Research on E-commerce Customer Loyalty under Big Data
AUTHORS
Kokula Krishna Hari Kunasekaran,Association of Scientists, Developers and Faculties (ASDF), United Kingdom
ABSTRACT
Based on the characteristics of the e-commerce industry, this paper conducts a comprehensive analysis of the factors affecting the e-commerce customer loyalty. Based on the classic RFM customer loyalty model, two important attributes that affect customer loyalty in e-commerce are introduced: satisfaction and attention, thereby establishing a RFMSA e-commerce customer loyalty partition model. In this model, the basis for dividing customer loyalty in e-commerce transactions is analyzed more comprehensively from multiple perspectives. Based on the establishment of a customer loyalty model for e-commerce, the customer loyalty is divided by a cluster analysis algorithm. Based on the classic clustering algorithm K-means, an improved algorithm to determine the initial clustering center by segment was proposed to divide customer loyalty. This method can effectively reduce the time to determine the initial cluster center and the problem of local optimal solution caused by iterative calculation. In order to verify the effectiveness of the algorithm proposed in this paper, the customer loyalty is divided by analyzing the transaction data of an online mall member. The experimental results show that, compared with the K-means-based clustering algorithm, the improved method proposed in this paper has higher accuracy in the classification of e-commerce customer loyalty and can better segment the e-commerce customer loyalty.
KEYWORDS
Customer loyalty, RFMSA, K-means
REFERENCES
[1] Liu Qingwei, “Research on the application and implementation strategy of precision marketing system in mobile value-added services,” Master’s Thesis of Beijing University of Posts and Telecommunications, pp.8-9, (2013)
[2] Du Le., “Research on customer classification of B2C E-commerce enterprises,” Master thesis of North China University of Technology, pp.8-9, (2014)
[3] Field. “Data analysis of online shopping market questionnaire based on data mining technology,” Jilin University Master Thesis, pp.10-12, (2014)
[4] Sherif and Cantril, “The psychology of ego ~ involvements,” Social Attitudes and Identifications (Book Review) Schermerhorn, R A. Social Forces 26, vol.1, pp.362, (1947)
[5] Carvajal, Sara Arancibia, and Ruzzi, “Focusing resources for customer loyalty: An application to the Chilean banking industry,” African Journal of Business Management, vol.1, pp.1100-1108, (2012)
[6] Tung and Feng Cheng, “Customer satisfaction, received value and customer loyalty: the mobile services industry in China,” African Journal of Business Management, vol.5, pp.1730-1737, (2013)
[7] Wang Zhong, Liu Guiquan, and Chen Enhong, “A K ~ mkuoeans algorithm for optimizing the initial center point,” Pattern Recognition and Artificial Intelligence, vol.22, no.2, pp.300-304, (2009)
[8] Rokham Hooman and Falakshahi Hale, “Web users clustering analysis,” International Journal of Computer Science and Information Security, vol.9, pp.49-52, (2014)
[9] Mortezapour Reza, and Afzali Mehdi, “Assessment of customer credit through combined clustering of artificial neural networ, genetics algorithm and Bayesian probabilities,” International Journal of Computer Science and Information Security, vol.12, pp.53-57, (2013)