Prediction of Foreign Exchange Rates by Collective Intelligence of Counter Party Banks

Abstract

In foreign-exchange (FX) dealing, FX brokers basically cancel out the orders fromtheir customers to prevent the price fluctuation risk by cover transactions with global megabankscalled Counter Party (CP). Each CP has huge amount of money to play a role of market reader,and might have proprietary know-how to foresee future price movements. From this viewpoint,we try to extract their knowledge by a machine learning approach, and therefore we apply thestacking method that aggregates some predictors to extract the ensemble knowledge. If CP's pricequotations are decided by foreseeing future price possibilities, their quotations can be consideredas predictors. From this concept, we apply the stacking method to their quotations and obtain theensemble knowledge from them. Through some simulations using real price data, we could con-firm that the given ensemble knowledge improves the prediction accuracy of FX price movementscompared to the machine learning using a single CP's price quotation.