| Summary: | 碩士 === 中原大學 === 資訊管理研究所 === 91 === 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.
|
|---|
