進階搜尋


下載電子全文  
系統識別號 U0026-2408201123181600
論文名稱(中文) 利用線上拍賣交易資訊以增加網路賣家交易媒合機會
論文名稱(英文) Utilizing Online Auction Trading Information to Improve Matching Mechanism for Online Sellers
校院名稱 成功大學
系所名稱(中) 資訊工程學系碩博士班
系所名稱(英) Institute of Computer Science and Information Engineering
學年度 99
學期 2
出版年 100
研究生(中文) 吳奕賢
研究生(英文) Yi-Hsien Wu
學號 p76981235
學位類別 碩士
語文別 中文
論文頁數 68頁
口試委員 指導教授-盧文祥
口試委員-陳信希
口試委員-張嘉惠
口試委員-張景新
中文關鍵字 線上拍賣  C2C  交易媒合  買家意圖 
英文關鍵字 Online Auction  C2C  Auction Matching Mechanism  Buyer Intent 
學科別分類
中文摘要 網路快速的發展造就電子商務的興起,其中又以C2C (Consumer-to-Consumer)平台快速便利為眾多使用者喜愛,使用者在平台搜尋商品後,通常在交易前,具有購買意圖向賣家提出問題,但經觀察發現,隨著使用者問題愈多,會與賣家進行交易的使用者並沒有明顯上升,而使用者交易後又可能後悔或不想等待而取消訂購,不但無法讓賣家營銷增加,反而因回答使用者問題或聯絡退訂事宜造成無形中浪費時間成本。
基於上述問題,我們提出最大熵學習法(Maximum Entropy)買家媒合系統,與目前相關研究最主要的差異是採用買家的各種因素,其中包含使用者的購買意圖、價格及時間因素,以預測候選買家意圖及降低交易後糾紛的產生,進而節省賣家時間。
在實驗部份,我們提出一個正確率七成的識別器,用來識別候選買家提出的問題,而我們推薦給賣家的候選買家列表中的前五名時,有近於50%的拍賣會進行交易。這代表我們提出的方法為可用,進而幫助其大量節省時間。
英文摘要 The fast development of Web is resulting in great growth of E-Commerce. Among E-Commerce platforms, Consumer-to-Consumer (C2C) platforms become popular for consumers, because the advantage is that trading process time on these platforms is short, and any seller can supply various products or multiple identical items in one fixed price (eBay-like buy-it-now auction) to customers (buyers) at online marketplaces, e.g. eBay. Before making an order, a buyer usually has intent to ask questions about product specification, price, shipping charge, amount in stock, etc. Although online marketplaces also offer an efficient way of question-answering between buyers and sellers, actually lots of questions asked by buyers don』t result in successful trading finally and consequently waste sellers』 time of replying and opportunities of dealing with other potential sales.
Therefore, in this paper we describe a new framework based on Maximum Entropy to recommend possible buyers for a buy-it-now auction. Different from the task of price prediction for online auctions, which focused adopting seller features, our work mainly utilize buyer features, including question intents which buyers asked about products, product price, and buyer trading records. The framework utilizes the features to reduce time cost of sellers.
In our experiments, our proposed question intent identifier achieves 78% average accuracy of those identifiers is 78%. The proposed Maximum-Entropy-based framework can achieve 48% trading rate in recommending top 5 buyer candidates to seller..
論文目次 摘要.........................III
Abstract......................IV
誌謝..........................VI
第一章 介紹....................1
1.1 背景及動機.................1
1.2 研究想法...................5
1.3 論文架構...................7
第二章 相關工作................9
2.1 線上拍賣平台...............9
2.2 價格......................10
2.3 時間......................12
2.4 語言分析..................12
2.5相關工作比較...............14
第三章 方法...................15
3.1 研究概述及觀察............15
3.2 Buyer-Matching System.....20
3.2.1 系統架構................20
3.2.2 買家媒合模型............21
3.3 特徴函數說明..............22
3.3.1 候選買家問題意圖........22
3.3.2 賣家平均回覆時間差......29
3.3.3 候選買家歷史交易價格....30
3.3.4 交易處理時間差........31
第四章 實驗...................33
4.1資料集.....................33
4.1.1 拍賣案例資料............33
4.1.2 意圖關鍵詞列表..........34
4.2 評估方法..................35
4.3 比較方法..................36
4.3.1 候選買家評價............36
4.4 識別候選買家問題意圖......37
4.4.1 問題意圖識別............37
4.4.2 各種問題意圖權重設定....41
4.5 買方媒合系統..............42
4.6 討論......................46
第五章 結論與未來工作.........48
5.1 結論......................48
5.2 未來工作..................48
第六章 參考文獻...............50
附錄 A........................54
附錄 B........................57
附錄 C........................59
參考文獻 [1] Walczak, S., Gregg, D.G. and Berrenberg, J.L. (2006). Market Decision Making for Online Auction Sellers: Profit Maximization or Socialization. In Journal of Electronic Commerce Research, Vol. 7, No.4.
[2] O’Donovan, J., Smyth, B., Evrim, V. and McLeod, D. (2007). Extracting and Visualizing Trust Relationships from Online Auction Feedback Comments. In Proceedings of International Joint Conferences on Artificial Intelligence(IJCAI).
[3] Resnick, P. and Zechjuser, R. (2002). Trust Among Strangers in Internet Transactions: Empirical Analysis of eBay’s Reputation System. In Advances in Applied Microeconomics, Vol. 17, 127-157.
[4] O’Donovan, J. and Smyth, B. (2005). Trust in Recommender Systems. In Proceedings of the 10th international conference on Intelligent user interfaces(IUI).
