(34.229.64.28) 您好!臺灣時間:2021/05/06 06:49
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:黃升煌
研究生(外文):Sheng-Huang Huang
論文名稱:以顧客動態購買興趣樣式為基礎並考慮產品利潤之協同推薦系統
論文名稱(外文):A Profit-Based Collaborative Recommender System Using the Dynamic Customer Profile
指導教授:黃承龍黃承龍引用關係
指導教授(外文):Cheng-Lung Huang
學位類別:碩士
校院名稱:國立高雄第一科技大學
系所名稱:資訊管理所
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2009
畢業學年度:97
語文別:中文
論文頁數:103
中文關鍵詞:興趣輪廓檔序列樣式推薦系統利潤探勘
外文關鍵詞:ProfilesSequential PatternRecommender SystemProfit Mining
相關次數:
  • 被引用被引用:7
  • 點閱點閱:627
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:256
  • 收藏至我的研究室書目清單書目收藏:0
推薦系統普遍應用在電子商務、知識管理、文件管理等領域,為了改善傳統的推薦系統的推薦品質,本研究將「時間」與「利潤」兩個因素加入推薦系統的運作,提出「以顧客動態購買興趣樣式為基礎並考慮產品利潤」之協同推薦系統,主要目的為偵測出客戶隨著時間變異而改變的購買行為,進而在正確的時間推薦正確的商品給顧客,並站在廠商的立場上加上利潤考量,企圖在不失去推薦準確度的狀況下,產生更高的利潤,造成顧客與企業雙贏的局面。
本研究提出RFP AprioriAll演算法,將傳統AprioriAll序列樣式探勘演算法加入「時間」與「利潤」兩個因素,用來產生更具有意義的顧客購買行為之序列樣式;並且搭配考量利潤的協同推薦系統架構,進一步提高銷售的利潤。
本研究所設計的推薦系統包含五個主要步驟:(1)建立顧客的動態興趣輪廓檔、(2)使用分群演算法將顧客分群、(3)使用RFP AprioriAll序列樣式演算法來預測顧客未來感興趣的產品分類、(4)根據序列樣式支持度與利潤計算產品類別分數和(5)依據前幾名產品分類下的產品熱門程度與利潤計算分數並做出最後個人化的產品推薦。
本研究使用IBM Almaden Research Center提供的Assoc.gen模擬程式產生模擬的顧客交易行為紀錄和真實世界中的超市資料庫(FoodMart)作為實驗的資料來源,進行預測目標顧客未來的購買行為,預測結果經無母數統計檢定得到以下結論:在顧客的購買行為會隨著時間變異而改變的條件下,本研究提出之推薦系統架構能在推薦準確度沒有顯著變化的情況下,明顯增加銷售的利潤。
This study propose a sequential pattern based collaborative recommender system, which adds “time” and “profit” factors to the operation of the recommender system to improve the quality and profit performances of the collaborative recommender systems. The purposes of this study are to detect the customer time-variant buying behavior, and then to recommend the right products and high profit products to the right customers in the right time.
To recommend the right products and high profit products, this study proposed a RFP Apriori algorithm that considered the last purchasing time (recency) and the product profit, to discover the RFP-Patterns, and combine to a profitable recommender system.
The framework of system includes five steps: (1) create dynamic customer profile, (2) find the k nearest neighbors using a clustering algorithm, (3) predict product category using the RFP AprioriAll sequential pattern algorithm, (4) compute the product category score and select Top-M product category, and (5) compute the Top-N product item score and recommend Top-I product item to the target customers.
This study used a food mart and simulated database to examine the performance of the proposed approach and compared it with the Top-N recommendation. The recommendation accuracy is similar to the Top-N recommendation, but the profit of the proposed system is much better than that of the Top-N recommendation.
