English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 80990/80990 (100%)
造訪人次 : 41633872      線上人數 : 3962
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋


    請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/60117


    題名: App應用在電子商務的推薦服務-以P公司為例;The App Implementation of Recommender System for E-Commerce Website: A Case Study of P E-Commerce Company
    作者: 黃正賢;Huang,Cheng-Hsien
    貢獻者: 資訊管理學系在職專班
    關鍵詞: 隱性回饋;協同過濾;Implicit Feedback;Collaborative Filtering;Apache Mahout
    日期: 2013-06-25
    上傳時間: 2013-07-10 12:07:07 (UTC+8)
    出版者: 國立中央大學
    摘要: 因智慧型手機與平板電腦的普及,再加上行動上網的便利,消費者持有著智慧型手持裝置的比例更是逐年提高,改變了消費者使用智慧型手持裝置的行為與生活型態,而智慧型手持裝置已成為民眾生活裡資訊與服務傳遞重要的媒介,這不僅改變民眾的生活型態,也將促使新的行動商務發展。這讓電子商務網站得更用心地思考該如何吸引消費者,以及如何進一步做好顧客經營以提高顧客忠誠度。
    在電子商務領域中推薦系統被廣泛的利用,推薦系統可以在三方面增進電子商務的銷售量,分別是讓瀏覽者成為購買者、提供交叉銷售及提升忠誠度。因此,本研究採用協同過濾式推薦系統,依據使用者在App中的瀏覽時間、瀏覽歷程與點選操作動作,透過評比機制取得使用者對各類別的喜好輪廓,再針對所推測出的使用者喜好類別,發送特定的通知 (Notification) 訊息,通知中提供更好的服務資訊或選出適合使用者的商品資訊加以推薦,藉此提高消費者滿意度並掌握其消費動向。本研究所計算出的使用者輪廓,其所發送的筆數較少且點閱率高,可達到較高的效益。

    For the popularity of smartphones and tablet PCs, as well as the convenience of the mobile Internet, consumers who hold the proportion of smart handheld devices has increased annually, it changes the behavior and lifestyle of people using smart handheld devices. Therefore, the smart handheld devices have become the important medium for people to share the information and deliver the service, which not only changes the lifestyle of the people, but also accelerate the new mobile commerce development. E-commerce websites supplier must think how to attract consumers more carefully, and how to handle customers’ management to increase customer loyalty.
    E-commerce recommender system is widely applied in the E-commerce field, and the recommender system can promote e-commerce sales with three advantages respectively, which includes enabling browsers into buyers, cross-sell and enhance loyalty. Therefore, this study uses a collaborative filtering recommender system, on the basis of user browsing time in the App, browsing history and click to evaluate the user’s preferences by appraisal mechanism contour, and then send the notification message to the inferred user categories. The recommended notification with superior information or selected more proper product for the customers to reinforce their satisfaction and master the consumption trend. The customers’ data sent by the Institute calculated with less click through rate can achieve a higher efficiency.
    顯示於類別:[資訊管理學系碩士在職專班 ] 博碩士論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    index.html0KbHTML920檢視/開啟


    在NCUIR中所有的資料項目都受到原著作權保護.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 隱私權政策聲明