摘要
针对Apriori关联规则算法与用户兴趣度不匹配,容易造成错误商务决定的问题。提出一种新的基于相似度的Apriori混合算法,以提高数据分析的准确率。通过加入用户兴趣度权重,利用协同过滤算法中客观用户相似度替代主观兴趣度改进了Apriori算法,并进行测试。实验结果表明,改进后的算法平均置信度提高了13%,平均支持度提高了25%,有效提高了关联规则的准确性。
Because of the mismatch between Apriori association rules algorithm and user interest,it is easy to make wrong business decisions.A new Apriori hybrid algorithm based on similarity is proposed to improve the accuracy of data analysis.Apriori algorithm is improved and tested by adding user interest weight and replacing subjective interest with objective user similarity in collaborative filtering algorithm.Experimental results show that the improved algorithm improves the average confidence by 13%,the average support by 25%,and improves the accuracy of association rules.
作者
罗洁
王力
LUO Jie;WANG Li(College of Big Data and Information Engineering,Guizhou University,Guiyang 550025,China;Bijie Industry Polytechnic College,Bijie Guizhou 551700,China;School of Information Engineering,Guizhou University of Engineering Science,Bijie Guizhou 551700,China)
出处
《智能计算机与应用》
2023年第8期158-160,164,共4页
Intelligent Computer and Applications
基金
贵州省教育厅创新群体重大研究资助项目(黔财教合[2016]118)
贵州省首批国家级新工科研究与实践资助项目(黔教高函[2018]209号)。
