Design of optimal hedge-algebras-based model for fuzzy time series forecasting

Abstract

Fuzzy time series forecasting has garnered significant attention due to its ability to handle uncertainty and imprecision in time series data. Traditional fuzzy time series models often face limitations in capturing complex relationships between variables. To address this challenge, we propose a novel approach called the Optimal Hedge-Algebras-based Model (OHAM). First, we introduce the concepts of hedge algebra and its application in fuzzy time series analysis. Subsequently, we present the model construction steps, including defining linguistic labels in hedge algebra, constructing fuzzy relations from data, and partitioning the universe of discourse. Following this, we propose an optimization algorithm to fine-tune the parameters of OHAM, aiming to achieve optimal forecasting performance. Finally, experiments are conducted on several specific datasets to evaluate the effectiveness of the model. The experimental results demonstrate that the newly proposed model exhibits better accuracy than many others.