Is this not a parody, making a joke about how sensitive to supervision "unsupervised" learning methods are?
Unsupervised machine learning with basket clusters
31–39 of 39 posts
Re: Unsupervised machine learning with basket clusters
#32This is systematic semi-blind guessing at what other people will guess in the future are good investments. It sprays investment capital equally at companies that are not in any way equivalent. Hypothetically, just because two companies both have names that begin with "Z" and sell product on Amazon, that is not an investment thesis for treating them alike. Treating them alike is a recipe for misallocation of capital, in the long run, which is what it seems sometimes we have in this economy in spades.
Re: Unsupervised machine learning with basket clusters
#33Earlier quoted context omitted.
That is a rather large accusation. Can you restate that as something constructive or helpful to the conversation?
Do you understand investing at all? People have been attempting to "beat the market" for decades and nobody has been successful. There is always the "reversion to the mean" issue in every case. People with algorithms think they are beating the market then something changes and their algorithm no longer works. Except for Renaissance--they have consistently been beating the market, or so it appears. Does that help?
I work at a hedge fund. I may not write the trading models, but I'd like to think I'm not totally ignorant.
Re: Unsupervised machine learning with basket clusters
#34Earlier quoted context omitted.
That is a rather large accusation. Can you restate that as something constructive or helpful to the conversation?
I didn't interpret it as an accusation. I interpreted it as he wrote: a suspicion that something other than RT's algorithms is a non trivial contributor to their success. He gave an example of insider trading, but it could be something else ranging from the equally sinister lying about outcomes (e.g. by creative accounting of what counts as a return) to the less sinister better access or timing to information anybody…
They, and other hedge funds, apparently classify their earnings in a way the IRS objects to.
http://www.reuters.com/article/usa-irs-hedgefunds-idUSL3N0ZP...
Re: Unsupervised machine learning with basket clusters
#35Is this not a parody, making a joke about how sensitive to supervision "unsupervised" learning methods are?
If it's not a parody, it's one of the most unintentionally hilarious things involving data I have ever seen presented.
To anyone who takes this seriously: I have a price of butter in Bangladesh indicator which works REALLY WELL on the S&P500.
Re: Unsupervised machine learning with basket clusters
#36Earlier quoted context omitted.
Do you understand investing at all? People have been attempting to "beat the market" for decades and nobody has been successful. There is always the "reversion to the mean" issue in every case. People with algorithms think they are beating the market then something changes and their algorithm no longer works. Except for Renaissance--they have consistently been beating the market, or so it appears. Does that help?
I work at a hedge fund. I may not write the trading models, but I'd like to think I'm not totally ignorant.
So does your hedge fund beat the market every year like clockwork or do you have losses sometimes?
Re: Unsupervised machine learning with basket clusters
#37Earlier quoted context omitted.
No, it doesn't help all. You have yet to provide any evidence for your accusation of insider trading (or "something else"). You can't really accuse RT of wrongdoing, just because you don't understand their methodology. Also -- if I were a quant that managed to beat the market consistently, I would shut up and go straight to RT, for two reasons. To avoid toxic dubious comments like yours, and because RT can pay me bet…
Except that Renaissance trading doesn't really want to hire quants. They wish to hire scientists and mold them in the Renaissance way, which is something you'd know if you were a quant. http://www.reuters.com/article/simons-hedge-idUSN21355752200...
It's a good article, but it's all that you will find about them, no real details on how they are beating the markets over and over again. It's simply not possible to be that successful for so long. The article states that some experiments succeed and some fail and that their strategies peter out over time and they have to develop new ones. Okay, but never booking a loss?
Re: Unsupervised machine learning with basket clusters
#38Earlier quoted context omitted.
Do you understand investing at all? People have been attempting to "beat the market" for decades and nobody has been successful. There is always the "reversion to the mean" issue in every case. People with algorithms think they are beating the market then something changes and their algorithm no longer works. Except for Renaissance--they have consistently been beating the market, or so it appears. Does that help?
No, it doesn't help all. You have yet to provide any evidence for your accusation of insider trading (or "something else"). You can't really accuse RT of wrongdoing, just because you don't understand their methodology. Also -- if I were a quant that managed to beat the market consistently, I would shut up and go straight to RT, for two reasons. To avoid toxic dubious comments like yours, and because RT can pay me bet…
It is not toxic nor dubious to point out the outlier and wonder why.
Re: Unsupervised machine learning with basket clusters
#39Earlier quoted context omitted.
Except that Renaissance trading doesn't really want to hire quants. They wish to hire scientists and mold them in the Renaissance way, which is something you'd know if you were a quant. http://www.reuters.com/article/simons-hedge-idUSN21355752200...
It's a good article, but it's all that you will find about them, no real details on how they are beating the markets over and over again. It's simply not possible to be that successful for so long. The article states that some experiments succeed and some fail and that their strategies peter out over time and they have to develop new ones. Okay, but never booking a loss?
Speaking as a former quant myself (1 year), I believe that there are transient patterns in the market.
The challenge is that those patterns appear and then they disappear mostly forever because they are frequently created by someone else's mistakes like Nassim Taleb buying way out of the money put options that never really created any significant profit. Free Alpha, get your free Alpha, right there.
To tap into those patterns while they are profitable, you need a lot of smart people, and a great deal of infrastructure for experimentation and delivery of strategies that can tap into those patterns before they disappear. While you're right that it is possible that they cheat, it's also possible that they have a sufficiently sophisticated infrastructure to actually make this work. It's kind of like how Nintendo only ships 1 out of 3 video games they develop. All IMO of course.