Article ID Journal Published Year Pages File Type
884822 Journal of Economic Behavior & Organization 2006 15 Pages PDF
Abstract
Agents evolve their forecast rules over time via a modified genetic algorithm in a simple artificial currency market. These forecast rules can be nonlinearly misspecified. When the misspecification is suppressed, learning tends to be complete. When it is not suppressed, learning can generate persistent exchange rate dynamics.
Keywords
Related Topics
Social Sciences and Humanities Economics, Econometrics and Finance Economics and Econometrics
Preview
Learning with misspecification in an artificial currency market
Authors
,