一种基于改进信任度的协同过滤算法
|
摘要
随着电子商务的发展,它的功能日益强大,个性化产品推荐作为其重要的一个组成部分,也为推动电子商务的发展起到了重要的作用。其中,最重要的一种推荐算法就是协同过滤算法,各个大的电子商务网站都或多或少地应用了该算法,然而在实际应用中,该推荐算法也有其不足之处,不能很好地为企业和用户服务,故很多学者提出了各种相应的改进算法。
本文首先分析了协同过滤算法的不足,提出了基于改进信任度的协同过滤算法,并指明该算法的应用。文章构建评价算法的框架：先根据个性化产品推荐过程,构建概念模型；在此基础上,首次尝试从公司利益最大化的角度确定公司的主要目标和任务,数据收集模块和推荐结果列示模块通过比较分析现有的评价推荐结果指标,选取评价指标,并根据这些指标对主要目标和任务的实现所做的贡献,运用层次分析法,确定贡献率,最后得出综合评价结果；在推荐算法运行模块,应用敏感性分析法分析相似度计算对推荐结果的影响,进一步地改进算法。
对传统的协同过滤推荐算法和基于改进信任度的协同过滤推荐算法的推荐结果进行显著性分析评价,验证本文提出的改进算法能够显著的提高推荐的准确性。
With the development of electronic commerce, it becomes more powerful everyday, personalized products recommendation as an important part, which has played an important role on promoting the development of e-commerce. One of the most important recommendation algorithms is the collaborative filtering algorithm (CF), which is applied to many e-commerce sites more or less. But in practical application, this recommendation algorithm also has its drawbacks. It can not give good service to consumers and companies, therefore, many scholars have proposed various improved algorithms.
This paper analyzes the shortcomings of the use-based collaborative filtering algorithms, and proposes a new algorithm based on modified trustworthiness, and specified the application of this algorithm. Then we construct a framework for evaluation of algorithms: first, proposes concept models based on personalized products recommendation process; Secondly, being attempt to stand in the perspective of maximizing interests of the company to determine the company's main objectives and tasks, select the evaluating indicators in data collection module and recommended lists module by comparing existing indicators of the evaluation recommendations, according to the contribution of these indicators to achieve the main objectives and tasks, using AHP to ascertain the contribution rate and draw the conclusion of the evaluation results; in the running recommendation algorithm module, utilizing sensitivity analysis to analyze whether similarity calculation will affect the recommended results and how to affect, then to improve the algorithm further.
Design experiment to prove whether the improved trustworthiness in the collaborative filtering. recommendation algorithms can get significant improvement the results. According to experiment results, the improved algorithm can significantly get better recommendation accuracy.
本文首先分析了协同过滤算法的不足,提出了基于改进信任度的协同过滤算法,并指明该算法的应用。文章构建评价算法的框架：先根据个性化产品推荐过程,构建概念模型；在此基础上,首次尝试从公司利益最大化的角度确定公司的主要目标和任务,数据收集模块和推荐结果列示模块通过比较分析现有的评价推荐结果指标,选取评价指标,并根据这些指标对主要目标和任务的实现所做的贡献,运用层次分析法,确定贡献率,最后得出综合评价结果；在推荐算法运行模块,应用敏感性分析法分析相似度计算对推荐结果的影响,进一步地改进算法。
对传统的协同过滤推荐算法和基于改进信任度的协同过滤推荐算法的推荐结果进行显著性分析评价,验证本文提出的改进算法能够显著的提高推荐的准确性。
With the development of electronic commerce, it becomes more powerful everyday, personalized products recommendation as an important part, which has played an important role on promoting the development of e-commerce. One of the most important recommendation algorithms is the collaborative filtering algorithm (CF), which is applied to many e-commerce sites more or less. But in practical application, this recommendation algorithm also has its drawbacks. It can not give good service to consumers and companies, therefore, many scholars have proposed various improved algorithms.
This paper analyzes the shortcomings of the use-based collaborative filtering algorithms, and proposes a new algorithm based on modified trustworthiness, and specified the application of this algorithm. Then we construct a framework for evaluation of algorithms: first, proposes concept models based on personalized products recommendation process; Secondly, being attempt to stand in the perspective of maximizing interests of the company to determine the company's main objectives and tasks, select the evaluating indicators in data collection module and recommended lists module by comparing existing indicators of the evaluation recommendations, according to the contribution of these indicators to achieve the main objectives and tasks, using AHP to ascertain the contribution rate and draw the conclusion of the evaluation results; in the running recommendation algorithm module, utilizing sensitivity analysis to analyze whether similarity calculation will affect the recommended results and how to affect, then to improve the algorithm further.