摘要 i
Abstract ii
致謝 iii
目錄 iv
表目錄 vii
圖目錄 ix
壹、緒論 1
一、研究背景與動機 1
二、研究目的 3
三、研究範圍與限制 3
四、研究流程 3
五、論文架構 4
貳、文獻探討 5
一、推薦系統 5
(一) 內容過濾式推薦系統 5
(二) 協同過濾式推薦系統 7
(三) 混合式推薦系統 12
(四) 推薦系統相關研究 13
二、群集分析 14
(一) K-means分群演算法 15
三、RFM分析 16
四、利潤探勘 17
五、序列樣式探勘 18
(一) AprioriAll演算法 18
1. 排序(sort)階段 19
2. 大型項目集(Litemset)階段 19
3. 轉換(transformation)階段 19
4. 序列(sequence)階段 19
5. 最大(maximal)序列階段 19
六、RFM-Apriori演算法 23
参、系統架構 25
一、RFP AprioriAll演算法 25
(一)RFP AprioriAll演算法步驟 26
(二)實例說明RFM AprioriAll演算步驟 28
1. 產生大型1-候選序列並計算其支持度 28
2. 移除支持度與利潤較低的候選序列 28
3. 計算大型2-候選序列並移除支持度低的序列 31
(一)模型建立階段 34
1. 計算產品利潤與產品類別之平均利潤 34
2. 建立顧客的動態興趣輪廓檔(Dynamic Customer Profile) 34
3. 利用分群演算法將動態輪廓檔分為k群 35
4. 針對各群顧客過去一段期間的交易類別產生序列樣式集合 36
(二)產生推薦階段 36
1. 選擇目標顧客 37
2. 建立目標顧客的動態興趣輪廓檔 37
3. 計算目標顧客所屬群集 37
4. 針對目標顧客過去的交易類別計算候選序列樣式集合 37
5. 比對顧客所屬群集之序列樣式與候選樣式預測顧客興趣之類別 38
6. 以類別利潤與顧客興趣為基礎計算並產生TopM推薦類別 38
7. 從推薦類別中以產品利潤與項目熱門程度產生TopN推薦項目 40
8. 從M N個推薦項目中依照產品分數產生TopI推薦項目 41
(三)實例說明本研究提出之推薦系統架構 42
肆、實驗展示 47
一、實驗資料來源 47
(一) 模擬資料集 47
(二) 真實世界資料集 48
二、實驗環境 49
三、實驗設計 49
(一) 本研究提出之系統架構 49
(二) 傳統推薦方法 50
(三) 系統參數說明 50
四、實驗評估指標 52
五、模擬資料集之實驗與結果 53
(一) 系統建構參數說明 53
1. 建立顧客的動態興趣輪廓檔 53
2. 利用分群演算法將動態輪廓檔分為k群 53
3. 針對各群顧客過去一段期間的交易類別產生序列樣式集合 54
4. 以類別利潤與顧客興趣為基礎計算並產生TopM推薦類別 54
5. 從推薦類別中以產品利潤與項目熱門程度產生TopN推薦項目 54
6. 從M N個推薦項目中依照產品分數產生TopI推薦項目 54
(二) 實驗結果分析與討論 55
1. 比較RFPP、Collaboration與Random 55
2. 比較*F**、 RF**與*FPP 57
3. 比較RF*P、RFP*和RFPP 59
4. 無母數檢定 61
六、真實世界資料集之實驗與結果 63
(一) 系統建構參數說明 63
1. 建立顧客的動態興趣輪廓檔 63
2. 利用分群演算法將動態輪廓檔分為k群 63
3. 針對各群顧客過去一段期間的交易類別產生序列樣式集合 64
4. 以類別利潤與顧客興趣為基礎計算並產生TopM推薦類別 64
5. 從推薦類別中以產品利潤與項目熱門程度產生TopN推薦項目 64
6. 從M N個推薦項目中依照產品分數產生TopI推薦項目 64
(二) 實驗結果分析與討論 65
1. 比較RFPP、Collaboration與Random 65
2. 比較*F**、 RF**與*FPP 67
3. 比較RF*P、RFP*和RFPP 69
4. 無母數檢定 71
七、敏感度分析 72
(一)Recency分析 73
(二)Gap分析 75
(三)Weight分析 77
(四)Profit分析 79
(五)推薦數量分析 81
伍、結論 83
一、學理上的貢獻 84
二、應用面的貢獻 84
三、未來研究方向 84
參考文獻 86
1.林朝興、唐瑩荃,2005,應用RFM 模組與權重漸進探勘使用者最近習慣進行協力式推薦,2005年NCS全國計算機會議,崑山科技大學。
2.吳志宏,2004,以隱性回饋為基礎的自動化推薦機制,朝陽科技大學資訊管理研究所碩士論文。
3.周寬怡,2003,以內容分析法獲取推薦系統中使用者profile之研究,國立成功大學資訊管理研究所碩士論文。
4.許耀文,2004,序列型樣快速探勘演算法,南台科技大學資訊管理研究所碩士論文。
5.黃承龍、黃維良,2006,具有「隨時間變異的顧客購買興趣」預測能力之協同推薦系統,第十二屆資訊管理暨實務研討會,虎尾科技大學。
6.黃維良,2007,具有「隨時間變異的顧客購買興趣」預測能力之多階層協同式推薦系統,國立高雄第一科技大學碩士論文。
7.張哲銘,2003,以使用者偏好分類為基礎之網際資源推薦系統,國立台灣大學資訊管理研究所碩士論文。
8.Adomavicius, G., and Tuzhilin, A., “Towards the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions” IEEE Transactions on Knowledge and Data Engineering, 2005, Vol. 17, No. 6, pp. 734-749.
