medallion trades about eight thousand stocks. There was no way they could quickly revamp the portfolio.

After several more all-nighters, a couple of researchers developed a theory about what was causing the problems: A once-trusted strategy was bleeding money. It was a rather simple strategy - if certain stocks rallied in previous weeks, Medallion's system had taught itself to buy more of the shares, under the assumption the surge would continue. For several years, this trending signal had worked, as the fund automatically bought Nasdaq shares that were racing still higher. Now the system's algorithms were instructing Medallion to buy more shares, even though a vicious bear market had begun."

Which book are  you referring to?
Title: Re: Are Renaissance Technologies just trend followers?
Post by: muscleman on November 09, 2019, 10:42:45 PM
Thank you!
Title: Re: Are Renaissance Technologies just trend followers?
Post by: cherzeca on November 10, 2019, 02:34:16 PM
need to read new book, but the best performing quants are arb traders not momentum traders.  see ed thrope, a man for all markets
Title: Re: Are Renaissance Technologies just trend followers?
Post by: cameronfen on November 10, 2019, 04:55:55 PM
need to read new book, but the best performing quants are arb traders not momentum traders.  see ed thrope, a man for all markets

I may be wrong but I don't think arb trading scales all that well, which I think all the big names are trend followers, or at least even the big firms that started off arb trading jave branched into trend following. 
Title: Re: Are Renaissance Technologies just trend followers?
Post by: muscleman on November 10, 2019, 07:53:52 PM
The Man Who Solved the Market: How Jim Simons Launched the Quant Revolution
by Gregory Zuckerman

From the book:

"In January 2000, Medallion made 10.5%. By March 2000, the fund was sitting on over $700 million of profits...Then came true trouble...The tech bubble burst on March 10....Medallion lost about $90 million in a single day in March; the next day it was $80 million more.

Medallion's losses now approached $300 million....Medallion trades about eight thousand stocks. There was no way they could quickly revamp the portfolio.

After several more all-nighters, a couple of researchers developed a theory about what was causing the problems: A once-trusted strategy was bleeding money. It was a rather simple strategy - if certain stocks rallied in previous weeks, Medallion's system had taught itself to buy more of the shares, under the assumption the surge would continue. For several years, this trending signal had worked, as the fund automatically bought Nasdaq shares that were racing still higher. Now the system's algorithms were instructing Medallion to buy more shares, even though a vicious bear market had begun."

Which book are  you referring to?


Thank you! I just picked up the book. I'll read it.
I have a feeling that the fact that they started to publicly talk about their strategies is a hint that their strategies stopped working that well, which seems to be indeed the case for their new institutional equity fund.  :)


Title: Re: Are Renaissance Technologies just trend followers?
Post by: Liberty on November 11, 2019, 10:28:43 AM
Nothing these guys do is "just" something. Otherwise everybody else would do it.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: LC on November 11, 2019, 12:31:28 PM
Nothing these guys do is "just" something. Otherwise everybody else would do it.
Seriously. These guys are better than Buffett:

(https://digital.hbs.edu/platform-digit/wp-content/uploads/sites/2/2017/02/Picture3.png)
Title: Re: Are Renaissance Technologies just trend followers?
Post by: Gregmal on November 11, 2019, 12:35:17 PM
Well, theyre not traditional value investors, so I'd gander many here would say that their returns dont count or something...
Title: Re: Are Renaissance Technologies just trend followers?
Post by: Spekulatius on November 11, 2019, 12:42:41 PM
Itís interesting to think about who you are up against, if you try short term or daytrading.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: crastogi on November 11, 2019, 12:54:56 PM
Well, theyre not traditional value investors, so I'd gander many here would say that their returns dont count or something...

I would take those returns any day  ;)
Title: Re: Are Renaissance Technologies just trend followers?
Post by: LC on November 11, 2019, 01:00:18 PM
Itís interesting to think about who you are up against, if you try short term or daytrading.

Even longer term. It is publicly known that Rentech uses value/fundamental strategies.

Simple 15 minute example:

1) Obtain credit ratings for all companies - proxy for "moat"
2) Determine trailing 1, 3, 5 year earnings/cash flows, growth rates
3) Make some exclusion/treatment rules to throw out highly volatile companies or correct for idiosyncratic events
4) Use 1)2) to build a fundamental model +/- 15% of normalized PEs

and trade around that.

