Periodicity analysis and a model structure for consumer behavior on hotel online search interest in the US

Abstract

This paper aims to analyze and model consumer behavior on hotel online search interest in the USA. Design/methodology/approach: Discrete Fourier transform was used to analyze the periodicity of hotel search behavior in the USA by using Google Trends data. Based on the obtained frequency components, a model structure was proposed to describe the search interest. A separable nonlinear least squares algorithm was developed to fit the data. Findings: It was found that the major dynamics of the search interest was composed of nine frequency components. The developed separable nonlinear least squares algorithm significantly reduced the number of model parameters that needed to be estimated. The fitting results indicated that the model structure could fit the data well (average error 0.575 per cent). Practical implications: Knowledge of consumer behavior on online search is critical to marketing decision because search engine has become an important tool for customers to find hotels. This work is thus very useful to marketing strategy. Originality/value: This research is the first work on analyzing and modeling consumer behavior on hotel online search interest.