| With the development and popularization of computer and Internet in China,and as the social and economic development has entered a new historical stage,online trading in China is booming.Compared to other e-commerce patterns,such as the B2 B pattern,C2 C online shopping market has broader space for further development.While since China’s market economic system and operation mechanism is still not perfect,the environment for its development is immature,so there is still a gap between China’s C2 C online shopping market and that of the developed countries.Sellers on the C2 C platform neither have enough understanding of trading volume and nor did comprehensive analysis of it and that result in inadequate or excess in inventory.As a result,logistics companies are unable to estimate the future trend.Scientific and accurate analysis of volume can not only greatly reduce the pressure on warehouses,but also cut unnecessary cost during offseason and reduce the logistics cost,and improve the service quality of logistics company.Time series refers to the data sequence of observed values in different time of same phenomenon in a chronological set,and the C2 C online shopping market volume fluctuations are nonlinear and non-stationary time series.The impact of its volatility is a result of the interaction of many different factors,and the volatility of these factors is uncertain,so the C2 C online shopping market analysis methods should be more adaptable.Among researches related to online shopping market time series both at home and abroad,time series methods currently applied in C2 C market are mainly arithmetic average method,moving average method,exponential smoothing method,but they still lacking analysis on the fluctuation of nonlinear and non-stationary and tending to ignore the possible causes which generate the non-stationary nonlinear fluctuation in applications.In recent years,empirical mode decomposition(EMD)method has been applied to the analysis of the factors of stock price and grain yield,and it has been proved to be the best way to extract trend in non-stationary and nonlinear time series.In view of the characteristics of time series of C2 C online shopping platform,and the certain superiorities that the EMD method has in dealing with non-stationary data processing,therefore,in this paper the EMD method is used to analyze the time series of trade volume.These data are then divided into several groups of modal,the high frequency part,the low frequency part and the residual term and explained by user’s habits,holiday promotions and long-term trends.Based on the original time series data of one online store on TAOBAO during a year,the EMD is used to analyze the factors that affect the sales of the stores.The main conclusions of this paper are as follows:Compared with other traditional methods,the EMD can extract and analysis the nonlinear wave quantitative of the volume caused by the online shopping platform promotional activities,therefore it is more suitable in the unsteady nonlinear time series data analysis such as the trade volume of C2 C online shores;the trade volume of China’s online shopping market show obvious seasonal fluctuation;In terms of shopping time customers of the C2 C online shopping market tend to shop more at the beginning of the week,which completely opposite to those of the traditional trading market;Monthly trade volume usually reaches the maximum value at the beginning of the month which suggests that online trades are more concentrated at the beginning of each month. |
PDF Full Text Request