Research on Forecasting Method Based on Improved Set Pair Analysis and Fuzzy-Markov Chain

摘要

Forecasting of freight volume is a complicated system engineering that is influenced by multitudinous factors. To improve forecasting accuracy, and to reduce the limitation of conventional forecasting methods, the set pair analysis theory combined with fuzzy-Markov theory is introduced to describe the dynamic system, and the forecasting model based on SPA-fuzzy-Markov for freight volume forecasting is set up based on analyze and forecast the state transition of the uncertain factor. Meanwhile, verify methods for fuzzy-Markov fitting in multidimensional space are suggested. Finally, a case study has been carried out in order to testify objectivity and applicability by using calculating and comparing analysis with forecasting accuracy of relevant forecasting model, The results show that this model can improve forecasting accuracy than SPA model, moreover, the accuracy of forecasting model based on SPA-fuzzy-Markov is not only greater than any other single forecasting models, but also superior to other traditional combinational forecasting models. Therefore, it can well reflect the laws of development of things and can be of practical and effective value in actual use of construction project.