Design experiment to prove whether the improved trustworthiness in the collaborative filtering. recommendation algorithms can get significant improvement the results. According to experiment results, the improved algorithm can significantly get better recommendation accuracy.
引文
[1]许海玲,吴潇,李晓东.互联网推荐系统比较研究.软件学报,2008,20(2)：350-362
[2]余力,刘鲁.电子商务个性化推荐研究.计算机集成制造系统,2004,10(10)：1306-13 13
[3]Lawrence R D. Personalization of supermarket product recommendations[R]. IBM Research Report,2000.
[4]刘建国,周涛,郭强,汪秉宏.个性化推荐系统评价方法综述.复杂系统与复杂性科学,2009,6(3)：1-13
[5]宋峻峰,李国辉.信息检索算法评价指标的分析与改进.小型微型计算机系统,2003,24(10)：1800-1803
[6]Resnick, Varian. Recommendation systems Communications of the ACM,1997,40(3): 56-C58.
[7]熊馨.电子商务个性化推荐系统研究-个性化产品推荐策略研究及算法设计.中国科学技术大学硕士学位论文,2005：1-66
[8]吴昕方.基于特征的个性化电子商务网站推荐系统的研究与实现[D].硕士论文,2006
[9]李丹丹.基于混合算法的个性化电子商务推荐系统研究[D].天津财经大学,2008：1-33
[10]许志佴,邹恒明基于协同过滤的垃圾邮件过滤系统.计算机工程,2008,34(23)：153-155
[11]王卫平,吴伦.协同过滤在CRM交叉销售中的应用研究.管理学报,2007,4(4)：436-441
[12]朱岩,林泽楠.电子商务中的个性化推荐方法评述.软科学研究成果与动态,2008：183-192
[13]Good N, Schafer J B, Konstan J A, Borehem, et al. Combining collaborative filtering with personal agents for better recommendation//proceeding of the sixteenth nation conference on artificial intelligence,1999:439-446.
[14]Lijuan Zheng, Yaling Wang, Jiangang Qi, Dan Liu. Research and Improvement of Personalized RecommendationAlgorithm Based on Collaborative Filtering. IJCSNS International Journal of Computer Science and Network Security, VOL.7 No, July 2007
[15]侯翠琴,焦李成,张文革.一种压缩稀疏用户评分矩阵的协同过滤算法.西安电子科技大学学报,2009,36(4)：614-617
[16]Ling, Kim B M. Clustering approach for hybrid recommender system:proc. of the IEEE /WIC International Conference on Web Intelli——nce(WI'03)[C]. [S.I.]:[s.n.],2003
[17]宗胜,姜丽红.推荐系统中遗漏值解决方法的研究.计算机应用与软件,2008,25(6)：193-195
[18]Schein A I, Popescul A, Ungar L H, Pennock D M. (2002):Methods and metrics for cold-start recommendations. In Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval. New York, NY, USA: ACM Press,2002:253-260.
[19]李珊,何建敏,厉浩.基于知识的协同过滤推荐系统研究.情报学报,2008,27(3)：357-362
[20]许建潮,王红梅.改进的协同过滤算法.吉林大学学报,2008,26(1)：99-105
[21]张富国.用户多兴趣下基于信任的协同过滤算法研究.小型微型计算机系统,2008.29(8)：1415-1421
[22]郑先荣,汤泽滢,曹先彬.适应用户兴趣变化的非线性逐步遗忘协同过滤算法.计算机辅助工程,2007,16(2)：69-53
[23]王岚,翟正军.基于时间加权的协同过滤算法.计算机应用,2007,27(9)：2302-2305
[24]刘勇.基于项目相似度计算改进的协同过滤算法.商场现代化,2007：84-85
[25]徐翔,王煦法.协同过滤算法中的相似度优化方法.计算机工程,2010,36(6)：52-56
[26]宣照国,苗静,党延忠.基于扩展邻居的协同过滤算法.情报学报,2010,29(3)：443-338
[27]郭艳红,邓贵仕,锥春雨.基于信任因子的协同过滤推荐算法[J].计算机工程,2008(10),20(34)：1-7
[28]卢竹兵,詹雁.一种基于信任网络的协同过滤推荐策略[J].西南师范大学学报,2008(4),33(2)：123-126
[29]Johll O, Barry S. Eliciljng Trust Values from Recommendation Errors. In Proceedings of the 18th Intematioml Florida Artificial Intelligence Research Society Conference (FLAIRS 05). Clearwater Beach, Florida, USA, May 15 — 172005.289-294
[30]Sheng Zhang, Yi Ouyan, James Ford.Analysis of a Low-dimensional Linear Model underRecommendation Attacks. SIGIR'06, August 6.11,2006, Seattle, Washington, USA.
