Applied Research Of Time Series Analysis In Customer Satisfaction DATA

By reviewing the emergence, development and current research situation of customer satisfaction theory, summarizing the working flow of customer satisfaction measurement and current application situation of customer satisfaction data analysis, we find that the time series analysis approach, as an important part of customer satisfaction measurement, has not been applied systemically in customer satisfaction data sequence analysis. As a kind of maturity statistic tool for solving the question of time series data, time series analysis can model the stochastic mechanism that gives rise to an observed series and predict future value of a series based on the history observations. Sequentially, more information can be fund more accurately if time series analysis is applied to customer satisfaction data sequence.Customer satisfaction data sequence has the characteristic that it is stationary within a relatively short time but nonstationary over a long period. It is difficult to avoid the abrupt exterior factor's impact in the process of customer satisfaction data sequence developed over a long period. So, in this paper, we use the interference analysis model, as a special kind of time series model, to analyze customer satisfaction data sequence.This paper can be divided into four parts. Firstly, we summarized eight interference factors from the real information, and defined interference variables based on these interference factors. Secondly, we analyzed the impact of the interference variables on the customer satisfaction data by regression analysis. Thirdly, a time series model was fitted to the regression residual sequence. Finally, this model was used to a real data—the Shanghai taxi industry customer satisfaction data sequence, and the future trend of data sequence was successfully predicted using the interference analysis time series model.Our research results provide a new practical tool to customer satisfaction measurement, and largely enrich the customer satisfaction data analysis methods.