A Novel Time Series Forecasting Method Based on Fuzzy Visibility Graph

Aiming at the defect of visibility graph, this paper first proposes the definition of fuzzy visibility graph, then gives a new similarity measure of time series induced from the similarity of fuzzy visibility graphs. Based on the proposed definition and similarity measure, a novel time series forecasting method is established. To demonstrate the performance of the proposed method, experiments are carried out on Alabama enrollment, stock price index and Shanghai Pudong Development Bank’s closing price. The results show that the proposed method improves the accuracy of prediction.