[31]邓燕萍.网络信息检索效果评估.现代情报,2004,4：45-46
[32]刘志勇.网络环境下信息检索效率的评价.大连大学学报,2002,23(1)：110-112
[33]张海英.基于夏普比率的信息检索系统性能评价方法.统计与决策,2008,20：171-172
[34]杨立英,尚克聪.评价情报检索系统性能的新方法——加权中值法.情报学报,2003,22(1)：32-35
[35]刘宝利,肖晓春,张根度.基于层次分析法的信息系统脆弱性评估方法.计算机学,2006,33(12)：62-64
[36]Billsus D, Pazzani M J. Learning collaborative information filters[c]//Rich C, Mostow J. Proceedings of the 15th NationalConference o/1 Artificial
[37]Evaluating the intrusion cost of recommending in recommender systems. In User modeling 2005,10th international conference:342-346
[38]Pazzani M, BiUsus D. Learning and revising user profiles:the identification of interesting web sites[J]. Machine Learning,1997,27:313—331.
[39]Basu C, High H, Cohen W W. Recommendation as classification：using social and content-based information in recommendation el//Rich c, Mostow J. Proceedings of the 15th National Conference on Artificial Intelli- gence(AAAI — 1998). MenloPark, Calif:hAM Pressj 1998:11—14.
[40]邱燕燕.基于层次分析法的网络信息资源评价.情报科学,2001,19(6)：599-602
[41]苏芳荔,张帆.基于层次分析法的网络信息过滤系统评价研究.实践研究,2008,6(31)：900-903
[42]张娜.电子商务环境下的个性化信息推荐服务及应用研究[D].安徽：合肥工业大学,2007
[43]Massa P, Avesani P. Trust—aware Coilaborative Filtering for Recommender Systems[A]. Proceedings of International.Conference on Cooperative Information Systems Ec]. Berlin:Springer,2004:492—508
[44]Grandison T, Sloman M. A Survey Of Trust in internet Applications[J]. IEEE Communications Survey and Tutorials 3.2000.
[45]卢竹兵.基于信任关系的协同过滤推荐策略研究[D].重庆：西南大学,2008
[46]Emiko Orimo, Hideki Koike, Toshiyuki Masui, and Akikazu Takeuchi. Analysis and Evaluation of Recommendation Systems. Human Interface,Part I, HCII 2007, LNCS 4557: 144-152
[47]Johll O, Barry S. Eliciljng Trust Values from Recommendation Errors. In Proceedings of the 18th Intematioml Florida Artificial Intelligence Research Society Conference (FLAIRS 05). Clearwater Beach, Florida, USA, May 15-17,2005.289——294
[48]郭艳红.推荐系统的协同过滤算法与应用研究[D].大连：大连理工大学,2008
[49]胡慧蓉.电子商务个性化推荐系统分析与设计.创新教育,2009,(8)：202-203
[50]余力,刘鲁,罗掌华.我国电子商务推荐策略的比较分析[J].系统工程理论与实践,2004,(8)：96-101
[51]Jonathan, JosephA, Konstan, Loren G., Terveen, John T, Riedl. Evaluating Collaborative FilteringRecommender Systems. ACM Transactions on Information Systems, Vol.22, No.1, January 2004, Pages 5-53.
[52]Pazzani M, BiHsus D. Learning and Revising UserProfiles:The Identification of Interesting Web Sites.Machine Learning,1997.27:313——331
[53]Foffsts, Perelsonas, Allen L, et al. Self-nonself Discrimination in a Computer[C] Proceedings of IEEE Symposium on Research in Security and Privacy. Oakland, CA:IEEE Press,1994:202——212
[54]Hong Joo Lee, Jong Woo Kim, Sung Joo Park. Understanding Collaborative Filtering Parameters Forpersonalized Recommendations in e-commerce. Electron Commerce Res (2007)7:293-314
[55]Zhang S, Wang W H, Ford J, et al. Using singular value decomposition approximation for collaborative filtering[c]. In; Proceedings of 7th IEEE International Conference on Ecormmerce Technology,2005,257——264.