[5] Marsh, S. (1994). Formalising Trust as a Computational Concept.
[6] Yates, A., Joseph, J., Popescu, A.M., Cohn, A.D. and Sillick, N. (2008) SHOPSMART: Product Recommendations Through Technical Specifications and User Reviews. In 17th ACM International Conference on Information and Knowledge Management (CIKM).
[7] Chang, C.-H. and Lin, J.-H. (2009). Decision support and profit prediction for online auction sellers. In Proceedings of the 1st ACM SIGKDD Workshop on Knowledge Discovery from Uncertain Data(U)
[8] Kobayashi, M. and Ito, T. (2008). A Transactional Relationship Visualization System In Internet Auctions. In Studies in Computational Intelligence(SCI).
[9]Wang, J.C. and Chiu, C.C. (2008). Recommending Trusted Online Auction Sellers using Social Network Analysis. In Expert System with Application Vol. 34, 1666-1679.
[10]Melnik, M.I. and Alm, J. (2002). Does a seller’s Ecommerce Reputation Matter Evidence from eBay. In The Journal of Industrial Economics Vol. 50, No. 3, pp. 337–349.
[11] Standifird, S.S., Roelofs, M.R. and Durham, Y. (2004). The Impact of eBay’s Buy-It-Now Function on Bidder Behavior. In International Journal of Electronic Commerce, Vol.9, No.2.
[12]Matsuo, T., Hyodo, M. and Ito, T. (2003). A Buyer Allocation Support System in First-Price Auctions. In SICE 2003 Annual Conference.
[13] Silva, A., Calais, P., Pereira, A.M., Mourão, F., Almeida, J.M., Jr., W.M. and Góes, P. (2008). A Seller's Perspective Characterization Methodology for Online Auctions. In Proceedings of the 10th international conference on Electronic commerce(ICEC).
[14] Ghani, R. (2005). Price Prediction and Insurance for Online Auctions. In Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining(KDD).
[15] Ghani, R. (2005). Predicting the End-Price of Online Auctions. In Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining(KDD).
[16] Anderson, S., Friedman, D., Milam, G. and Singh, N. (2008). Buy it Now: A Hybrid Internet Market Institution. In International Journal of Electronic Business, Vol. 9, No.2.
[17] Durham, Y., Roelofs, M.R. and Standifird, S.S. (2004). eBay's Buy-It-Now Function: Who, When and How. In Topics in Economic Analysis and Policy Vol. 4, No. 28.
[18] Wang, X., Montgomery, A. and Srinivasan, K. (2008). When Auction Meets Fixed Price: a Theoretical and Empirical Examination of Buy-It-Now Auctions. In Quantitative Marketing and Economics(QME), pp. 339-370.
[19] Standifird, S.S., Roelofs, M.R. and Durham, Y. (2004). The Impact of eBay’s Buy-It-Now Function on Bidder Behavior. In International Journal of Electronic Commerce, Vol.9, No.2.
[20]Piron, F. (1991). Defining impulse purchasing. In Advances in Consumer Research, Vol. 18, pp. 509-514
[21] Koski, N. (2004). Impulse Buying on the Internet: Encouraging and Discouraging Factors. In Frontiers of E-Business Research, Vol. 1, pp. 23-35.
[22] Giménez, J. and Màrquez, L. (2003). Fast and Accurate Part-of-speech Tagging: The SVM Approach Revisited. In Recent Advances in Natural Language Processing(RANLP).
[23] Wu, Y., Zhang, Q., Huang, X. and Wu, L. (2009) Phrase Dependency Parsing for Opinion Mining. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing(EMNLP).
[24] Liu, F., Zhao, J., Lv, B., Xu, B. and Yu, H. (2005). Product Named Entity Recognition Based on Hierarchical Hidden Markov Model. In Proceedings of the Fourth SIGHAN Workshop on Chinese Language Processing(SIGHAN).
[25] Hoffman, D.L., Novak T.P. and Peralta, M. (1998). Building Consumer Trust Online. In Communications of the ACM, Vol. 42, No. 4.
[26] Franz, J. O. and Hermann, N. (2002). Discriminative Training and Maximum Entropy Models for Statistical Machine Translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL),
[27] Chang, C.C. and Lin, C.J. (2001). LIBSVM : a library for support vector machines.
[28] Hsu, C.W., Chang, C.C. and Lin, C.J. (2003). A practical guide to support vector classification.
[29] 石崇蕾, 陳建甫(2004). C2C拍賣網站經營決策因素之分析—以兩岸主要拍賣網站為例. Master thesis, Univ. of Tamkang.
[30] 劉祐廷, 何靖遠(2009) 問答機制影響線上拍賣結果之研究. Master thesis, Univ. of National Central..
[31] 陳志明, 蔡鴻仁, 林宏漢(2008). 具備自動撮合功能之C2C雙向拍賣平台之設計與研究. Master thesis, Univ. of Ling Tung.
[32] 黃怡菁,黃華山,王怡舜(2009). 線上拍賣購物者滿意度與忠誠度影響因素之研究. Master thesis, National Changhua Univ. of Education.
[33] 周書華,吳有龍(2004) 拍賣仲介者經營拍賣網站之關鍵成功因素-基於使用者觀點, Master thesis, Univ. of I Shou.
[34] 林欣晨,虞孝成,林亭汝(2006) 台灣女性服飾精品網路拍賣之研究. Master thesis, Univ. of National Chiao Tung.

論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2011-09-05起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2011-09-05起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw