Fuzzy time series forecasting based on proportions of intervals and particle swarm optimization techniques

In this paper, we propose a new fuzzy time series (FTS) forecasting method based on the proportions of intervals and particle swarm optimization (PSO) techniques. First, it uses PSO techniques to obtain the optimal partitions of intervals in the universe of discourse (UOD). Then, each historical testing datum (HTD) is transformed into one of the obtained optimal intervals to construct logical relationships (LRs). Then, based on the current states of the constructed LRs, it constructs logical relationship groups (LRGs). Finally, it performs the forecasting based on the constructed LRGs and the proportions of intervals. The proposed method outperforms the existing methods for forecasting the enrollments of the University of Alabama (UA), the time series data of killed in car road accidents in Belgium and the spot gold in Turkey. (C) 2019 Elsevier Inc. All rights reserved.