Machine designed strategies. Do they work?

Quote from amazingIndustry:

Sorry but you are a total troll because you have no issues with snake oil salesmen who are cocky and arrogant...
More...
You are calling a troll someone who has never behaved like one simply because he asked you specific questions you didn't possibly knew what they involve. I do believe that you have no idea what Sharpe means.

Then, you accuse others of being snake oil salesmen but you are the one who has tried very hard to maybe sell his background here. Yes, I have figured out your argumentation. This is what you say essentially:

"Nobody can do it, no program can do it, they are all bad people, they all sell snake oil, I can only do it, I have the qualifications, I know PDEs, I know stochastic calculus..."

But we haven't seen anything specific from you. Just vague things we heard and you throwing around mad and accusations. You are asking very hard others to put you on ignore fellow.
 
Quote from amazingIndustry:

a) I gave a lot more examples but I guess you were to preoccupied with other things

b) generally people coming right out of grad school are a lot more specific and detailed because they lack working experience in most cases and fail to often see the big picture while career practitioners are often generalizing rather than digging into details from the outset of a discussion. Hence, you should actually observe the opposite. Those who can describe things in simple terms and can extrapolate imho are more grown and mature than those who try to win arguments biting their teeth into a single detail and lose sigh of the actual point they try to make. If you do not comprehend what point I tried to make then I failed explaining it or your intellect could not grasp it, make a choice

c) I should have answered the Sharpe ratio question? I had to? you forced me? What a troll you are. I have to do nothing! So what if I tell you some of my hft strategies sport an annualized 8-10 Sharpe based on daily returns and return vol with 95% confidence? Next you need to see proof? I am not engaging with you in a pissing contest, so rest it. I never made any claim whatsoever in regards to performance.

d) I never said all approaches to trading involve higher level math. Quote me please.

e) I traded for over 14 years 6 of which are post grad school in several tier one ibanks and hedge funds, after which I started running my own hft venture. I posted those numbers before if you did not pay attention then it speaks to your ignorance.

f) I answered his question in much detail, my point AGAIN was that correlations alone do not matter much, neither does statistical significance in isolation. One example is that the OOS could be way too short a period to capture different market dynamics. Even you have 10 different statistically significant OOS results that speak for an implementation of your strategy you may not at all have captured different market dynamics. There are aspects involved in arriving at a truly promising strategy that can only be learned from actual risk management and risk taking experience. No book will teach you that, no time series analysis will get you that.

Sorry but you are a total troll because you have no issues with snake oil salesmen who are cocky and arrogant but you take issue with those who may be arrogant and cocky but definitely have put in the work and have plenty enough experience and the educational background. For whatever reason you appear very insecure by attacking on a personal level. If you believe I pulled out all the things I wrote out of my ass or copied some wiki pages then I rest my case. This is my last msg to you I have no inclination to battle about irrelevant things.
More...

Mate, Alright I am a troll :) But the point is you still didn't answer specific questions. Why shy away from disclosing your PF and Sharpe when you feel free to harp on your IBanking experience, as you have done again in your post above. LOL. Do you think readers are stupid. LOL.

Btw, I don't need to see any proof of your PF and Sharpe. For record, I would believe whatever Sharpe you tell me you are running - because you obviously are a few years industry pro and those guys typically don't lie. So, don't worry I won't accuse you of lying - but yes I do accuse you of using your pedigree to win an argument instead of engaging in specifics. Like you didn't answer how many strategies you have. Anyways, its your choice. By this action, you only lose credibility.

Anyways, as I have already said there is not much I differ with you other than your attitude. Had you been on my desk in an ibank, even if you would have been my MD and I an associate, I would have given you a tough time, because I never let people go away by hand-waving and using their pedigree as a bulletproof jacket. Cheers!

EDIT: I agree that in this post you mentioned that you have traded for 14yrs, 6 of which after your grad school. I give you credit for at least disclosing this part of information. Thanks.
 
I think I qualify as an entrepreneur. Five companies over 40 years. One really successful, one a total failure. Three so so. None directly in the trading area.

Things aren't as clear as to what's most productive as you go day to day. And no one is rational all the time except in hindsight.

