Analysis of Tourist Flow Forecasting Model Based on Multiple Additive Regression Tree

2nd International Symposium on Application of Materials Science and Energy Materials

材料科学;能源学

Kang, Chuanli^1^2 ; Gu, Junfeng^1^2

Guangxi Key Laboratory of Spatial Information and Geomatics, Guilin

541006, China^1

College of Geomatics and Geo-information, Guilin University of Technology, Guilin

541006, China^2

关键词: Accurate prediction;    Additive regression;    Average errors;    Development planning;    Flow forecasting;    Flow prediction;    Prediction accuracy;    Sunshine duration;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/490/4/042001/pdf
DOI  :  10.1088/1757-899X/490/4/042001

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

Accurate prediction of tourist flow is a key issue in tourism economic analysis and development planning. This paper proposes a tourist flow prediction model based on Multiple Additive Regression Tree (MART) by using machine learning ideas. The model uses factors such as temperature, sunshine duration, air quality and so on to construct eigenvector, and constructing multiple base learners through the boosting framework to predict tourist flow accurately. Take Guilin city from 2015 to 2018 Tourist as an example for analysis, the prediction accuracy of the model is evaluated by means of the average error, square equalization error and other indicators. The experimental results show that the proposed method has high accuracy in the prediction of tourist flow.