Title :
Optimization of trading physics models of markets
Author :
Ingber, Lester ; Mondescu, Radu Paul
Author_Institution :
Lester Ingber Res., Chicago, IL, USA
fDate :
7/1/2001 12:00:00 AM
Abstract :
We describe an end-to-end real-time S&P futures trading system. Inner-shell stochastic nonlinear dynamic models are developed, and canonical momenta indicators are derived from a fitted Lagrangian used by outer-shell trading models dependent on these indicators. Recursive and adaptive optimization using adaptive simulated annealing is used for fitting parameters shared across these shells of dynamics and trading models
Keywords :
commodity trading; simulated annealing; statistical analysis; stochastic processes; adaptive simulated annealing; canonical momenta indicators; financial market; futures trading system; recursive optimization; statistical mechanics; stochastic nonlinear dynamic models; Artificial intelligence; Context modeling; Genetic algorithms; Lagrangian functions; Mathematical model; Nonlinear dynamical systems; Physics; Power system modeling; Simulated annealing; Stochastic processes;
Journal_Title :
Neural Networks, IEEE Transactions on
