关键词: 数据挖掘, 加权时态关联规则, 加权时态频繁项集

Abstract: The association rules would be more real and useful when considering temporal constraint because of temporal semantics existing in many real databases.Lots of algorithms for mining temporal association rules have been proposed at present and most of them treat each item uniformly，but decision-makers are more inclined to items whose profits are higher than others.A mining algorithm of weighted temporal association rules is proposed.In the algorithm item’s lifespan is used as time feature and user is allowed to specify different weights for different items.Experiments show that not only the new algorithm is effective in mining the weighted temporal association rules but also more useful association rules can be found.

Key words: data mining, weighted temporal association rules, weighted temporal frequent itemsets