You then combine this with other models in the firm which are estimating heatmaps of the market - i.e. expected cash inflows or outflows or some other metrics. So your  +15% band expands during periods of expected inflows and your -15% band contracts during outflows.

Now you've built a model to automate the fundamental investor.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: Liberty on November 11, 2019, 01:06:57 PM
Nothing these guys do is "just" something. Otherwise everybody else would do it.
Seriously. These guys are better than Buffett:

(https://digital.hbs.edu/platform-digit/wp-content/uploads/sites/2/2017/02/Picture3.png)

That's after charging 44% fees or something, yes. But they also capped their funds at a much smaller amount of capital than Buffett... It's all very different, but in the end, both are making tons of money and at the top of their fields.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: LC on November 11, 2019, 01:18:03 PM
Very true. Rentech manages something like 100B so quite heavy but not all in Medallion.

One of the other fascinating things is the human component.

Berkshire is the product of two people. Simons/Rentech took a group of incredibly smart mathematicians, programmers, etc. (and all the neurosis that come with that) and got them to work and function together. That is one hell of a feat if you ask me.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: Munger_Disciple on November 11, 2019, 01:34:21 PM
I just started reading Zuckerman's book. So far very interesting. There is a table in the appendix showing Medallion fund results & they are stunning. Medallion however is not the only fund Rentech manages. I have the following comments on Rentech performance:

1. The first 10 years of Rentech results (1977-1987) which were not so good were ignored in the performance table (this table starts in 1988).

2. Medallion fund is an internal fund. Only founders & employees can invest in it and no outsiders are allowed. They use it as an incentive to hire talent. From the book it looks like Simons kicked out investors and even friends out of this fund. So Rentech's best ideas go to this fund. Given that they don't manage outside money in Medallion, I don't understand why Medallion has massive fees. Who is earning these fees?

3. In addition to the $10B Medallion fund, Rentech also manages $55B for outside investors and no performance data for these funds is shown in the book. One has to look at the aggregate performance of all assets under management, not just a portion of it to get a better picture of Rentech capabilities. I heard that the results of the outside money are not that good (perhaps someone more knowledgeable can comment on this), certainly not as good as the Medallion results.

4. If I recall correctly, Zuckerman said in an interview Medallion is levered 10 times?


Title: Re: Are Renaissance Technologies just trend followers?
Post by: wescobrk on November 11, 2019, 08:26:33 PM
I'm reading the book and Medallion was managing $5 billion I believe up to 2005 then it went up to $10 billion but Simons doesn't allow anything beyond $10 billion as it can't scale beyond that.
I've heard the returns on all the other funds are average-ish (certainly less than Buffett).
It hasn't been reported Buffett is being judged on a market cap of $500 billion whereas Simmons is managing $10 billion (he distributes the profits every year).
How the hell can you compare $10 billion to $500 billion? Plus, Buffett's is after tax and Simmons is pretax plus all of Simmons gains are short term (the irs ruled that way as he only holds for a few days although Simmons did appeal it).
Title: Re: Are Renaissance Technologies just trend followers?
Post by: sleepydragon on November 11, 2019, 08:58:01 PM
There are many different ways to make money in the market. But itís really hard to scale with size. Ren is doing very high frequency trading, resulted in very high sharpe but size canít be scaled up to more than a certain percentage of a stock ADV
Title: Re: Are Renaissance Technologies just trend followers?
Post by: cameronfen on November 13, 2019, 06:00:27 PM
There are many different ways to make money in the market. But itís really hard to scale with size. Ren is doing very high frequency trading, resulted in very high sharpe but size canít be scaled up to more than a certain percentage of a stock ADV

