Multi-agent approaches to economic modeling: Game theory, ensembles, evolution and the stock market

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

2 Citations (Scopus)

Abstract

A multi-agent system that learns by using neural networks is implemented to simulate the stock market. Each committee of agents, which is regarded as a player in a game, is optimized by continually adapting the architecture of the agents through the use of genetic algorithms. The proposed procedure is implemented to simulate trading of three stocks, namely, the Dow Jones, the NASDAQ and the S&P 500.

Original languageEnglish
Title of host publicationAdvanced Information and Knowledge Processing
PublisherSpringer London
Pages195-213
Number of pages19
Edition9781447150091
DOIs
Publication statusPublished - 2013

Publication series

NameAdvanced Information and Knowledge Processing
Number9781447150091
ISSN (Print)1610-3947
ISSN (Electronic)2197-8441

ASJC Scopus subject areas

  • Management Information Systems
  • Information Systems
  • Information Systems and Management
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Multi-agent approaches to economic modeling: Game theory, ensembles, evolution and the stock market'. Together they form a unique fingerprint.

Cite this