Presentation 2000/1/12
Analysis of Exchange Rate Scenarios Using an Artificial Market Approach
Kiyoshi IZUMI, Kazuhiro UEDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study we used a new agent-based approach, an artificial market approach, to support decision-making of exchange rate policies. We first interviewed a dealer and found that the features of dealer interaction in learning were similar to features of genetic operations in biology. Next we constructed an artificial market model using a Genetic Algorithm by regarding the market as a multi-agent system. Finally, using the computer simulation of the model, several strategic scenarios of rate policies were compared. As a result, it was found that intervention and the control of interest rates were effective on the stabilization of yen-dollar rates in 1998.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Artificial markets / Foreign exchange markets / Decision support systems / Genetic algorithms / Multi-agent systems
Paper # AI99-67
Date of Issue

Conference Information
Committee AI
Conference Date 2000/1/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Analysis of Exchange Rate Scenarios Using an Artificial Market Approach
Sub Title (in English)
Keyword(1) Artificial markets
Keyword(2) Foreign exchange markets
Keyword(3) Decision support systems
Keyword(4) Genetic algorithms
Keyword(5) Multi-agent systems
1st Author's Name Kiyoshi IZUMI
1st Author's Affiliation Information Science Div., ETL PRESTO, JST.()
2nd Author's Name Kazuhiro UEDA
2nd Author's Affiliation Dept. of General Systems Studies University of Tokyo
Date 2000/1/12
Paper # AI99-67
Volume (vol) vol.99
Number (no) 533
Page pp.pp.-
#Pages 8
Date of Issue