9.Agrawal, R., and Srikant, R., “Mining sequential patterns” IEEE International Conference on Data Engineering, 2005, pp.3-14.
10.Agrawal, R., and Srikant, R., “Mining sequential patterns: generalizations and performance improvements” Proceedings of the 6th International Conference on Extending Database Technology (EDBT), March 1996, pp. 3–17.
11.Ayres, J., Flannick, J., Gehrke, J., Yiu, J., “Sequential PAttern mining using a bitmap representation” Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining, 2002, pp:429-435.
12.Balabanovic, M., and Shoham, Y., “Fab:content-based, collaborative recommendation” Communications of the ACM, 1997, Vol. 40, No.3, pp.66-72.
13.Breese, J.S., Heckerman, D., and Kadie, C., “Empirical Analysis of Predictive Algorithms for Collaborative Filtering” Proceedings of the 14th Annual Conference on Uncertainty in Artificial Intelligence, 1998, pp.43-52.
14.Boucher-Ryan, P.D., and Bridge, D., “Collaborative Recommending using Formal Concept Analysis” Knowledge-Based Systems, 2006, pp.309-315.
15.Chen, L.-S., Hsu, F.-H., Chen, M.-C., Hsu, Y.-C., “Developing recommender systems with the consideration of product profitability for sellers” Information Sciences: an International Journal, 2008, Volume 178, pp. 1032-1048.
16.Chen, Y., Zhao, Y., and Yao Y., “A Profit-based Business Model for Evaluating Rule Interestingness” Advances in Artificial Intelligence, 2007, Volume 4509, pp. 296-307
17.Chen, Y.L., Kuo, M.H., Wu, S.Y., Tang , K., “Discovering Recency, Frequency, and Monetary(RFM) Sequential Patterns from Customers’ Purchasing Data” Electronic Commerce Research and Applications, 2009.
18.Cheung, K.W., Tsui, K.C., and Liu, J., “Extended Latent Class Models for Collaborative Recommendation” IEEE Transactions on Systems, Man, and Cybernetics – Part A:Systems and Humans, 2004, Vol. 34, No.1, January.
19.Cho, Y.B., Cho, Y.H., and Kim, S.H., “Mining changes in customer buying behavior for collaborative recommendations” Expert System with Applications 28, 2005, pp. 359-369.
20.Chun-Jung Chu, Vincent S. Tseng, Tyne Liang, “An efficient algorithm for mining temporal high utility itemsets from data streams”, Journal of Systems and Software, Vol. 81, Issue 7, 2008, pp. 1105-1117.
21.Davies, D.L., and Bouldin, D.W., “A Cluster Separation Measure” IEEE Transaction on Pattern Analysis and Machine Intelligence, 1979, Vol. 1, No. 2, pp.224-227.
22.Goldberg, D., Nichols, D., Oki, B.M., and Terry, D., “Using Collaborative Filtering to Weave an Information Tapestry” CACM, 1992, Vol. 35, No.12, pp.61-70.
23.Haruechaiyasak, C., Tipnoe, C., Kongyoung, S., Damrongrat, C., and Angkawattanawit, N., “A Dynamic Framework for Maintaining Customer Profile in E-Commerce Recommender Systems” IEEE International Conference on e-Technology, e-Commerce and e-Service, 2005.
24.Hirooks, Y., Terano, T., and Otsuka, Y., “Recommending Books of Revealed and Latent Interests in E-Commerce” Industrial Electronics Society, 2000. IECON 2000. 26th Annual Conference of the IEEE, Vol. 3, 1632-1637.
25.Huang, Chen-Lung and Huang, Wei-Liang “Handling sequential pattern decay: Developing a two-stage collaborative recommender system” Electronic Commerce Research and Applications, Vol. 8, Issue 3, 2009, pp. 117-129.
26.Hughes,A. M., Strategic Database Marketing, 1994, Chicago, Probus Publishing.
27.Kim, J.K., Cho, Y.H., Kim, W.J., Kim, J.R., and Suh, J.H., “A personalized recommendation procedure for Internet shopping support” Electronic Commerce Research and Applications, 1, 2002, pp.301-313.
28.Krulwich, B., and Burkey, C., “Learning user information interests through extraction of semantically significant phrases” Proceedings of the AAAI Spring symposium on Machine Learning in Information Access, 1996.
29.Lang, K., “Newsweeder: Learning to Filter Netnews” Proceedings of the Machine Learning conference, Tahoe City, Calif, 1995, pp. 331-339.
30.Li, L. H., Lee, F. M. and Liu, W. J.,“The Timely Product Recommendation Based on RFM Method,” Proceedings of International Conference on Business and Information, Singapore, 2006.
31.Linden, G., Smith, B., and York, J. “Amazon.com recommendations: item-to-item collaborative filtering” IEEE Internet Computing, 7(1), 2003, pp.76-80.
