Software Release Announcement: Evolutionary Agent-based Market Simulation Software (free alpha version)
- From: "Jim Witkam" <jim.witkam@xxxxxxxxx>
- Date: 5 Mar 2007 01:25:03 -0800
Adaptive Modeler creates agent-based market simulation models for
analyzing historical prices of stocks, currencies or other market
traded securities. The agent-based model simulates a financial market
consisting of thousands of individual agents whose trading rules
evolve through genetic programming. The evolution of trading rules
combined with market pricing dynamics drives the agent population to
learn to recognize and anticipate recurring price patterns while
adapting to changing market behavior. The overall behavior of this
virtual market is the basis for trading signals.
For genetic programming researchers this application may be of
interest to study the evolution and behavior of genetic programs in an
agent-based (market) environment. Note however that the approach is
unconventional. Adaptive Modeler uses continuous retraining (in such a
way that every price is evaluated only once) and steady-state
breeding. Parameters such as population size, breeding frequency,
selection and replacement criteria and mutation rate can be configured
by the user.
Various population statistics can be followed in live charts including
histograms for wealth distribution, age distribution, genome size
distribution, genome depth distribution, etc. Also some crossover and
mutation statistics are available. A data export function is included
to export data for further analysis in other applications.
A free alpha evaluation version (no registration required) can be
downloaded at: http://www.altreva.com
Jim Witkam
.
- Prev by Date: Software Release Announcement: Evolutionary Agent-based Market Simulation Software (free alpha version)
- Next by Date: IICAI-07 call for papers
- Previous by thread: Software Release Announcement: Evolutionary Agent-based Market Simulation Software (free alpha version)
- Next by thread: IICAI-07 call for papers
- Index(es):
Relevant Pages
|
|