一种改进的协同过滤推荐算法

doi:10.3969/j.issn.1000-1565.2020.01.012

河北大学学报(自然科学版) ›› 2020, Vol. 40 ›› Issue (1): 77-86.DOI: 10.3969/j.issn.1000-1565.2020.01.012

一种改进的协同过滤推荐算法

李昆仑,戎静月,苏华仃

收稿日期:2019-07-03 出版日期:2020-01-25 发布日期:2020-01-25
通讯作者: 戎静月(1993—),女,河北石家庄人,河北大学在读硕士研究生.主要从事推荐算法、机器学习、数据分析等方向研究. E-mail:rongjingyueRRR@163.com
作者简介:李昆仑(1962—),男,河北保定人,河北大学教授,博士,主要从事模式识别、图像处理、计算机网络、智能信息处理等方向研究. E-mail:likunlun@hbu.edu.cn
基金资助:
国家自然科学基金资助项目(61672205)

An improved collaborative filtering recommendation algorithm

LI Kunlun, RONG Jingyue,SU Huading

College of Electronic Information Engineering, Hebei University, Baoding 071000, China

Received:2019-07-03 Online:2020-01-25 Published:2020-01-25

摘要/Abstract

摘要： 协同过滤推荐算法是目前个性化推荐系统中应用比较广泛的一种算法,但也同样面临着数据稀疏性、冷启动、可扩展性等问题.本文主要针对数据稀疏性问题和冷启动问题导致的推荐效果不精确,提出了一种改进的数据填充方式和相似度计算方法.首先根据用户评分习惯对用户进行层次聚类,其次利用用户基本信息如年龄初步计算用户之间的相似度,并将共同评分项所占比值作为权重得到用户相似度,最后利用Slope-one算法计算前K个相似用户的填充值,加入相似度的权重以获得最终填充值.计算相似度寻找近邻集时,将用户基本属性作为相似度权重,并且引入Sigmoid函数来添加时间戳对相似度的影响,并得到最终的相似度计算方法. 实验结果表明,推荐精度得到了显著提高,数据稀疏性问题和冷启动问题得到了改善.

关键词: 协同过滤, 数据稀疏性, 相似度, Sigmoid, 评分尺度

Abstract: The collaborative filtering recommendation algorithm is one of the most widely used algorithms in the personalized recommendation system, but it also faces problems such as data sparsity, cold start, and scalability. This paper mainly proposes an improved data filling method and similarity calculation method for the inaccurate recommendation effect caused by the data sparsity problem and the cold start problem. Firstly, the user is hierarchically clustered according to the user's scoring habits, and then the users basic information such as age is used to calculate the similarity between users, and the ratio of the common scoring items is used as the weight to obtain the user similarity. Finally, the Slope-one algorithm is used to calculate the padding values of the first K similar users, and the similarity weights are added to obtain the final padding value. When calculating similarity to find the nearest neighbor set,the basic attribute of the user is used as the similarity weight,and the Sigmoid function is introduced to add the impact of the timestamp on the similarity and obtain the final similarity calculation method The experimental results show that the recommendation accuracy is significantly improved, and at the same time the data sparsity problem and the cold start problem are improved.

Key words: collaborative filtering, data sparsity, similarity, Sigmoid, scoring scale

中图分类号:

TP301

李昆仑,戎静月,苏华仃. 一种改进的协同过滤推荐算法[J]. 河北大学学报(自然科学版), 2020, 40(1): 77-86.

LI Kunlun, RONG Jingyue,SU Huading. An improved collaborative filtering recommendation algorithm[J]. Journal of Hebei University (Natural Science Edition), 2020, 40(1): 77-86.

