PSO-based high order time invariant fuzzy time series method: Application to stock exchange data

Egrioglu E.

ECONOMIC MODELLING, vol.38, pp.633-639, 2014 (SSCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 38
  • Publication Date: 2014
  • Doi Number: 10.1016/j.econmod.2014.02.017
  • Journal Name: ECONOMIC MODELLING
  • Journal Indexes: Social Sciences Citation Index (SSCI), Scopus
  • Page Numbers: pp.633-639
  • Keywords: Fuzzy time series, Particle swarm optimization, Fuzzy c-means, Forecasting, Define fuzzy relation, FORECASTING ENROLLMENTS, TEMPERATURE PREDICTION, LOGICAL RELATIONSHIPS, MODEL, INTERVALS, LENGTHS, ANFIS
  • Ondokuz Mayıs University Affiliated: No

Abstract

Fuzzy time series methods are effective techniques to forecast time series. Fuzzy time series methods are based on fuzzy set theory. In the early years, classical fuzzy set operations were used in the fuzzy time series methods. In recent years, artificial intelligence techniques have been used in different stages of fuzzy time series methods. In this paper, a novel fuzzy time series method which is based on particle swarm optimization is proposed. A high order fuzzy time series forecasting model is used in the proposed method. In the proposed method, determination of fuzzy relations is performed by estimating the optimal fuzzy relation matrix. The performance of the proposed method is compared to some methods in the literature by using three real world time series. It is shown that the proposed method has better performance than other methods in the literature. (C) 2014 Elsevier B.V. All tights reserved.