http://www.senteco.com/thoughtleader2002/03farmer.html
i came across this and thought others would find it interesting.
Q1
i came across this and thought others would find it interesting.
Q1
Interesting Models
- Thread starter Quiet1
- Start date
"Farmer is currently developing agent-based models to better understand financial markets."
I like Farmer for his pedagogy he's really smart for that. I have in the past posted a book reference from Santa Fe Institute look in archive.
As for agent-based models that's the first thing one could think about when trying to model stock market, that's the way I lookd at myself of course but it would lead to anything but triviality : that people buy because others are buying
These kind of models will just explain the CONSEQUENCES of the EMERGENCE OF CRASH. It's rather a risk model that can be used for arbitrage than for the trader that wants precision.
As Mandelbrott puts it himself humbly for his own model:
http://www.elliottwave.com/education/SciAmerican/Mandelbrot_Article2.htm
"These techniques do not come closer to forecasting a price drop or rise on a specific day on the basis of past records. But they provide estimates of the probability of what the market might do and allow one to prepare for inevitable sea changes. The new modeling techniques are designed to cast a light of order into the seemingly impenetrable thicket of the financial markets. They also recognize the marinerâs warning that, as recent events demonstrate, deserves to be heeded: On even the calmest sea, a gale may be just over the horizon."
As for my model it goes much farther than just risk it really predicts since it is a deterministic model whereas the others are fundamentally of stochastic nature.
http://harrytrader.membres.jexiste.org/guide/home.html.html
I like Farmer for his pedagogy he's really smart for that. I have in the past posted a book reference from Santa Fe Institute look in archive.
As for agent-based models that's the first thing one could think about when trying to model stock market, that's the way I lookd at myself of course but it would lead to anything but triviality : that people buy because others are buying
These kind of models will just explain the CONSEQUENCES of the EMERGENCE OF CRASH. It's rather a risk model that can be used for arbitrage than for the trader that wants precision.As Mandelbrott puts it himself humbly for his own model:
http://www.elliottwave.com/education/SciAmerican/Mandelbrot_Article2.htm
"These techniques do not come closer to forecasting a price drop or rise on a specific day on the basis of past records. But they provide estimates of the probability of what the market might do and allow one to prepare for inevitable sea changes. The new modeling techniques are designed to cast a light of order into the seemingly impenetrable thicket of the financial markets. They also recognize the marinerâs warning that, as recent events demonstrate, deserves to be heeded: On even the calmest sea, a gale may be just over the horizon."
As for my model it goes much farther than just risk it really predicts since it is a deterministic model whereas the others are fundamentally of stochastic nature.
http://harrytrader.membres.jexiste.org/guide/home.html.html