Personally, I hate trading. It makes me feel lousy. But, I love developing software. And I love math and statistics. Most of the traders I know are lousy at both software development and math. Combine the two and you can get something really good. Which is what hedge funds do.

I guess I would go with the fighter plane designer/fighter pilot analogy.
 
Quote from lel4866:

...Most of the traders I know are lousy at both software development and math...
More...

I agree with this part.

While there is a small subset of traders from a quant background, these guys are the exception rather then the rule, as far as I have seen.

There are still desks full of knuckle dragging sales traders, execution guys, and prop desks that run off economic, sector, and single stock research, rather than quant models & algorithms.

None of these traders are math/tech guys.

The math/tech guys are their bitches.
 
A comment about the original topic...Machine Learning.

This is the field I work in. However, I don't recall, after scanning through the 34 pages of this thread where anyone tried to define what they mean by Machine Learning.

Academically, it is an extremely broad field. I have taken classes at the graduate school level at both the University of Washington and MIT. It covers everything from nonlinear optimization based techniques such as support vector machines, and neural networks, genetic and evolutionary search algorithms, rule base systems, decision trees, etc.

Commercially, my company is paid hundreds of millions of dollars each year to develop and configure this stuff, primarily in the financial industry. We have hedge fund and investment banking clients. I have met with them and worked with them.

So, I can only figure that these clients think these methods have some merit, although because of their secrecy, I have no idea whether trading systems using these techniques are actually deployed. One of the areas I can guarantee where they deploy our software is in the area of portfolio selection and risk analysis.

All that said, I do believe these techniques are useful in developing trading systems. But, not by novices. You have to ***understand*** what's going on.

AmazingIndustry said something about 5 pages back that was particularly relevant:

"but you still know in the back of your mind that the dynamics of the strategy were not derived from logical reasoning that you derived from experience about market dynamics but that it instead originated from a mathematical optimization tool".

The problem with non-interpretable strategies like those typically produced by neural networks, for instance, is if you can't understand why something is happening, you don't know when the logic is breaking down. Because people are at least subconsciously aware of this, they can't continue to trade these systems when they go through the normal periods of drawdown.
 
digital solutions do not work in an analog game.

never have, never will.

as long as 2 legged mammals are still pulling the levers on the playing field, i suggest you all do the same.

to think that a bunch of digital robotic crap actually has a hope in hell of an ROI is pure fantasy.

pissing up a rope comes to mind.

they go up, down and sideways.
if that changes i will post up an alert to the contrary.

if digital strategies were so sucessful, one group would have all the coin.

not gonna happen.

cheers,

s

:cool:
 
Quote from lel4866:

Commercially, my company is paid hundreds of millions of dollars each year to develop and configure this stuff, primarily in the financial industry. We have hedge fund and investment banking clients. I have met with them and worked with them.
More...

Thank you for posting this. It's good to have some more official confirmation regarding the fact that ML is being used more broadly.
Hundreds of millions? Wait, can I sell my software like that? heh... oh thats right, i have to fail at trading first. Ok, never mind.

One of the areas I can guarantee where they deploy our software is in the area of portfolio selection and risk analysis.
More...

Bingo!

Synthetic risk curves ftw. I'm completely agreeing with this so far.
 
Quote from braincell:



Bingo!

Synthetic risk curves ftw. I'm completely agreeing with this so far.
More...

I could be wrong but I think he means risk management in longer-term asset allocation strategies. I have a neighbor who does this type of work in NYC. Very dry and slow-paced, but lots of funds are doing this type of work I think.
 
Quote from ssrrkk:

I could be wrong but I think he means risk management in longer-term asset allocation strategies. I have a neighbor who does this type of work in NYC. Very dry and slow-paced, but lots of funds are doing this type of work I think.
More...

Yeah that's "almost" the same thing. Shift the time frames around but basically you are syncing portfolios. Just like you can fit in assets, you can fit in strategies - each has it's own nature and the assumptions are much easier to make than for single markets. Lots of variants on the subject, like hedging sideways on the same instruments and different accounts, etc etc. We might not be using the same terminology but I think it's similar enough.
 
You must log in or register to reply here.
Back
Top