透過您的圖書館登入
IP:3.145.42.94
  • 學位論文

基於網頁點擊之序列探勘的交易推薦機制

Purchase Recommendations Based on Web Click Sequence Mining

指導教授 : 薛夙珍
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


在現今的電子商務環境之下,有著眾多的電子商務網站供使用者選擇,卻也降低了使用者對於網站之忠誠度。因此企業間為了因應商業競爭激烈,紛紛使用客戶關係管理策略,其中最常被使用的方法之一,就是「推薦系統(Recommendation system)」。利用推薦系統可減少客戶搜尋商品所耗之時間成本,並且可引導使用者對於企業特定欲銷售之商品的關注力,達成行銷策略中的目標市場行銷。此外,多數的大型電子商務網站已有多年的經營歷史,網站除了擁有交易資料,還有大量的網站瀏覽記錄,這些顧客的點擊順序,往往呈現使用者的消費意願。若能找出這些資料之間所隱含的消費傾向與習慣,將有助於網路行銷成效的提升。因此,本研究所提出的方法以點擊序列的時間先後順序來設定權重,並以滑動視窗(Sliding window)模型,將已有成交紀錄的顧客在不同時間區段內的點擊序列(Click sequence)作訓練分析,找出有效購買的點擊路徑。所提出的方法,透過實驗之呈現顧客瀏覽網頁的循序型別與購買交易決策的關聯性之綜整分析,掌握顧客動態的偏好特性,提升推薦效能。

並列摘要


The sheer volume of E-Commerce sites today provides vast amount of selections for customers but also reduces the loyalty of customers. Many enterprises have used customer relationship management to face the fierce competition and recommendation systems are widely used for customers’ retention. Recommendation systems may reduce the searching time cost of customers and direct users to the targeted products specified by the enterprises. That is, recommendation systems may increase the power of targeted marketing. In adition, a vast amount of operational data has been accumulated in e-commerce websites. These web-logs collect not only the committed transactions but also the clicking sequences, which indicates the consumers’ purchasing desire and thinking logic. Mining these data may reveal excellent target marketing strategies by exploring the relationships between a consumer’s tendency and his/her clicking path. We propose an approach to adaptively adjust the weights of clicking sequences as time goes by. The approach uses a sliding window model, mines successful purchasing sequences from previous transactions, and discovers effective purchasing paths from sequences of different time periods. Experimental results report the relation of customer browsing sequences and purchasing transaction analysis, increase effectiveness of recommendations and marketing campaign by considering customer’s dynamic preferences.

參考文獻


2.李御璽與顏秀珍(2008),「網路交易型樣探勘技術之研究」,電子商務學報,第10卷,第4期,第989-1008頁。
4.胡雅涵(2007),使用以限制為基礎的序列規則方式的顧客購買行為研究,博士論文,國立中央大學資訊管理系,高雄。
11.黃純敏、林重佑、黃進瑞(2013),「結合學習向量量化與協同過濾之交換混合式過濾電影推薦架構」,資訊管理學報,第二十卷,第四期,第423-448頁。
20.Agrawal, Rakesh, Imieliński, Tomasz, and Swami, Arun(1993), "Mining association rules between sets of items in large databases," ACM SIGMOD Record, Vol. 22, No. 2, pp. 207-216.
21.Chang, Joong Hyuk(2011), "Mining weighted sequential patterns in a sequence database with a time-interval weight," Knowledge-Based Systems, Vol. 24, No. 1, pp. 1-9.

延伸閱讀