應用協同過濾機制於 商機撮合電子報之研究 –以食品業電子市集為例

E-newsletter for Transaction Matching by Collaborative Filtering - A Case of e-Marketplace in the Food Industry

韓双福(Shuang-Fu Han)

指導教授 ： 吳肇銘

中原大學/商學院/資訊管理研究所/碩士(2003年)

https://doi.org/10.6840/cycu200300211

摘要

隨著企業間電子商務的風潮，企業紛紛採用「電子市集」來提升交易效率。電子市集藉由大量聚集買賣雙方及交易流程的自動化，使得買方可以擴展其選購產品與服務的空間。賣方則可以擴展新市場、新客戶，並降低雙方的交易成本。而正因為「電子市集」可以為廠商同時帶來規模與範疇經濟，因此許多企業紛紛設立或加入電子市集。

目前電子市集主要是利用商品類別來撮合買賣雙方，然而其撮合出來的商品數量往往過於龐大，不僅無法協助採購人員進行有效的採購決策，更造成「資訊過載」的困擾。本研究應用個人化技術中的協同過濾(Collaborative Filtering)技術開發出一套「協同過濾式商機撮合系統」，該系統可以推薦給買家其相似群組的偏好商品，同時也幫助供應商開發潛在客戶。此外，為了增進推薦內容資訊鮮度，本研究也利用內容基礎技術來推薦相關新進商品。在呈現推薦商品方面，本研究利用電子郵件行銷的方式，將撮合結果寄送給買家，以降低買家的資訊取得成本。

本研究在經過食品業之電子市集實際驗證後，發現「協同過濾式商機撮合系統」可以提升電子市集的撮合績效，會員對於電子報也抱持著肯定的態度。本系統可以使得買家得以進行更有效的採購決策、賣家得以增加商品的曝光率，更創造出電子市集業者對於買家和供應商的附加價值。對於電子市集業者而言，本系統可以成為一種無形的策略性資源，可以幫助電子市集業者得以獲致長期的競爭力。

關鍵字

個人化 ； 協同過濾 ； 商機撮合 ； 電子市集

並列摘要

The trend of B-to-B e-commerce makes quite a few companies to improve purchase efficiency with e-marketplace. By aggregating a large number of enterprises and automating transaction process, buyers have more choices about the selection of products or services, and sellers can broaden the scope of maket and reduce the transaction costs. For the advantage of the economy of scale and scope, most of companies are very enthusiastic about the adoption or establishment of e-marketplace.

So far, e-marketplces just use the category of product to match buyers with sellers. However, the matching results are often too huge. It not only fails to help agents purchasing effectively, but also causes the problem of “Information Overloading”. This study applies “Collaborative Filtering”, a kind of web- personalization, to recommend buyers the products according to their similar group and provide sellers the potential customers. Moreover, for the “Recommandation Freshness,” this study also recommends the correlative up-to-date products by content-based approach. About the delivery of recommendation, the system will dispatch the matching results to buyers by e-newsletter.

After the empirical test in an e-Marketplace of the food industry, this study finds that “the Collaborative Filtering Matching System” can make a good matching performance for e-marketplace. Most members are satisfied with the recommendation in the e-newsletter. By this system, buyers can make superior purchase decision, sellers can benefit from the exposedness of products. Besides, it helps e-marketplace create the added value for buyers and sellers. From the standpoint of e-marketplace owner, it could be an intangible strategic resource to acquire the long-term competitiveness.

並列關鍵字

Collaborative Filtering ； Matching ； Personalization ； e-Marketplace

參考文獻

3. Anderson, P., Anderson, E., “The New E-Commerce Intermediaries”, MIT Sloan Management Review, Summer, 2002, pp. 53-62.

5. Bakos, J. Y., “The emerging role of electronic marketplaces on the Internet”, Communications of the ACM, 41(8), August 1998, pp. 35-42.

6. Balabanovic, M. and Shoham, Y., “Fab: Content-Based, Collaborative Recommendation,” Communications of the ACM, 40(3), 1997, pp. 66-72.

7. Baroudi, J.J., and Orlikowski, W.J., “A Short-Form Measure of User Information Satisfaction: A Psychometric Evaluation and Note on Use,” Journal of Management Information Systems, 4(4), 1988, pp. 44-59.

8. Berghel, H.,“Email-the good, the bad, and the ugly”. Communications of the ACM, 40(4), 1997, pp. 11-15.