臺灣博碩士論文加值系統

探勘頻繁項目集(frequent itemset mining)考慮的是項目集在資料庫中被購買的交易筆數，並沒有考慮交易中項目被購買的數量以及項目的利潤探勘高效益項目集(high utility itemset mining)考慮了項目的單位利潤及交易中項目購買數量，找出可以為公司賺更多錢的商品組合。而在考慮整體交易資料庫的情況下，會遺漏一些在某些時間才會經常被購買或者高效益的商品組合。因此後來的一些研究加上了時間的因素，找出跟時間有關的商品組合。在本篇論文中，我們對於交易資料庫中交易發生的時間來作為時段的區分，找出哪些連續時段會有哪些高效益項目集。另外，考慮了效益值接近但低於門檻值的項目集，此項目集稱為潛在高效益項目集，目的在於確保因為時段的切割，造成效益值分散在鄰近的時段的項目集不被忽略，當項目集與鄰近的的效益值做累加後，找出項目集在哪些時段可以帶來高效益。針對這些時段進行促銷，即可將原本為潛在高效益項目集的效益。

Frequent itemset mining considers the frequency of items appearing in a transaction database, but not the purchased quantity and the profit for an item. High utility itemset mining considers the purchased quantity and profit for an item in order to find the combination of goods that can make more money. Considering the circumstances of entire database might lose some itemset which is high utility or frequency in some time. Therefore, some research consider the factory of time to find the itemset which is dependent on time.In this paper, we propose an algorithm to find the temporal high utility itemset. We mines those transactions in that period. Also, we define the potential high utility itemset which utility is close to high utility threshold to include those itemset. We find out itemset which is high utility by cumulating its profit value. Finally sales these itemset that brings potential high utility itemset into real high utility itemset.

目錄 5
圖目錄 6
表目錄 7
第壹章 簡介 9
第貳章 相關研究 12
2.1 探勘高效益項目集 12
2.2 THUI (TEMPORAL HIGH UTILITY ITEMSETS) MINE 13
2.3 HIGH UTILITY ITEMSETS FROM ON-SHELF TIME 16
2.4 TWAIN-ALGORITHM 22
2.5 FP-GROWTH 28
第参章 研究方法 31
3.1 範例說明 31
3.2 虛擬碼 42
第肆章 實驗數據 44
第伍章 結論與未來工作 48
參考文獻 49

1.　　R. Agrawal and R. Srikant, “Fast Algorithms for Mining Association Rules in Large Database”, In Proc. Of the 20th Intel. Conf. on Very Large Databases (VLDB), pp. 487-499, 1994.
2.　　R. Chan, Y. Shen and Q. Yang, ”Mining high utility itemsets” The 3rd IEEE International Conference on Data Mining, p. 19-26
3.　　C.-C. Chang, Y. C. Li and J. S. Yeh, “Isoland Items Discarding Strategy for Discovering High Utility Itemsets,” Data and Knowledge Eng, vol. 64, pp. 198-217, 2008.
4.　　M. S. Chen, B.-R. Dai and J. W. Huang, “Twain: Two-end association miner with precise frequent exhibition periods” ACM Trans. Knowl. Discov. Data, Vol.1,2, Article 8, 33pages, 2007.
5.M.S. Chen , C. H. Lee and C. R. Lin, “Sliding-window filtering: an efficient algorithm for incremental mining” Proc. ACM 10th Int’l Conf. Information and Knowledge Management, Nov. 2001.
6.　　A.L.P. Chen, S.J. Yen, “A Graph-Based Approach for Dicovering Various Types of Association Rules,” IEEE Transactions on Knowledge and Data Engineering (TKDE), 13(5), 2001, PP. 839-845.
7.　　A. Choudhary, W. Liao and Y. Liu, “A Fast High Utility Itemsets Mining Algorithm”, In Proc. Of the ACM Intel. Conf. on Utility-Based Data Mining Workshop (UBDM), 2005.
8.　　C. J. Chu, T. Liang and Vincent S. Tseng, “Mining temporal rare utility itemsets in large databases using relative utility thresholds,” International Journal of Innovative Computin, Information and Control, vol. 4, no.8, pp. 2775-2792, 2008.
9.Chun-Jung Chu, Tyne. Liang and Vincent S. Tseng, “An efficient algorithm for mining temporal high utility itemsets from data streams”, Journal of System Software, Vol. 81, No. 7, pp. 1105-1117.
10.　　Mohammad El-Hajj, Osmar R. Zaiane, “Non Recursive Generation of Frequent K-itemsets from Frequent Pattern Tree Representation,” In Proceedings of 5th International Conference on Data Warehousing and Knowledge Discovery (DaWak’2003), September 2003, pp.371-380.
11.　　J. Han, J. Pei, and Y. Yin, “Mining frequent patterns without candidate generation”, In Proc. Of the ACM-SIGMOD Intel. Conf. on Management of Data, pp.1-12, 2000.
12.　　T. P. Hong, G. C. Lan and V. S. Tseng, “Discovery of high utility itemsets from on-shelf time periods of products” Expert Systems with Application, 38(5), pp. 5851-5857, 2011.
13.　　Jianying Hu, Aleksandra Mojsilovic, “High-utility pattern mining: Amethod for discovery of high-utility item sets”, Pattern Recognition, Elsevier Science Inc, vol. 40, Issue 11, pp. 3317-3324, 2007.
14.　　Y.S. Lee, L.Y. Ouyang, C.K. Wang, J.W. Wu and S.J. Yen, “The Studies of Mining Frequent Patterns Based on Frequent Pattern Tree”, PAKDD 2009, LNAI 5476, 2009, PP. 232-241.
15.　　G. Liu, H. Lu, Y. Xu, and J.X. Yu, “From Path Tree to Frequent Patterns: A Framework for Mining Frequent Patterns,” In Proc. Intel Conf. Data Mining (ICDM ‘02), pp. 514-521, Dec. 2002.