32.MacQueen, J. B. “Some Methods for classification and Analysis of Multivariate Observations” Proceedings of 5-th Berkeley Symposium on Mathematical Statistics and Probability, Berkeley, University of California Press, 1967, 1:281-297.
33.Maulik, U. and Bandyopadhyay, S. “Genetic Algorithm-Based Clustering Technique” Pattern Recognition, 33, 2000, pp.1455-1465.
34.Min, S.H., and Han, I. “Detection of the customer time-variant pattern for improving recommender systems” Expert Systems with Applications, 28, 2005, pp.189-199.
35.Mock, and Vemuri, “Information Filtering Via Hill Climbing, Wordnet, and Index Patterns” Information Processing & Management, Vol. 33, No. 5, 1997, pp.633-644.
36.Pei, J., Han, J., Mortazavi-Asl, B., Wang, J., Pinto, H., Chen, Q., Dayal, U., Hsu, M.C. “Mining sequential patterns by pattern-growth: the PrefixSpan approach” IEEE Transactions on Knowledge and Data Engineering 16 (11), 2004, 1424-1440.
37.Pei, J., Han, J., Pinto, H., Chen, Q., Dayal, U., Hsu, M.C., “PrefixSpan: Mining sequential patterns efficiently by prefix-projected pattern growth” in: Proceeding of the 2001 Int''l Conf on Data Engineering (ICDE'' 01), Heidelberg, Germany, 2001.
38.Perugini, S., Concalves, M.A., and Fox, E.A, “Recommender Systems Research: A Connection-Centric Survey” Journal of Intelligent Information Systems, Vol. 23, No.2, 2004, pp.107-143.
39.Rashid, A.M., Albert, I., Cosley, D., Lam, S.K., McNee, S.M., Konstan, J.A., and Riedl, J. “Getting to know you: learning new user preferences in recommender systems” Proceedings of the IUT 02, San Francisco, CA, 2002, pp.127-134.
40.Resnick, P., Iacovou, N., Suchak, M., Bergstrom, P., and Riedl, J. “GroupLens: an open architecture for collaborative filtering of Netnews” Proceedings of the CSC Wconference, Chapel Hill, NC, 1994, pp.175-186.
41.Roberts M. L., “Expanding the Role of the Direct Marketing Database,” Journal of Direct Marketing, 1992, 6, pp.51-60.
42.Rucher, J., and Polanco, M.J. “Personalized navigation for the Web” Communications of the ACM, March, 40(3), 1997, pp. 73-75.
43.Sarwar, B., Karypis, G., Konstan, J., and Riedl, J. “Analysis of Recommendation Algorithms for E-Commerce” Proceedings of the ACM E-Commerce Conference, 2000, pp. 158-167.
44.Schafer, J.B., Konstan, J. and Riedl, J., “Recommender Systems in E-Commerce” ACM Conference on E-Commerce, 1999, p.158-p.166.
45.Shardanand, U., and Maes, P. “Social Information Filtering: Algorithms for Automating ‘Word of Mouth’” Proceedings of the Conference on Human Factors in Computing Systems (CHI95), 1995, pp. 210-217.
46.Ujjin, S., and Bentley, P.J., “Particle Swarm Optimization Recommender System” Swarm Intelligence Symposium, 2003. SIS ''03. Proceedings of the 2003 IEEE.
47.Wang, K., and Su, M.-Y., “Item Selection by "Hub-Authority" Profit Ranking” Conference on Knowledge Discovery in Data, 2002, pp. 652 – 657
48.Wang, K., Zhou, S., and Han, J., “Profit Mining: From Patterns to Actions” Lecture Notes in Computer Science, Vol. 2287, 2002, pp.70-87
49.Wang, K., Zhou, S., Yang, Q., Yeung, M.-S., “Mining Customer Value: From Association Rules to Direct Marketing” Data Mining and Knowledge Discovery, Volume 11. Number 1, 2005, pp. 57 – 79
50.Wang, Y. F., Chuang, Y. L, Hsu, M. H., and Keh, H. C. “A personalized recommender system for the cosmetic business” Expert Systems with Applications, 26, 2004, pp.427-434.
51.Xu Xiujuan, Jia Lifeng, Wang Zhe, Zhang Hongyan, Liang Shuang, Zhou Chunguang “Fast algorithm for mining item profit in retails based on microeconomic view” 2005 International Conference on Cyberworlds (CW''05), 2005, pp.349-353.
52.Yang, W., Wang, Z., and You, M., “An improved Collaborative Filtering Method for Recommendations’ Generation” 2004 IEEE International Conference on Systems, Man and Cybernetics, 2004.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊
 
系統版面圖檔 系統版面圖檔