Yes but the idea is you trade every single stock, every commodity, every currency pair and derivative contracts.  After all a neural network that can follow one trend has an easier time of generalizing to other assets.  With that you can manage a lot of assets.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: johnhuber on November 14, 2019, 08:04:34 AM
The other thing to consider about Renaissance is the massive tax bill that LP's paid each year. I know much of their investor base became institutions that in some cases don't pay tax, but if you are a tax paying investor, your results were still incredible, but much, much closer to owning BRK. In fact, if you were a high net worth individual living in NYC, I would bet that your after tax returns would have been higher just owning BRK during its prime three decades than owning Renaissance during their run.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: sleepydragon on November 14, 2019, 08:30:48 AM
There are many different ways to make money in the market. But itís really hard to scale with size. Ren is doing very high frequency trading, resulted in very high sharpe but size canít be scaled up to more than a certain percentage of a stock ADV

Yes but the idea is you trade every single stock, every commodity, every currency pair and derivative contracts.  After all a neural network that can follow one trend has an easier time of generalizing to other assets.  With that you can manage a lot of assets.

Making money through stats arb doesnít mean they use neural network or even any sophisticated AI. The neural network is actually a pretty new thing. Any alpha/ideas employed by hedge fund human traders can be automated by Stats arb. But itís not easy to apply most ideas in equity to other assets.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: sleepydragon on November 14, 2019, 08:33:12 AM
The other thing to consider about Renaissance is the massive tax bill that LP's paid each year. I know much of their investor base became institutions that in some cases don't pay tax, but if you are a tax paying investor, your results were still incredible, but much, much closer to owning BRK. In fact, if you were a high net worth individual living in NYC, I would bet that your after tax returns would have been higher just owning BRK during its prime three decades than owning Renaissance during their run.

If all the BRK investors invest in the Renís internal fund, it will start posting loses immediately. Like WEB said he could do 50% return in a year if he manages small money.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: RuleNumberOne on November 14, 2019, 09:40:48 AM
Buffett's principles will always remain valid. No doubt he would win a stock-picking contest with any Renaissance employee even today.

But Renaissance is like the Google of the investing world. Someone who has read all the newspapers and encyclopedias of the last 100 years can beat any Google employee in a trivia contest. But they can't beat the search engine.

The typical hedge-fund portfolio consists of FAAMG, V, MA, PYPL, BKNG. Whereas the Renaissance 13-F looks completely inhuman, hundreds of positions entered and exited without any regard to market cap. If they were made to file a 13-F every week, we could get a better idea of what the Renaissance machine does.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: cameronfen on November 14, 2019, 09:50:58 AM
There are many different ways to make money in the market. But itís really hard to scale with size. Ren is doing very high frequency trading, resulted in very high sharpe but size canít be scaled up to more than a certain percentage of a stock ADV

Yes but the idea is you trade every single stock, every commodity, every currency pair and derivative contracts.  After all a neural network that can follow one trend has an easier time of generalizing to other assets.  With that you can manage a lot of assets.

Making money through stats arb doesnít mean they use neural network or even any sophisticated AI. The neural network is actually a pretty new thing. Any alpha/ideas employed by hedge fund human traders can be automated by Stats arb. But itís not easy to apply most ideas in equity to other assets.

AFAIK rentech is not stat arb typically (although at this point they probably do a bit of everything).  I think stat arb is not just programming hedge fund ideas.  It is but is grounded in mathematical or at least statistically valid arbitrage opportunities ie actual situations where the same asset has different prices.  Rentech is mainly a trend following quant shop, which means they use techniques to identify then follow trends.  While you donít have to use cutting edge machine learning to identify those trends, most of the big quant shops have teams that apply machine learning and deep learning to these problems.  I know for sure that Rentech hires machine learning phds.  Iím not saying generalizing a statistical model is easy, but itís much easier if you have one model the follows trends to extend that to other assets and even asset classes.  While they might pick up fundamentals, to some extent when you are trading based on trend a lot of that is probably picking up subtle behavioral reactions to price movement and that generalized across any asset class. 
Title: Re: Are Renaissance Technologies just trend followers?
Post by: RuleNumberOne on November 15, 2019, 09:30:32 AM
Good points cameronfen. Another item to add is conviction - machines have a lot more compared to humans. Six of Renaissance's top 10 positions right now are drug stocks.

A "fundamentals-based" hedge-fund builds its portfolio around the hedge-fund favorites - FAAMG, V, MA. The only stock in that list that appears in the Renaissance top 10 is FB at #10.

The Renaissance people are betting their own money on models that they themselves built. Who would think of betting their money on drug stocks in an election year with Liz and Bernie tweeting threats all the time.

