應用分群技術於網路產品促銷策略之研究

Implementing Clustering Technique in Internet-Product Sales Promotion Strategies

賴宏文(Hung-Wen Lai)

指導教授 ： 詹智強

朝陽科技大學/理工學院/工業工程與管理系/碩士(2009年)

摘要

隨著網際網路的普及、電子商務市場的快速發展，愈來愈多的實體通路廠商投身到網際網路中尋找商機，並將原先的經營模式轉移至網路購物上。因此，網路購物商店要如何在眾多的競爭者中吸引消費者的目光，進而促使消費者購買產品，就得靠良好的產品促銷策略來達成此目標。
本研究將根據顧客RFM分析模型為基礎，延伸為產品RFM分析模型，將某3C電子交易網站所提供之產品歷史交易資料以產品RFM分析模型轉換成三維的產品價值，再以粒子群最佳化演算法（Particle Swarm Optimization）進行產品分群，並驗證分群後的群體特性與提出的促銷策略做搭配是否合適；達到縮短決策產品促銷的時間、提升產品購買率與產品獲利的目標，依此建立起各網路購物產品群體特性所合適的促銷策略之模式。

關鍵字

促銷策略 ； 粒子群最佳化演算法 ； 產品價值 ； RFM分析模型 ； 產品分群 ； 資料探勘

並列摘要

With the popularization of the Internet and the rapid development of the E-commerce market, more and more physical channels look for new business via the Internet and transfer the early physical business model into the Internet shopping. Therefore, online stores rely on outstanding product sales promotion strategies to catch consumers’ attention and increase their purchase opportunities.
In this thesis, by using the customer RFM analysis model and product RFM analysis model, we transform the product history transaction data, provided by a 3C electronics online store, into the three-dimension product value. Then, we use Particle Swarm Optimization (PSO) to conduct product clustering at first and to verify that the clustered group characteristic is suitable for the presented promotion strategy in order to shorten the product-promotion decision time, raise the product-purchasing rate and get profits. Finally, based on the methodology, we establish the promotion strategy model which is suitable for different group characteristics of online shopping products.

並列關鍵字

Data Mining ； Promotion Strategies ； Product Value ； Particle Swarm Optimization (PSO) ； RFM Analysis Model ； Product Clustering

參考文獻

[32]林家五、林美慧、林裘緒，「影響消費者手機知識的前導因素與後續影響」，東吳經濟商學學報，第52期，（2006）。

[3]Batra, Rajee, Ahtola, Olli T., “Measuring Hedonic and Utilitarian Sources of Consumer Attitudes”, Marketing Letters, pp.159-171. (1991).

[4]Boris Snoj, Aleksandra Pisnik Korda, Damijan Mumel, “The relationships among perceived quality, perceived risk and perceived product value”, Journal of Product & Brand Management, Vol. 13, pp.156-167. (2004).

[6]Ching-Yi Chen, Fun Ye, “Particle Swarm Optimization Algorithm and Its Application to Clustering Analysis”, Proceedings of the 2004 IEEE International Conference on Networking, sensing & Control Taipei, Taiwn, March 21-23, pp.789-794. (2004).

[7]Dittmar, H., “The social psychology of material possessions: to have is to be”, New York: St. Martin’s. (1992).