GSSA：以階段分組排序搜尋機制探勘關聯規則之演算法

GSSA: A Gradation Sorting and Scanning Algorithm for Data Mining and Applications

黃仁鵬(Jen-Peng Huang) ； 柯柏瑄(Po-Hsuan Co)

《電子商務學報》 11卷3期 (2009/09) Pp. 551-568

https://doi.org/10.6188/JEB.2009.11(3).04

摘要

本研究提出GSSA演算法(Gradation Sorting and Scanning Approaches)。GSSA演算法主要的特色就是資料庫分組排序的概念與階段縮減過濾機制。資料庫分組排序可減少計算支持度時需掃瞄資料庫之範圍，進而改善傳統關聯規則演算法資料庫的掃瞄方式；而階段縮減過濾機制可大量減少非頻繁項目集的數量，將可更適用於探勘交易長度較長的資料庫並且有效提昇記憶體的使用率。本研究實驗顯示本演算法在效能上優於Apriori與FP-growth演算法。

關鍵字

資料探勘 ； 關聯規則 ； 資料庫分組排序 ； 階段搜尋 ； 頻繁項目集

並列摘要

In this paper we propose GSSA (Gradation Sorting and Scanning Approaches), a new algorithm for mining association rules. GSSA algorithm adopts the concept of database sorting and the gradation reduction mechanisms to increase the performance. Comprehensive experiments have been conducted to assess the performance of the proposed algorithm. The experimental results show that GSSA outperforms others previously proposed algorithms under a variety of conditions.

並列關鍵字

data mining ； association rules ； database sorting ； gradation scanning ； frequent itemsets

參考文獻

Agrawal, R.,Srikant, R.(1994).Fast algorithms for mining association rules.Proceedings of 1994 International Conference on Very Large Data Bases.(Proceedings of 1994 International Conference on Very Large Data Bases).

Brin, S.,Motwani, R.,Ullman, J. D.,Tsur, S.(1997).Dynamic itemset counting and implication rules for market basket data.ACM SIGMOD Conference on Management of Data.(ACM SIGMOD Conference on Management of Data).

Chen, X.,Li, L.,Ma, Z.,Bai, S.,Guo, F.(2006).F-Miner: A New Frequent Itemsets Mining Algorithm.IEEE International Conference on e-Business Engineering.(IEEE International Conference on e-Business Engineering).

Han, J.,Pei, J.,Yin, Y.(2000).Mining Frequent Patterns without Candidate Generation.Proc. ACM SIGMOD Int. Conf. on Management of Data.(Proc. ACM SIGMOD Int. Conf. on Management of Data).

Huang J. P.,Lan G. C.(2006).An Efficient Algorithm for Mining Association Rules-GRA.Journal of e-Business.8(4),469-498.