Intelligent forecasting of inbound tourist arrivals by social networking analysis

Tourism is very important for many countries. Many tourism demand forecasting methodologies are continuously being proposed. Most studies have used lagging economic factors as predictors, but these can cause an inaccurate prediction when unexpected events happen. In this study, a tourism social network will be used in our forecasting model. In addition, a least square support vector regression with genetic algorithm will be developed to predict the monthly tourist arrivals. Grey Relational Analysis indicates that the model outperforms the comparison models, and the null hypothesis of the predicted series having the same mean of the actual series is accepted. The experimental results indicate that the predictors from social network are excellent alternatives to economic indicators. •Most studies have used lagging economic factors as predictors to forecast tourism demand.•This study forecasts tourist arrivals using social network analysis.•The degree centrality and structure hole from a tourism social network are used in our forecasting model.•This study successfully introduce that the predictors using social network are excellent alternatives to economic indicators.•It is a significant breakthrough and finding in tourism demand forecasting.