Even when "fundamentals-based" investors jump into drug stocks, they come out with a Valeant as 10-30% of their portfolio. Hard to say "fundamentals-based" can in any way be superior to Renaissance's machines.

There are many different ways to make money in the market. But itís really hard to scale with size. Ren is doing very high frequency trading, resulted in very high sharpe but size canít be scaled up to more than a certain percentage of a stock ADV

Yes but the idea is you trade every single stock, every commodity, every currency pair and derivative contracts.  After all a neural network that can follow one trend has an easier time of generalizing to other assets.  With that you can manage a lot of assets.

Making money through stats arb doesnít mean they use neural network or even any sophisticated AI. The neural network is actually a pretty new thing. Any alpha/ideas employed by hedge fund human traders can be automated by Stats arb. But itís not easy to apply most ideas in equity to other assets.

AFAIK rentech is not stat arb typically (although at this point they probably do a bit of everything).  I think stat arb is not just programming hedge fund ideas.  It is but is grounded in mathematical or at least statistically valid arbitrage opportunities ie actual situations where the same asset has different prices.  Rentech is mainly a trend following quant shop, which means they use techniques to identify then follow trends.  While you donít have to use cutting edge machine learning to identify those trends, most of the big quant shops have teams that apply machine learning and deep learning to these problems.  I know for sure that Rentech hires machine learning phds.  Iím not saying generalizing a statistical model is easy, but itís much easier if you have one model the follows trends to extend that to other assets and even asset classes.  While they might pick up fundamentals, to some extent when you are trading based on trend a lot of that is probably picking up subtle behavioral reactions to price movement and that generalized across any asset class.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: LC on November 15, 2019, 09:53:45 AM
Most fundamental investors (myself included) have zero industry specific knowledge in healthcare r&d. The ones that do hire specialists (baupost), and their portfolio looks much different than bill ackman and valeant.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: RuleNumberOne on November 15, 2019, 10:03:12 AM
Owning drug stocks with Liz and Bernie hovering is very painful. Bernie caused a lot of pain to drug stock investors in 2016.

Humans don't want that pain. Machines don't feel the pain and Renaissance is content to let the machine do its thing.

When it came to Valeant, it was not just Bill Ackman. The list of Valeant luminaries included Lou Simpson (12% of portfolio), Sequoia Fund (> 30% of portfolio), Glenn Greenberg (36% of portfolio), Wally Weitz. They probably derived conviction from each other.


Most fundamental investors (myself included) have zero industry specific knowledge in healthcare r&d. The ones that do hire specialists (baupost), and their portfolio looks much different than bill ackman and valeant.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: Spekulatius on November 15, 2019, 06:04:28 PM
Owning drug stocks with Liz and Bernie hovering is very painful. Bernie caused a lot of pain to drug stock investors in 2016.

Humans don't want that pain. Machines don't feel the pain and Renaissance is content to let the machine do its thing.

When it came to Valeant, it was not just Bill Ackman. The list of Valeant luminaries included Lou Simpson (12% of portfolio), Sequoia Fund (> 30% of portfolio), Glenn Greenberg (36% of portfolio), Wally Weitz. They probably derived conviction from each other.

Valeant was easy to avoid - lots of red flags: high debt levels, rollup with exponential growth, unconventional business model, promotional ď OutsiderĒ management, heavy promotion of non-GAAP accounting.

People got greedy and were neglecting the downside because so much money was made with this stock. If you just focus on downside, you never would have gotten into Valeant to begin with.


Most fundamental investors (myself included) have zero industry specific knowledge in healthcare r&d. The ones that do hire specialists (baupost), and their portfolio looks much different than bill ackman and valeant.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: opihiman2 on November 15, 2019, 06:18:53 PM
The new book is great, and it's illuminating.  Sad to see how much errors there are in this thread about RenTech. 

1) Medallion hasn't been publicly available for a LONG TIME.  Their institutional funds are and have very public performance data.  However, the institutional fund performance #'s are nothing to write home about.

2) Medallion is limited to around $10B, I think.  They disburse all gains above and beyond to stakeholders.  Even at this size, their performance #'s are unreal.

