Technical analysis with artificial intelligence

Quote from Thunderdog:

I don't think that LTCM was a black box thing. And wasn't the fall based at least in part on a misplaced overconfidence in a timely reversion to the mean under any circumstances by Meriwether? As I understand it, towards the end, Meriwether had blind faith in the model that exceeded the confidence of the academics who developed it.
More...

LTCM biggest problem was they moved away from the core models that where reliable because they had saturated these core markets. In addition they overtraded and forgot that the risk of the 5 sigma event is much greater than a normal distribution would imply. In some ways it the same type of thing that happens to many traders who blow up, over confidence and then over trading.
 
Quote from Murray Ruggiero:

In some ways it the same type of thing that happens to many traders who blow up, over confidence and then over trading.
More...

They returned half their investors money at one point but allowed the same margin amount, effectively doubling their leverage before the 5 sigma event. Talk about over confident.
 
Murray,

And wasn't it also the case that LTCM's model didn't factor in a government (Russia) defaulting on its bonds?

I think it was their VAR model - which may be what your referring to.

Grant.
 
Quote from cvds16:
technical analysis is no science ...
More...
That's really very funny. On a basis of fundamental mathematics, I wonder if you even realize how absurd that comment is.

I'm not intending to be inflammatory here. It just baffles me when people make statements like this. Or that ai is not applicable to the markets when they obviously don't even know what ai is... what various types of ai there are. Or even if they did, they would not have a clue as to how-and-what data decision environments they could properly accommodate.

So consider... before commenting on a subject, be relatively sure you know what it is your commenting on.

jmho
-kt
 
Quote from Grant:

Murray,

And wasn't it also the case that LTCM's model didn't factor in a government (Russia) defaulting on its bonds?

I think it was their VAR model - which may be what your referring to.

Grant.
More...

Yes , It was David DeRosa dubbed VAR models as "a lighthouse for the soon to be shipwrecked"

In terms of the Russia issues , The spread between Treasuries and corporate bonds widen which was the opposite of what LTCM was betting on.

The Russian issues were not in the model, because once you add these types of events to a model it become too hard to model , that is why VAR models have big problems.
 
Technical analysis is no science... Why, because the markets rely on the interaction of people, and since sociology is about as much a science as astrology, it is no science.

But there are reoccuring generalities, however.
 
Quote from marklucas:
Technical analysis is no science... Why, because the markets rely on the interaction of people, and since sociology is about as much a science as astrology, it is no science.
But there are reoccuring generalities, however.
More...
I guess some people prefer to act before actually thinking and confirming there beliefs.

Sociology: Scientific study of human social behavior. As the study of humans in their collective aspect, sociology is concerned with all group activities—economic, social, political, and religious. Sociologists study such areas as bureaucracy, community, deviant behavior, family, public opinion, social change, social mobility, social stratification, and such specific problems as crime, divorce, child abuse, and substance addiction. Sociology tries to determine the laws governing human behavior in social contexts; it is sometimes distinguished as a general social science from the special social sciences, such as economics and political science, which confine themselves to a selected group of social facts or relations.
More...
 
A science is falsifiable... Can you predict human behaviour as accurately as the force of gravity on a falling object?
''No," I hear you say? Why not?

Because it 'aint science! :)
 
Quote from marklucas:

A science is falsifiable... Can you predict human behaviour as accurately as the force of gravity on a falling object?
''No," I hear you say? Why not?

Because it 'aint science! :)
More...

Just a question to ponder
Then you would say that meteorology is also not a science because the weather can not be predicted like gravity ?.
 
You must log in or register to reply here.
Back
Top