Dynamic Trend Simulation Analysis of Tourism Big Data based on Feedback Constraint Association Rules

  Ruiping Chen

Foshan Polytechnic, Foshan, 528137, China

Abstract: In order to improve the ability of tourism big data to predict and evaluate, realize the quantitative statistical evaluation of tourism information, and thus to guide tourism planning and decision-making, A dy-namic trend prediction algorithm for tourism big data is proposed based on feedback constraint association rules. The statistical prior information of tourism big data is constructed by the autosimilar regression model. In the autosimilar regression model, the empirical modal decomposition of the tourism big data statistical dis-tribution series is carried out. The feature extraction method of feedback constraint association rules is used to analyze the features of tourism big data, and the BP neural network classification model is used to deal with the feature information clustering and information fusion of tourism big data. The descriptive statistical analysis method is used to analyze the statistical characteristics of tourism big data, to construct the statistical characteristic quantity of the tourism big data distribution, and the principal component analysis is used to mine the association rules of tourism big data. The prediction of tourism big data's dynamic trend is realized. The simulation results show that the proposed method has high accuracy, good convergence and good prediction accuracy for the dynamic trend of tourism big data.

Keywords: tourism big data; feedback constraints; association rules; data mining; statistical analysis; feature extraction