Modeling Exchange Rate Behavior with a Genetic Algorithm

Motivated by empirical evidence, we construct a model whereheterogeneous, boundedly-rational market participants rely on a mix of technical and fundamental trading rules. The rules are applied according to a weighting scheme. Traders evaluate and update their mix of rules by genetic algorithm learning. Even for fundamental shocks with a low probability, the interaction between the traders produces a complex behavior of exchange rates. Our model simultaneously produces several stylized facts like high volatility, unit roots in the exchange rates, a fuzzy relationship between news and exchange-rate movements, cointegration between the exchange rate and its fundamental value, fat tails for returns, a declining kurtosis under time aggregation, weak evidence of mean reversion, and strong evidence of clustering in both volatility and trading volume.