which more advanced methods would you look at ...

[man]

thnx gents for your replies. do not get me wrong, we are pretty active and neither afraid of any complexity, nor do i think that superstrings are the holy grail ...

i do not want some academic to find me a system, i just need indications to explore it on my own. this is a very different thing. actually i want to use more sophisticated tech in the same way as i use a standard indicator. and there is no argument why wavelet should be less effective than ATR ...

nosense, you are one of the few people i know from boards that i would really like to meet once in persona ...

nbates ... thnx, i come back to you ...

 

[Walther]

I would like to add something for members who are searching for more and more and more advanced methods. successful and profitable method must be derived from market price movement.
Any experiment with nature and man made frequencies,Neural and other nets, astro movements, Fib ratios and Gann angles and numbers will fail to produce profitable method. Save yourself a time and concentrate on PRICE .

 

[hardyards]

Quote from Walther:

I would like to add something for members who are searching for more and more and more advanced methods. successful and profitable method must be derived from market price movement.
Any experiment with nature and man made frequencies,Neural and other nets, astro movements, Fib ratios and Gann angles and numbers will fail to produce profitable method. Save yourself a time and concentrate on PRICE .

PRICE & VOLUME

 

[stephencrowley]

Your assumptions are based on technology that is publically available and in wide-spread use, hence your dismal perception of neural nets.

All of the publically available and widely used models of neural nets are silly hacks that really have no relation to how brains recognize patterns and make decisions.

By you saying silly things like, neural nets cant make money, think of it this way: people are neural nets, and people can make money.

I am not proposing that I, or anyone else will succeed in recreating human intelligence in a machine anytime in the near future.

What I am suggesting is that by reverse enginering nature's best pattern maching and decision making machine (the brain) then we can begin to understand how to program machines to simulate intelligent behaviour.

I'm working out a self-study relationship with a professor currently who specializes in this type of stuff(not neural modelling, but very closely related fields) and will be going into research with a hard-core focus on building applications

Quote from Walther:

I would like to add something for members who are searching for more and more and more advanced methods. successful and profitable method must be derived from market price movement.
Any experiment with nature and man made frequencies,Neural and other nets, astro movements, Fib ratios and Gann angles and numbers will fail to produce profitable method. Save yourself a time and concentrate on PRICE .

 

[trendmomentum]

Have you also considered astrology? There might some hidden reactions to the waves resulting from the alignment of the planets .. LOL

Quote from man:

... if you only had the time and skill?

i am currently contemplating on sponsoring some academic work. i would like them to do some initial research on advanced techniques which would take us several weeks each. reason for this is that we are already swamped with development issues and i need to concentrate on topics where i have indication that it could be worth it.

wavelets,
agent based models and
signal processing are now on my list.

i am not so fond of nn, since i am naturally paranoid of overfit and nn still seem to me to be the ultimate fitting candidate. we are already moving towards genetic algorithms, so that is covered. chaos theory is something i love to read about, yet have not indication that it can be applied profitably.

data basis will be index futures, not lower than minute bar level.

anyone having hints for addOns to "the list"?


peace

 

[man]

Quote from trendmomentum:

Have you also considered astrology? There might some hidden reactions to the waves resulting from the alignment of the planets .. LOL

choose one of the words forbidden here and feel as much insulted as your lack of mental forces allows you to.

 

[nononsense]

Quote from man:

[]
your lack of mental forces allows you to.

Ya could always supplement these with neural nets.
stephencrowley said so.

 

[stephencrowley]

lol, nonsense, you're a character.

but in principle I guess in the future machines will be able to judge people to be lacking mental capability, barring of course any nuclear wars or epidemics that wipe out mankind, or asteroids hitting the planet, or gun toting rednecks in control of the free world fucking everything up.

Quote from nononsense:

Ya could always supplement these with neural nets.
stephencrowley said so.

 

[Walther]

Quote from stephencrowley:

.

By you saying silly things like, neural nets cant make money, think of it this way: people are neural nets, and people can make money.

Really silly think is that 95% of people( neutral nets) will never make any money. Guys who are programming neural nets on any level cannot make money.
If you want to waste your time to know how neural net sees markets, be my guest.

 

[stephencrowley]

The military and space industry use neural nets for all sources of very difficult nonlinear control problems. A coworker of mine used to work for boeing taking AI theory and working with other researchers to turn it into application. Some of the models to fly a jetliner took nearly a week to train on a cray(this was 10 years ago). These are not the neural nets these kids play with in excel. These things are being used as well in designing space probes capable of making judgement calls on how to carry out the mission, because mission planners do not know what to expect when they reach their target.. the machines must reason and attempt to find ways to carry out their mission oals.

Same guy said when he was in the AI field, going to all the conferences, everyone there was either military, nasa or from wall-street investment banks.

I'm sure lots of people told Columbus not to waste his time sailing around the world.

Quote from Walther:

Really silly think is that 95% of people( neutral nets) will never make any money. Guys who are programming neural nets on any level cannot make money.
If you want to waste your time to know how neural net sees markets, be my guest.