運用貝氏網路於商品推薦之研究

Applying Bayesian Network in Product Recommendation

楊志輝(Yang Chi-Hui)

指導教授 ： 陳灯能

國立屏東科技大學/管理學院/資訊管理系所/碩士(2011年)

https://doi.org/10.6346/NPUST.2011.00030

摘要

隨著電子商務的日漸普及，愈來愈多的消費者選擇藉由線上購物的方式來進行消費，然而網路商店並不像傳統的商店會有店員協助進行商品的介紹，也因此網路商店上的自動化推薦機制的相關研究愈來愈受到重視。本研究結合創新接受理論與貝氏網路，建置商品推薦系統，研究並分成技術面及行為面兩大觀點進行實證，結果發現本研究之推薦系統所推薦的商品符合消費者需求的機率大約是70%上下，對於產品推薦具有顯著的效果；在行為面的實證方面，本研究發現消費者創新接受程度及網路購物生活型態對推薦系統的使用態度及使用意願具有正向的影響關係。

關鍵字

貝氏網路 ； 推薦系統 ； 創新接受程度 ； 網路購物生活型態

並列摘要

In recent years, consumers changed their shopping behavior gradually. They don’t limit to the physical store to buy but spend more time and money on the e-stores. More and more consumers change their consumption patterns by online shopping to replace the traditional way. Therefore, recommendation system is getting more and more popular in e-stores, because it can assist consumers shopping. In this research, we use an easy way to collect consumer-related data and combined Bayesian Network to build a product recommendation system. We tried to combine innovativeness and Bayesian Network to reduce the complexity on building of recommendation system. We also use acceptance of innovation and internet shopper lifestyle to evaluate their impacts on the attitude and behavior intention of recommendation systems. The results show that our Bayesian based recommendation system has good precision on recommending results.

並列關鍵字

Bayesian network ； Recommender System ； Acceptance of innovation ； Internet shopper lifestyle

參考文獻

吳偉文 "運用 PLS 探討兩岸三地千大公司經營指標之特徵," 東亞論壇:457) 2007, pp 13-23.

Ahuja, M., Galletta, D., and Carley, K. "Individual centrality and performance in virtual R&D groups: An empirical study," Management Science (49:1) 2003, pp 21-38.

Anderson, J., and Gerbing, D. "Structural equation modeling in practice: A review and recommended two-step approach," Psychological bulletin (103:3) 1988, pp 411-423.

Ansari, A., Essegaier, S., and Kohli, R. "Internet recommendation systems," Journal of Marketing Research (37:3) 2000, pp 363-375.

Balabanovi, M., and Shoham, Y. "Fab: content-based, collaborative recommendation," Communications of the ACM (40:3) 1997, p 72.