摘要：We developed profitable foreign exchange forecasts by applying a special adaptive form of the Strongly Typed Genetic Programming (STGP)-based learning algorithm to five-minute high frequency data of six of the most traded currency pairs. We examined the out-of-sample performance of these intraday technical trading models based on STGP and optimised linear forecasting. We found evidence of economically and statistically significant out-of-sample excess returns, after taking into account appropriate transaction costs.