[56]Bhanu Prasad. HYREC:A Hybrid RecommendationSystem for E-Commerce.ICCBR 2005, LNAI,3620, pp:408—420,2005
[57]Sarwar B M, Karypis G, Konstan J A. Analysis of recommendation algorithms for e-commerce.In Proceedings of the Second ACM Conferenceon Electronic Commerce (ECO00),2000, pp.285-295
[2]余力,刘鲁.电子商务个性化推荐研究.计算机集成制造系统,2004,10(10)：1306-13 13
[3]Lawrence R D. Personalization of supermarket product recommendations[R]. IBM Research Report,2000.
[4]刘建国,周涛,郭强,汪秉宏.个性化推荐系统评价方法综述.复杂系统与复杂性科学,2009,6(3)：1-13
[5]宋峻峰,李国辉.信息检索算法评价指标的分析与改进.小型微型计算机系统,2003,24(10)：1800-1803
[6]Resnick, Varian. Recommendation systems Communications of the ACM,1997,40(3): 56-C58.
[7]熊馨.电子商务个性化推荐系统研究-个性化产品推荐策略研究及算法设计.中国科学技术大学硕士学位论文,2005：1-66
[8]吴昕方.基于特征的个性化电子商务网站推荐系统的研究与实现[D].硕士论文,2006
[9]李丹丹.基于混合算法的个性化电子商务推荐系统研究[D].天津财经大学,2008：1-33
[10]许志佴,邹恒明基于协同过滤的垃圾邮件过滤系统.计算机工程,2008,34(23)：153-155
[11]王卫平,吴伦.协同过滤在CRM交叉销售中的应用研究.管理学报,2007,4(4)：436-441
[12]朱岩,林泽楠.电子商务中的个性化推荐方法评述.软科学研究成果与动态,2008：183-192
[13]Good N, Schafer J B, Konstan J A, Borehem, et al. Combining collaborative filtering with personal agents for better recommendation//proceeding of the sixteenth nation conference on artificial intelligence,1999:439-446.
[14]Lijuan Zheng, Yaling Wang, Jiangang Qi, Dan Liu. Research and Improvement of Personalized RecommendationAlgorithm Based on Collaborative Filtering. IJCSNS International Journal of Computer Science and Network Security, VOL.7 No, July 2007
[15]侯翠琴,焦李成,张文革.一种压缩稀疏用户评分矩阵的协同过滤算法.西安电子科技大学学报,2009,36(4)：614-617
[16]Ling, Kim B M. Clustering approach for hybrid recommender system:proc. of the IEEE /WIC International Conference on Web Intelli——nce(WI'03)[C]. [S.I.]:[s.n.],2003
[17]宗胜,姜丽红.推荐系统中遗漏值解决方法的研究.计算机应用与软件,2008,25(6)：193-195
[18]Schein A I, Popescul A, Ungar L H, Pennock D M. (2002):Methods and metrics for cold-start recommendations. In Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval. New York, NY, USA: ACM Press,2002:253-260.
[19]李珊,何建敏,厉浩.基于知识的协同过滤推荐系统研究.情报学报,2008,27(3)：357-362
[20]许建潮,王红梅.改进的协同过滤算法.吉林大学学报,2008,26(1)：99-105
[21]张富国.用户多兴趣下基于信任的协同过滤算法研究.小型微型计算机系统,2008.29(8)：1415-1421
[22]郑先荣,汤泽滢,曹先彬.适应用户兴趣变化的非线性逐步遗忘协同过滤算法.计算机辅助工程,2007,16(2)：69-53
[23]王岚,翟正军.基于时间加权的协同过滤算法.计算机应用,2007,27(9)：2302-2305
[24]刘勇.基于项目相似度计算改进的协同过滤算法.商场现代化,2007：84-85
[25]徐翔,王煦法.协同过滤算法中的相似度优化方法.计算机工程,2010,36(6)：52-56
[26]宣照国,苗静,党延忠.基于扩展邻居的协同过滤算法.情报学报,2010,29(3)：443-338
[27]郭艳红,邓贵仕,锥春雨.基于信任因子的协同过滤推荐算法[J].计算机工程,2008(10),20(34)：1-7
[28]卢竹兵,詹雁.一种基于信任网络的协同过滤推荐策略[J].西南师范大学学报,2008(4),33(2)：123-126
[29]Johll O, Barry S. Eliciljng Trust Values from Recommendation Errors. In Proceedings of the 18th Intematioml Florida Artificial Intelligence Research Society Conference (FLAIRS 05). Clearwater Beach, Florida, USA, May 15 — 172005.289-294
[30]Sheng Zhang, Yi Ouyan, James Ford.Analysis of a Low-dimensional Linear Model underRecommendation Attacks. SIGIR'06, August 6.11,2006, Seattle, Washington, USA.