3) Buffett doesn't even come close to Medallion #'s.  He wishes he could.  Even if he were trading with a small AUM, I HIGHLY doubt young Buffett would come close to Medallion Fund #'s

4) Medallion isn't really stat arb.  Not even close.  They did do some stat arb before, but not with equities.  They were pretty good in commodities and debt investments.  But, what really ramped up their #'s since late 90's was pattern recognition software.  They hired two guys from IBM from their speech recognition division who finally was able to get Medallion a significant edge in equities.  As a side note, one of the guys is a far right conservative who likely helped Trump win the election. 

5) They use leverage but not LTCM levels of leverage.  They can scale in and out of leverage fairly easily. 

6) Jim Simons gets way too much credit for the success of Medallion.  His main contribution was probably the idea of using quantitative models for trading and team gathering. 

7) They are definitely not fundamental investor types.  At least not since the early 90's.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: RuleNumberOne on November 15, 2019, 06:56:50 PM
Edit: the links don't work. Need to Google for author-name followed by "dblp"

Robert Mercer's papers are here: https://dblp.uni-trier.de/pers/hd/m/Mercer:Robert_L=

David Magerman's papers are here: https://dblp.org/pers/hd/m/Magerman:David_M=

No doubt these ideas were used at Medallion

"Jelinek wrote, "The performance of the Renaissance fund is legendary, but I have no idea whether any methods we pioneered at IBM have ever been used. My former colleagues will not tell me: theirs is a very hush-hush operation!"

If they didn't use any of it, they would have told their lead co-author Jelinek.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: RuleNumberOne on November 15, 2019, 07:30:10 PM
I know very little about neural networks, but the speech recognition research that happened in IBM in the 1990s was antiquated long ago. But suppose we start with what kind of queries can neural networks answer that would be relevant to stock trading?

Fill-in-the-blanks.

Given a sequence of winners and losers for training the model, the neural network could predict missing winners or losers. E.g. given the set of today's winners, which stocks are missing from the list... 5000 stock tickers per day over 10 years would be a total of 12.5 million words for training.

They would still need to add fundamental data as input to justify why a stock flips from reliable winner to loser and vice versa.

If multiple stocks are missing from today's stock market winners, there are likely no outliers, as opposed to a single stock missing from the list of winners...
Title: Re: Are Renaissance Technologies just trend followers?
Post by: RuleNumberOne on November 15, 2019, 07:52:06 PM
I think they also use some sentiment analysis of analyst reports or news articles for drug companies. Drug approvals in the case of NVO and VRTX, merger in the case of BMY and CELG.

The appearance of CMG could be explained by detecting an outlier in the sequence of winners.

I think the publication of this book will result in a lot of competitors. They have shown it works and there are a lot of smart people out there who can replicate these results - who never tried before because they had no idea such techniques would work.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: cameronfen on November 15, 2019, 09:05:27 PM
Edit: the links don't work. Need to Google for author-name followed by "dblp"

Robert Mercer's papers are here: https://dblp.uni-trier.de/pers/hd/m/Mercer:Robert_L=

David Magerman's papers are here: https://dblp.org/pers/hd/m/Magerman:David_M=

No doubt these ideas were used at Medallion

"Jelinek wrote, "The performance of the Renaissance fund is legendary, but I have no idea whether any methods we pioneered at IBM have ever been used. My former colleagues will not tell me: theirs is a very hush-hush operation!"

If they didn't use any of it, they would have told their lead co-author Jelinek.

His research at least as of 2019 is predominately neural network based.  Transformers, LSTMs with attention that like what is hot now and what was hot 3 years ago in language models with neural networks.  He has some other stuff but I am sure his work is mainly Neural Network based.  I bet by now there is no way Rentech are not using transformers to forecast these time series based on his expertise and what works.  It is likely he ran a giant transformer with like maybe 1billion+ parameters on the time series of every single financial asset and with maybe slight modification is running the same transformer to predict movement in those given assets.  If I had to guess you can copy the structure of the largest transformer, megaton-ln, from here: https://blog.exxactcorp.com/megatron-lm-unleashed-nvidias-transformer-megatraon-lm-is-the-nlp-model-ever-trained/ , steal the transformer base architecture from here: https://github.com/tensorflow/tensor2tensor and with little coding knowledge but 2 or 3 million dollars to spend on AWS you can likely replicate 50% of there returns just by training it on every possible asset class time series.  My guess is thatís the core of the model and all the ml smarts in the world gets only somewhat marginal improvements from there. 
Title: Re: Are Renaissance Technologies just trend followers?
Post by: RuleNumberOne on November 15, 2019, 09:42:14 PM
Robert L. Mercer (the Renaissance guy) last published a research paper in 1995.

