Learning to forecast the exchange rate: two competing approaches

In this paper, we investigate the behavior of the exchange rate within the framework of an asset pricing model. We assume boundedly rational agents who use simple rules to forecast the future exchange rate. They test these rules continuously using two learning mechanisms. The first one, the fitness method, assumes that agents evaluate forecasts by computing their past profitability. In the second mechanism, agents learn to improve these rules using statistical methods. First, we find that both learning mechanisms reveal the fundamental value of the exchange rate in the steady state. Second, both mechanisms mimic regularities observed in the foreign exchange markets, namely exchange rate disconnect and excess volatility. Fitness learning rule generates the disconnection at different frequencies, while the statistical method has this ability only at the high frequencies. Statistical learning can produce excess volatility of magnitude closer to reality than fitness learning but can also lead to explosive solutions.