[31]邓燕萍.网络信息检索效果评估.现代情报,2004,4：45-46
[32]刘志勇.网络环境下信息检索效率的评价.大连大学学报,2002,23(1)：110-112
[33]张海英.基于夏普比率的信息检索系统性能评价方法.统计与决策,2008,20：171-172
[34]杨立英,尚克聪.评价情报检索系统性能的新方法——加权中值法.情报学报,2003,22(1)：32-35
[35]刘宝利,肖晓春,张根度.基于层次分析法的信息系统脆弱性评估方法.计算机学,2006,33(12)：62-64
[36]Billsus D, Pazzani M J. Learning collaborative information filters[c]//Rich C, Mostow J. Proceedings of the 15th NationalConference o/1 Artificial
[37]Evaluating the intrusion cost of recommending in recommender systems. In User modeling 2005,10th international conference:342-346
[38]Pazzani M, BiUsus D. Learning and revising user profiles:the identification of interesting web sites[J]. Machine Learning,1997,27:313—331.
[39]Basu C, High H, Cohen W W. Recommendation as classification：using social and content-based information in recommendation el//Rich c, Mostow J. Proceedings of the 15th National Conference on Artificial Intelli- gence(AAAI — 1998). MenloPark, Calif:hAM Pressj 1998:11—14.
[40]邱燕燕.基于层次分析法的网络信息资源评价.情报科学,2001,19(6)：599-602
[41]苏芳荔,张帆.基于层次分析法的网络信息过滤系统评价研究.实践研究,2008,6(31)：900-903
[42]张娜.电子商务环境下的个性化信息推荐服务及应用研究[D].安徽：合肥工业大学,2007
[43]Massa P, Avesani P. Trust—aware Coilaborative Filtering for Recommender Systems[A]. Proceedings of International.Conference on Cooperative Information Systems Ec]. Berlin:Springer,2004:492—508
[44]Grandison T, Sloman M. A Survey Of Trust in internet Applications[J]. IEEE Communications Survey and Tutorials 3.2000.
[45]卢竹兵.基于信任关系的协同过滤推荐策略研究[D].重庆：西南大学,2008
[46]Emiko Orimo, Hideki Koike, Toshiyuki Masui, and Akikazu Takeuchi. Analysis and Evaluation of Recommendation Systems. Human Interface,Part I, HCII 2007, LNCS 4557: 144-152
[47]Johll O, Barry S. Eliciljng Trust Values from Recommendation Errors. In Proceedings of the 18th Intematioml Florida Artificial Intelligence Research Society Conference (FLAIRS 05). Clearwater Beach, Florida, USA, May 15-17,2005.289——294
[48]郭艳红.推荐系统的协同过滤算法与应用研究[D].大连：大连理工大学,2008
[49]胡慧蓉.电子商务个性化推荐系统分析与设计.创新教育,2009,(8)：202-203
[50]余力,刘鲁,罗掌华.我国电子商务推荐策略的比较分析[J].系统工程理论与实践,2004,(8)：96-101
[51]Jonathan, JosephA, Konstan, Loren G., Terveen, John T, Riedl. Evaluating Collaborative FilteringRecommender Systems. ACM Transactions on Information Systems, Vol.22, No.1, January 2004, Pages 5-53.
[52]Pazzani M, BiHsus D. Learning and Revising UserProfiles:The Identification of Interesting Web Sites.Machine Learning,1997.27:313——331
[53]Foffsts, Perelsonas, Allen L, et al. Self-nonself Discrimination in a Computer[C] Proceedings of IEEE Symposium on Research in Security and Privacy. Oakland, CA:IEEE Press,1994:202——212
[54]Hong Joo Lee, Jong Woo Kim, Sung Joo Park. Understanding Collaborative Filtering Parameters Forpersonalized Recommendations in e-commerce. Electron Commerce Res (2007)7:293-314
[55]Zhang S, Wang W H, Ford J, et al. Using singular value decomposition approximation for collaborative filtering[c]. In; Proceedings of 7th IEEE International Conference on Ecormmerce Technology,2005,257——264.
[56]Bhanu Prasad. HYREC:A Hybrid RecommendationSystem for E-Commerce.ICCBR 2005, LNAI,3620, pp:408—420,2005
[57]Sarwar B M, Karypis G, Konstan J A. Analysis of recommendation algorithms for e-commerce.In Proceedings of the Second ACM Conferenceon Electronic Commerce (ECO00),2000, pp.285-295