Search

In view of the shortcomings of traditional clustering algorithms in feature selection and clustering effect, an improved Recency, Frequency, and Money (RFM) model is introduced, and an improved K-medoids algorithm is proposed. Above model and algorithm are employed to segment customers of e-commerce. First, traditional RFM model is improved by adding two features of customer consumption behavior. Second, in order to overcome the defect of setting K value artificially in traditional K-medoids algorithm, the Calinski–Harabasz (CH) index is introduced to determine the optimal number of clustering. Meanwhile, K-medoids algorithm is optimized by changing the selection of centroids to avoid the influence of noise and isolated points. Finally, empirical research is done using a dataset from an e-commerce platform. The results show that our improved K-medoids algorithm can improve the efficiency and accuracy of e-commerce customer segmentation.

Alibaba’s Taobao is China’s dominant C2C e-commerce platform. Relying on novel transaction level data from its electronics category, this paper examines the roles of distance as well as seller and buyer experience in Chinese e-commerce. Our estimate of a gravity model shows that the distance elasticity in our data is greater than US C2C e-commerce but smaller than that of South America. In addition, we document greater home bias in China than either of the US or South American Settings. Moreover, by estimating a “new-new” trade model using seller-level transaction data, this paper studies the link between seller experience and distance. Our results show that more experienced sellers tend to sell more and export their goods farther into the marketplace.

In order to adjust Taiwan's industrial structure and raise technical levels, Taiwan's government has begun to use New Leading Product Development Projects (hereafter referred to as NLPDPs) to assist manufacturer research and develop hi-tech products since 1991. According to reports of Industrial Development Bureau (IDB) (1999), overall investment in NLPDPs from 1991 to 2000 was in excess of NT$40 billion. The purpose of this study is to investigate the variables influencing new products, which were developed in NLPDPs and have been introduced to market and sold successfully, a total of 214 projects were used to study using logistics regression. The result indicated that self-provided funds, firm size, number of R&D personnel, and the ratio of master's degree holders or higher were statistically significant. The impact of government subsidies (interest-free loans and grants) did not have a direct effect on large-sized enterprises, but had a direct effect on small and medium enterprises (SMEs). Besides, the more R&D experiences in NLPDPs, the more positive impacts were generated on the successful market introduction and sales of new products in SMEs, metal and mechanics industries, consumer goods, and chemical industries. Regarding the type of industries, government subsidies did not have an obvious effect on information and electronics industries, but was very helpful to the metal and mechanics industries, consumer goods, and chemical industries, which are mainly focused on OEM operations.