Robert E. Mercer is a professor somewhere and he is still publishing research papers.

Yeah, it is very easy now to run the latest algorithms on any amount of data compared to the 1990s. Lot of machine learning packages available.

But the key is what inputs to feed - how do you structure the inputs.

Edit: the links don't work. Need to Google for author-name followed by "dblp"

Robert Mercer's papers are here: https://dblp.uni-trier.de/pers/hd/m/Mercer:Robert_L=

David Magerman's papers are here: https://dblp.org/pers/hd/m/Magerman:David_M=

No doubt these ideas were used at Medallion

"Jelinek wrote, "The performance of the Renaissance fund is legendary, but I have no idea whether any methods we pioneered at IBM have ever been used. My former colleagues will not tell me: theirs is a very hush-hush operation!"

If they didn't use any of it, they would have told their lead co-author Jelinek.

His research at least as of 2019 is predominately neural network based.  Transformers, LSTMs with attention that like what is hot now and what was hot 3 years ago in language models with neural networks.  He has some other stuff but I am sure his work is mainly Neural Network based.  I bet by now there is no way Rentech are not using transformers to forecast these time series based on his expertise and what works.  It is likely he ran a giant transformer with like maybe 1billion+ parameters on the time series of every single financial asset and with maybe slight modification is running the same transformer to predict movement in those given assets.  If I had to guess you can copy the structure of the largest transformer, megaton-ln, from here: https://blog.exxactcorp.com/megatron-lm-unleashed-nvidias-transformer-megatraon-lm-is-the-nlp-model-ever-trained/ , steal the transformer base architecture from here: https://github.com/tensorflow/tensor2tensor and with little coding knowledge but 2 or 3 million dollars to spend on AWS you can likely replicate 50% of there returns just by training it on every possible asset class time series.  My guess is thatís the core of the model and all the ml smarts in the world gets only somewhat marginal improvements from there.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: cameronfen on November 15, 2019, 09:51:40 PM
Robert L. Mercer (the Renaissance guy) last published a research paper in 1995.

Robert E. Mercer is a professor somewhere and he is still publishing research papers.

Yeah, it is very easy now to run the latest algorithms on any amount of data compared to the 1990s. Lot of machine learning packages available.

But the key is what inputs to feed - how do you structure the inputs.

Edit: the links don't work. Need to Google for author-name followed by "dblp"

Robert Mercer's papers are here: https://dblp.uni-trier.de/pers/hd/m/Mercer:Robert_L=

David Magerman's papers are here: https://dblp.org/pers/hd/m/Magerman:David_M=

No doubt these ideas were used at Medallion

"Jelinek wrote, "The performance of the Renaissance fund is legendary, but I have no idea whether any methods we pioneered at IBM have ever been used. My former colleagues will not tell me: theirs is a very hush-hush operation!"

If they didn't use any of it, they would have told their lead co-author Jelinek.

His research at least as of 2019 is predominately neural network based.  Transformers, LSTMs with attention that like what is hot now and what was hot 3 years ago in language models with neural networks.  He has some other stuff but I am sure his work is mainly Neural Network based.  I bet by now there is no way Rentech are not using transformers to forecast these time series based on his expertise and what works.  It is likely he ran a giant transformer with like maybe 1billion+ parameters on the time series of every single financial asset and with maybe slight modification is running the same transformer to predict movement in those given assets.  If I had to guess you can copy the structure of the largest transformer, megaton-ln, from here: https://blog.exxactcorp.com/megatron-lm-unleashed-nvidias-transformer-megatraon-lm-is-the-nlp-model-ever-trained/ , steal the transformer base architecture from here: https://github.com/tensorflow/tensor2tensor and with little coding knowledge but 2 or 3 million dollars to spend on AWS you can likely replicate 50% of there returns just by training it on every possible asset class time series.  My guess is thatís the core of the model and all the ml smarts in the world gets only somewhat marginal improvements from there.

