基于行为和评分相似性的关联规则群推荐算法

计算机科学 ›› 2014, Vol. 41 ›› Issue (3): 36-40.

基于行为和评分相似性的关联规则群推荐算法

张佳乐,梁吉业,庞继芳,王宝丽

山西大学计算机与信息技术学院计算智能与中文信息处理教育部重点实验室太原030006;山西大学计算机与信息技术学院计算智能与中文信息处理教育部重点实验室太原030006;山西大学计算机与信息技术学院计算智能与中文信息处理教育部重点实验室太原030006;山西大学计算机与信息技术学院计算智能与中文信息处理教育部重点实验室太原030006

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受国家973计划前期研究专项(2011CB311805),山西省科技攻关计划项目(20110321027-01),山西省科技基础条件平台建设项目(2012091002-0101)资助

Behavior and Score Similarity Based Algorithm for Association Rule Group Recommendation

ZHANG Jia-le,LIANG Ji-ye,PANG Ji-fang and WANG Bao-li

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 使用关联规则推荐工具会遇到最优推荐规则选取难、规则信息不能充分利用等问题。利用较易获取的应用领域知识可有效解决这类问题。针对仅有商品名称和评分信息的推荐情形,提出一种基于行为和评分相似性的关联规则群推荐算法,该算法将规则及相应的评分信息视为推荐专家,将推荐结论相同的专家合并为一个专家组,利用客户行为和评分的双重相似性计算专家权重,并利用群决策的思想集结专家组的推荐意见,从而给出最佳推荐方案。最后通过实例和实验说明了该算法的可行性和有效性。

Abstract: Applying the association rule recommendation tool often meets the hardness of selection for optimal rule,inadequate utilization of rule information．Using easily obtained background knowledge can solve these problems．Aiming at the situation that only contains commodity’s name and score information,this paper proposed a behavior and score similarity based association rule group recommendation algorithm,in which the rule with its scores is regarded as an expert,and the experts with same conclusion are grouped together and the expert weights are calculated based on both behavior similarity and score similarity．A better recommendation suggestion is reached by aggregating the recommendation opinions of the experts．The experimental example shows that the algorithm is feasible and effective.

Key words: Association rule,Group recommendation,Behavior similarity,Score similarity

张佳乐,梁吉业,庞继芳,王宝丽. 基于行为和评分相似性的关联规则群推荐算法[J]. 计算机科学, 2014, 41(3): 36-40. https://doi.org/

ZHANG Jia-le,LIANG Ji-ye,PANG Ji-fang and WANG Bao-li. Behavior and Score Similarity Based Algorithm for Association Rule Group Recommendation[J]. Computer Science, 2014, 41(3): 36-40. https://doi.org/

参考文献

[1] Park D H,Kim H K．A literature review and classification ofrecommender systems research[J]．Expert Systems with Applications,2012,39(11):10059-10072
[2] 哈进兵,郑锐,甘利人.一种基于加权关联规则的协同推荐算法[J].情报学报,2010,9(4):718-722
[3] 龙舜,蔡跳,林佳雄.一个基于演化关联规则挖掘的个性化推荐模型[J].暨南大学学报,2012,3(3):264-267
[4] Thabtah F,Cowling P,Peng Y．MMAC:A new multi-class,multi-label associative classification approach[C]∥ICDM 2004:Proceedings of the 4th IEEE International Conference on Data Mining．Brighton,UK,2004:217-224
[5] 周欣,沙朝锋,朱扬勇.兴趣度-关联规则的又一个阈值[J].计算机研究与发展,2000,7(5):627-633
[6] 肖波.可信关联规则挖掘算法研究[D].北京:北京邮电大学,2009
[7] 李广原,杨炳儒,周如旗.一种基于约束的关联规则挖掘算法[J].计算机科学,2012,9(1):244-247
[8] 杨红菊,梁吉业.一种有效的关联规则的挖掘方法[J].计算机应用,2004,4(3):88-89
[9] 李杰,徐勇,王云峰.面向个性化推荐的强关联规则挖掘[J].系统工程理论与实践,2009,9(8):133-151
[10] Liu Y Z,Jiang Y C,Liu Y C．CSMC:A combination strategy formulti-class classification based on multiple association rules[J]．Knowledge-Based Systems,2008,21(8):786-793
[11] Pang J F,Liang J Y.Evaluation of the results of multi-attribute group decision-making with linguistic information[J]．Omega,2012,0(3):294-301
[12] Jiang Y C,Shang J,Liu Y Z．Maximizing customer satisfaction through an online recommendation system:A novel associative classification model[J]．Decision Support System,2010,8(3):470-479
[13] Cao F Y,Liang J Y,Li D Y,et al．A dissimilarity measure for the k-Modes clustering algorithm[J]．Knowledge-Based Systems,2012,26(1):120-127
[14] 余力,刘鲁.电子商务个性化推荐研究[J].计算机集成制造系统,2004,0(10):1306-1313
[15] Su J H,Wang B W,Hsiao C Y,et al．Personalized rough-set-based recommendation by integrating multiple contents and collaborative information[J]．Information Sciences,2010,180(1):113-131

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed