Tourism demand interval forecasting with an intelligence optimization-based integration method

Abstract

Interval forecasting for tourism demand holds significant theoretical and practical insights. However, research on integrating social reviews into multi-source for interval prediction is still developing. To fill this research gap, this study proposes an integrated method for tourism demand interval prediction by combining multi-source data with a modified swarm intelligence optimizer. This method can extract essential intrinsic features from multi-source data and select an appropriate probability density function to extend point predictions to initial prediction intervals, then further refine the initial prediction intervals to improve the prediction accuracy. Empirical studies on the tourism demand of Mount Siguniang and Jiuzhaigou validate the superior predictive capabilities of the proposed model. Experimental results demonstrate that (a) incorporating a multi-source dataset with social reviews significantly enhances the accuracy of the proposed model; and (b) the modified transit search algorithm effectively balances the coverage and width of prediction intervals, thus improving the generalizability of the model.