Oh interesting.  Strange both are in NLP.  Also maybe should have checked because I was surprised a 70 year old is both recently a CEO as well as publishing papers as well as running a Koch style political funding arm.  Either way before I think 90% prob base model is Transformer.  Now probably 80%.  None of his stuff has anything to do with neural networks from a cursory look, which is unsurprising as ANN only got hot 2015.  Still, Iíd be surprised if anything could outperform a core transformer model (megatron-ln) trained on basically every asset time series. 
Title: Re: Are Renaissance Technologies just trend followers?
Post by: RuleNumberOne on November 16, 2019, 07:19:36 PM
Until I read the book I thought quant traders didn't make money. It was an eye-opener. But it seems there have been a lot of people copying Renaissance over the last few years. Shouldn't the advantages that quants have get competed away?

WorldQuant manages money for or is owned by Millennium management (the same firm that two Renaissance people defected to as described in the book).

Citadel and Two Sigma are hiring computer science grads from universities and creating a campus environment.

https://www.bloomberg.com/news/articles/2017-03-06/citadel-joins-two-sigma-chasing-quants-in-campus-recruiting-push

"Two Sigma will take over ďThe Bridge,Ē a space on the new Cornell Tech campus on Roosevelt Island in New York, where engineers and entrepreneurs will work.

The hedge fund staff will collaborate with Cornell students and professors on machine learning and data science projects, creating a pipeline of academic talent to the firm. Job candidates will put on virtual-reality glasses to watch a video that explains how the hedge fund sees the world awash in data.

The students -- handpicked from 400 applicants -- are competing in a datathon hosted by the $26 billion hedge fund Citadel. Ken Griffinís firm is upping the ante in the industryís chase for data scientists and engineers, hosting 18 competitions at universities across the U.S., Britain and Ireland this year. The prize in the final data championship: $100,000.

Igor Tulchinsky, the founder of WorldQuant, is pitching a perk that breaks the tradition of hedge-fund secrecy. The $5 billion firm is hiring at least 15 teams of quant managers for its Accelerator platform, offering them the right to keep their intellectual property. The quant hedge fund has also opened more than 20 offices in 15 countries, including emerging markets like Russia and Romania, to find engineers. Talent is distributed around the globe, Tulchinsky said at the Milken conference, ďbut opportunity is not.Ē"
Title: Re: Are Renaissance Technologies just trend followers?
Post by: fareastwarriors on April 17, 2020, 02:59:27 PM
Renaissance hedge fund reportedly having one of its best years ever


https://www.cnbc.com/2020/04/17/renaissance-hedge-fund-reportedly-having-one-of-its-best-years-ever.html (https://www.cnbc.com/2020/04/17/renaissance-hedge-fund-reportedly-having-one-of-its-best-years-ever.html)
Title: Re: Are Renaissance Technologies just trend followers?
Post by: bennycx on April 17, 2020, 08:47:19 PM
Looking at their pnl profile, they should be doing market making (agency trading), similar to investment banks but hidden in a hedge fund without all the compliance and operational costs.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: Gregmal on June 12, 2020, 01:07:33 PM
https://www.ft.com/content/6bd17811-3205-454e-89e4-953dce6b4dfe

So their "employee only" fund does 60% a year...but their "rest of the people" fund, does this...

https://www.ft.com/content/6bd17811-3205-454e-89e4-953dce6b4dfe
Title: Re: Are Renaissance Technologies just trend followers?
Post by: frank87 on June 12, 2020, 01:10:17 PM
https://www.ft.com/content/6bd17811-3205-454e-89e4-953dce6b4dfe

So their "employee only" fund does 60% a year...but their "rest of the people" fund, does this...

https://www.ft.com/content/6bd17811-3205-454e-89e4-953dce6b4dfe

The Medallion fund doesn't do equities I believe and has been deliberately kept small to keep the high returns going. Their marketed funds have not been as successful due to size and different asset classes that they're involved in.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: CorpRaider on June 12, 2020, 06:18:17 PM
Based on their -20% and my own freaking whipsaws in an account where I try and implement a TF strategy....they might just be trend followers.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: given2invest on June 12, 2020, 07:49:23 PM
https://www.ft.com/content/6bd17811-3205-454e-89e4-953dce6b4dfe

