Modeling for Predicting Domestic Demands for Recreational Tourism in Tehran

Recreational tourism is an important form of domestic tourism in Tehran, based on the statistics of the National Center of Statistics and the views of the experts. This paper tried to propose models for predicting effective variables on predicting domestic demands for recreational tourism in Tehran. The study used the monthly information between 2001 and 2015. The independent variable was the number of domestic recreational tourists in Tehran, and the dependent variables were selected based on Delphi and Fuzzy DEMATEL techniques. The model framework was a combination of regression, the fuzzy neural network, and SVR algorithm. The combinations of these methods helped measure prediction errors and compare methods. Results showed that the proposed hybrid approach of regression and Adaptive Neuro-Fuzzy Inference System (ANFIS) could have a better prediction compared to other methods for predicting domestic recreational tourism.