An ensemble multi-objective particle swarm optimization approach for exchange rates forecasting problem

In this paper, the authors propose an ensemble multi-objective particle swarm optimisation approach (named EMPSO) for forecasting the currency exchange rate chain. The proposed algorithm consists of two main phases. The first phase uses a multi-objective particle swarm optimisation algorithm to find a set of the best optimal particles (named leaders). The second phase then uses these leaders to jointly calculate the final results by using the soft voting ensemble method. The two objective functions used here are predictive error and particle diversity. The empirical data used in this study are six different sets of currency exchange rates. Through comparison results with other evolutionary algorithms and other multi-objective PSO algorithms, the proposed algorithm shows that it can achieve better as well as more stability results on experimental data sets. © 2020 Association for Computing Machinery.