So their "employee only" fund does 60% a year...but their "rest of the people" fund, does this...

https://www.ft.com/content/6bd17811-3205-454e-89e4-953dce6b4dfe

Yah, it's completely different strategies.  Medallion is TRULY the greatest investment vehicle of all time. 
Title: Re: Are Renaissance Technologies just trend followers?
Post by: given2invest on June 12, 2020, 07:52:13 PM
https://www.ft.com/content/6bd17811-3205-454e-89e4-953dce6b4dfe

So their "employee only" fund does 60% a year...but their "rest of the people" fund, does this...

https://www.ft.com/content/6bd17811-3205-454e-89e4-953dce6b4dfe

The Medallion fund doesn't do equities I believe and has been deliberately kept small to keep the high returns going. Their marketed funds have not been as successful due to size and different asset classes that they're involved in.

Not true, Medallion does whatever Medallion wants to do.  I'm sure most of it is equities.  And "small" is $5b+ year in the fund returning 40-50% year after year, if not greater.   Yes, they return all the excess capital annually, but that's still a lot of capital for those kind of returns.  Amazing.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: frank87 on June 12, 2020, 08:01:29 PM
https://www.ft.com/content/6bd17811-3205-454e-89e4-953dce6b4dfe

So their "employee only" fund does 60% a year...but their "rest of the people" fund, does this...

https://www.ft.com/content/6bd17811-3205-454e-89e4-953dce6b4dfe

The Medallion fund doesn't do equities I believe and has been deliberately kept small to keep the high returns going. Their marketed funds have not been as successful due to size and different asset classes that they're involved in.

Not true, Medallion does whatever Medallion wants to do.  I'm sure most of it is equities.  And "small" is $5b+ year in the fund returning 40-50% year after year, if not greater.   Yes, they return all the excess capital annually, but that's still a lot of capital for those kind of returns.  Amazing.

I recall from reading the new book written on Jim Simon that Medallion's bread and butter was not equities; in fact, they had historically struggled to build profitable models on equities. A reason why Medallion pays out so much is that they've found it comparably difficult to reliably generate returns by trading new asset classes.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: Spekulatius on June 14, 2020, 05:01:44 AM
https://www.ft.com/content/6bd17811-3205-454e-89e4-953dce6b4dfe

So their "employee only" fund does 60% a year...but their "rest of the people" fund, does this...

https://www.ft.com/content/6bd17811-3205-454e-89e4-953dce6b4dfe

The Medallion fund doesn't do equities I believe and has been deliberately kept small to keep the high returns going. Their marketed funds have not been as successful due to size and different asset classes that they're involved in.

Not true, Medallion does whatever Medallion wants to do.  I'm sure most of it is equities.  And "small" is $5b+ year in the fund returning 40-50% year after year, if not greater.   Yes, they return all the excess capital annually, but that's still a lot of capital for those kind of returns.  Amazing.

I recall from reading the new book written on Jim Simon that Medallion's bread and butter was not equities; in fact, they had historically struggled to build profitable models on equities. A reason why Medallion pays out so much is that they've found it comparably difficult to reliably generate returns by trading new asset classes.

According the book, they struggled in equities for a long time and then achieved a breakthrough, which allowed them to scale up to their current size of $10B.

I m sure in the current mayhem in the stock markets, they make out like bandits this year.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: D33pV4lue on June 16, 2020, 08:28:20 AM
I tried looking for an article on Medallion fund but haven't found it. I think it came out last year in case anyone knows what I am talking about they can post it. From my memory, the article explained how the Medallion fund operates (vaguely as much of it is proprietary) much like a casino, placing millions of small trades every day on both sides. That way market moves are somewhat irrelevant and they take a daily vig. Investments never last longer than 2 weeks.
Title: Re: Are Renaissance Technologies just trend followers?
Post by: CorpRaider on June 16, 2020, 12:40:21 PM
Based on their -20% and my own freaking whipsaws in an account where I try and implement a TF strategy....they might just be trend followers.

Feeling better about this now.   ;D