Exchange rates forecasting using Tabu Search based Flexible Neural Networks

Forecasting currency exchange rates is an important financial problem, which is receiving increasing attention especially because of its difficulty and practical applications. Various techniques have been used to forecast exchange rates. Artificial Neural Networks have proven to be efficient and profitable in forecasting financial time series. Tabu Search (TS) is a quite flexible and promising search technique for obtaining good solutions quickly and has been applied to solve many optimization problems. In this paper a TS based Flexible Neural Network (INN) was employed to predict three major international currency exchange rates against American dollar. The forecasting performance of the TS-FNN models was evaluated using a number of widely used statistical metrics and the results were compared with the related methods. Experimental results show that the proposed method is effective and efficient.