簡易檢索 / 詳目顯示
| 研究生： |
李姿瑩 Tzu-Ying Li |
|---|---|
| 論文名稱： |
以交易數量為基礎之加權關聯規則 Quantity-based association rules with weights |
| 指導教授： |
曾富祥
Fu-Shiang Tseng |
| 口試委員: | |
| 學位類別： |
碩士 Master |
| 系所名稱： |
管理學院 - 工業管理研究所 Graduate Institute of Industrial Management |
| 論文出版年： | 2015 |
| 畢業學年度： | 103 |
| 語文別： | 英文 |
| 論文頁數： | 57 |
| 中文關鍵詞： | 資料挖礦 、關聯規則 、加權式關聯規則 、交易數量為基礎之關聯規則 |
| 外文關鍵詞： | Data Mining, Association Rules Mining, Quantity-based ARM, Weighted ARM |
| 相關次數： | 點閱：11 下載：0 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
所謂挖掘關聯規則，是要從企業銷售交易資料庫中，找出項目之間的關聯性。過去大部份研究所找出的關聯規則通常只能表達項目間有否相關，卻無法表達它們在不同購買數量時的相關性，也忽略掉每項商品會因其利潤大小帶來不同重要性。真實世界往往是兩種資料都記錄的，而傳統關聯規則方法卻只使用了部份的資料來推導規則，這意味著我們只能得出部份的資訊來創造出部份的價值。如此所產生的問題是，我們將無法知道該以什麼樣的比例來搭配不同產品一齊販售，也無法得知該項搭配是否能為公司帶來利潤。因此若關聯規則能加入項目數量及利潤資訊的話，將非常有益於制訂行銷策略。
本文提出，以權重值大小表示為該筆交易紀錄之重要性，其中，於單筆交易紀錄中，每賣出一樣商品所獲得的利潤作為該筆交易紀錄的權重值，取代傳統關聯規則方法只在意商品有否被購買的想法，並依購買數量出現次數將商品作分割可以找尋出包含項目數量的關聯規則，本篇研究將利用指定項目數量的區間以權重的方式找出更具有意義的關聯規則。
Association Rule is an important type of knowledge representation revealing implicit relationships among the items present in large number of transactions. The traditional association rules mining apply binary execution. It cares about the attendance and absence of items in the transaction all along. Recent research shows that traditional mining method is not so realistic and it might be lost some important patterns. The patterns include the information from profit and purchased quantity of items that would also cause the meaning of transaction records are the same.
In our study, according to the different profit and purchased quantity of items in the transaction, the importance of each record should be different. We are going to modify Apriori Algorithm into non-binary way with weights. Which emphasizes the importance of the quantity, we use the separation methods to divide items into segmentations. Since the usage of the ignored data, we receive more information in detail with the results of the Quantity-based association rules. These rules bring the information that includes not only the occurrence relationship of the items but also the profit relationship for the business. We get the more specific relationship with the purchased situation than before.
1. Adhikari, A. and P.R. Rao, “Association Rules Induced by Item and Quantity Purchased”, Springer-Verlag Berlin Heidelberg, pp. 478–485, 2008.
2. Brin, S., R. M. and C. S., “Beyond Market Baskets: Generalizing Association Rules to Correlations”, ACM, 1997.
3. Cai, C. H., A. W. C. Fu, Cheng and W.W. Kwong, “Mining Association Rules with Weighted Items”, Department of Computer Science and Engineering, The Chinese University of Hong Kong.
4. Chen, J., L. Kai, H. Haishan and X. Shasha, “Association Rules Mining Algorithm Based on Interest Measure And Its Application In Medical Audit”, International Clinical Studies Support Center(ICSSC), 2013.
5. Chi, X. and Z. W. Fang, “Review of Association Rule Mining Algorithm in Data Mining”, IEEE, 2011.
6. Dhanda, M., “An Approach To Extract Efficient Frequent Patterns From Transactional Database”, International Journal of Engineering Science and Technology, Vol. 3, July 2011.
7. Ibrahim, S. P. S. and J. S. Revathy, “A Novel Quantity based Weighted Association Rule Mining”, International Journal of Engineering Inventions, Vol.4, pp. 33-38, August 2014.
8. Khan, M. S., M. Muyeba and F. Coenen, “Weighted Association Rule Mining from Binary and Fuzzy Data”, Springer-Verlag Berlin Heidelberg, pp. 200–212, 2008.
9. Kumar, G. P. and A. Sarkar, “Weighted Association Rule Mining and Clustering in Non-Binary Search Space”, IEEE, Seventh International Conference on Information Technology, 2010.
10. Kumar, P. and A. VS, “Discovery of Weighted Association Rules Mining”, IEEE, 2010.
11. Liaquat, M.s., T. Basit and M.A.H Syed, “Interesting Measures for Mining Association Rules”, IEEE, 2004.
12. Liu, B., W. H., W. Ke and C. Shu, “Visually Aided Exploration of Interesting Association Rules”,Springer-Verlag Berlin Heidelberg,pp. 380-389, 1999.
13. Martin, D., A. Rosete and J. A. Fdez, “A New Multi-objective Evolutionary Algorithm for Mining a Reduced Set of Interesting Positive and Negative Quantitative Association Rules”, IEEE, Vol. 18, No. 1, 2013.
14. Ordonez, C., C. A. S. and Levien de B., “Discovery Interesting Association Rules in Medical Data”, The National Library of Medicine, 2000.
15. Rathod, A., A. Dhabariya, and C. Thacker, “An Approach to Mine Significant Frequent Patterns by Quantity Attribute”, IEEE, Fourth International Conference on Communication Systems and Network Technologies, 2014.
16. Sandhu, P. S., D. S. Dhaliwal and S. N. Panda, “Mining utility-oriented association rules: An efficient approach based on profit and quantity”, International Journal of the Physical Sciences, Vol. 6(2), pp. 301-307, January 18, 2011.
17. Sanhu, P. S., D. S. Dhaliwal, S. N. Panda and A. Bisht, “An Improvement in Apriori Algorithm Using Profit and Quantity”, IEEE, Second International Conference on Computer and Network Technology, 2010.
18. Sujatha, D. and N. CH, “Quantitative Association Rule Mining on Weighted Transactional Data”, International Journal of Information and Education Technology, Vol. 1, No. 3, 2011.
19. Tan, P. N., V. Kumar and J. Srivastava, “Selecting the Right Interestingness Measure for Association Patterns”, ACM, 2002.
20. Tao, F., F. Murtagh and M. Farid, “Weighted Association Rule Mining using Weighted Support and Significance Framework”, ACM, August 24-27, 2003.
21. Tsai, P. S. M. and C. M. Chen, “Mining Quantitative Association Rules in a Large Database of Sales Transaction”, Journal of Information Science and Engineering 17, 667-681, 2001.
22. Tsaia, P. S. M. and C. M. Chenb, “Mining interesting association rules from customer databases and transaction databases”, Information Systems, vol.29(8), pp.685-696, 2004.
23. Wu, X., C. Zeng and S. Zhang, “Efficient Mining of both Positive and Negative Association Rules”, ACM, Transaction on Information Systems, Vol. 22, No. 3, 2004.
