The Application of Improved SVM for Data Analysis in Tourism Economy

Abstract

In this thesis, the main content of statistical learning theory is firstly introduced briefly, based on this, the basic principle and process of ε-SVR (one algorithm of Support Vector Machine for Regression, SVR) is presented. Then this method is used to model tourist traffic prediction and predict one series data (Taian monthly tourist quantity data). Two different kernel functions are employed, and the former's performance is evidently better than the latter's. ε-SVR's performance is also compared with that of traditional time series analysis method, and the former outperforms the latter.

Computational Intelligence in the hospitality industry: A systematic literature review and a prospect of challenges

“…[123] also applied SVR to forecast electric load by optimizing the method with chaotic genetic algorithms and adding a seasonal component, creating a cyclic electric load forecasting model that yielded better forecasting results than ARIMA (AutoRegressive Integrated Moving Average) and other SVR models. In [118], is mentioned that SVMs are being widely used in these matters because of the idea of structural risk minimization. In this same research work, SVR is used to analyze various kinds of data inside the tourism economy, such as electric and water consumption, by modeling traffic demand and, additionally, monthly tourist quantity data.…”