A multi-factor and high-order stock forecast model based on Type-2 FTS using cuckoo search and self-adaptive harmony search

With the developing economy, an increasing number of factors and high-order data have considerably influenced fluctuations in stock. The fuzzy time series (Type-1) model has been recently studied by many scholars. In this study, an enhanced model on the study of stock forecasting is proposed. This model is a multi-factor and high-order time series forecast model that the Type-2 fuzzy time series model by integrating several other factors. We first employ the cuckoo search algorithm instead of the Conventional average method to partition the universe of discourse, and then propose a novel self-adaptive harmony search algorithm to optimize the high-order weight. Furthermore, the Shanghai Stock Exchange Composite Index and Taiwan Stock Exchange Capitalization Weighted Stock Index are used to verify the better performance of the proposed method. Experimental results show that the proposed method outperforms other baseline methods. (C) 2017 Elsevier B.V. All rights reserved.