参考文献

[1] ZOU C F, ZHANG D Q, WAN J F, et al. Using concept lattice for personalized recommendation system design[J]. IEEE Systems Journal, 2015, 11(1):1-10. DOI:10.1109/JSYST.2015.2457244.
[2] LIU X J. An improved clustering-based collaborative filtering recommendation algorithm[J].Cluster Computing, 2017, 20(2):1281-1288. DOI:10.1007/s10586-017-0807-6.
[3] SHU J B, SHEN X X, LIU H, et al. A content-based recommendation algorithm for learning resources[J]. Multimedia Systems, 2017(1):1-11.DOI: 10.1007/s00530-017-0539-8.
[4] XI Y, YUAN Q. Intelligent recommendation scheme of scenic spots based on association rule mining algorithm[C] //International Conference on Robots & Intelligent System, IEEE, 2017. DOI: 10.1109/ICRIS.2017.53.
[5] GUO Q J, JI W T, ZHOU R Y. Algorithm study under big data environment of personalized recommendation based on user interest model[C] // IEEE/ACIS International Conference on Computer & Information Science, 2017. DOI: 10.1109/ICIS.2017.7959988.
[6] WANG H M, ZHANG P,LU T, et al. Hybrid recommendation model based on incremental collaborative filtering and content-based algorithms[C] // IEEE International Conference on Computer Supported Cooperative Work in Design, 2017. DOI: 10.1109/CSCWD.2017.8066717.
[7] SONG M Q. A collaborative filtering recommendation algorithm based on multi-dimensional data filling[C] // IEEE International Conference on Computer & Communications, 2017. DOI: 10.1109/CompComm.2016.7924688.
[8] WEI J, HE J H, CHEN K, et al. Collaborative filtering and deep learning based recommendation system for cold start items[J]. Expert Systems with Applications, 2017, 69:29-39. DOI: 10.1016/j.eswa.2016.09.040.
[9] SU C,ZHANG B T. A collaborative filtering recommendation algorithm based on weighted SimRank and social trust[C] // International Conference on Materials Science, 2017. DOI:10.1063/1.4982551.
[10] SUN B S,DONG L Y. Dynamic model sdaptive yo user interest drift based on cluster and nearest neighbors[J]. IEEE Access, 2017(99):1-1. DOI: 10.1109/ACCESS.2017.2669243.
[11] YU C Y, HUANG L P. CluCF: A clustering CF algorithm to address data sparsity problem[J]. Service Oriented Computing and Applications, 2017, 11(1):33-45. DOI: 10.1007/s11761-016-0191-8.
[12] 李昆仑,万品哲,张德智.基于改进用户相似性度量和评分预测的协同过滤推荐算法[J].小型微型计算机系统,2018, 39(3): 567-571. DOI:10.3969/j.issn.1000-1220.2018.03.031.
[13] 李伟霖,王成良,文俊浩.基于评论与评分的协同过滤算法[J].计算机应用研究,2017,34(2):361-364, DOI: 10.3969/j.issn.1001-3695.2017.02.009.
[14] 王余斌, 王成良, 文俊浩. 基于用户评论评分与信任度的协同过滤算法[J].计算机应用研究,2018,35(5):94-97.DOI: 10.3969/j.issn.1001-3695.2018.05.019.
[15] 赵文涛,王春春,成亚飞,等.基于用户多属性与兴趣的协同过滤算法[J].计算机应用研究,2016,33(12):3630-3633. DOI: 10.3969/j.issn.1001-3695.2016.12.025.
[16] POZO M, CHIKY R, MEZIANE F, et al. Enhancing new user cold-start based on decision trees active learning by ising past warm-users predictions[C] // Conference on Computational Collective Intelligence Technologies and Applications. Springer, Cham, 2017. DOI:10.1007/978-3-319-67074-4_14.
[17] FELICIO C Z, PAIXAO K V R, BARCELOS C A Z, et al.Preference like score to cope with cold-start userin recommender systems[C] // IEEE International Conference on Tools with Artificial Intelligence. 2017. DOI: 10.1109/ICTAI.2016.0020.
[18] LI B, ZHU X, LI R, et al. Rating knowledge sharing in cross-domain collaborative filtering[J]. IEEE Transactions on Cybernetics, 2017, 45(5):1068-1082. DOI: 10.1109/TCYB.2014.2343982.
[19] WU X J, YUAN X J, DUAN C Y, et al. A novel collaborative filtering algorithm of machine learning by integrating restricted Boltzmann machine and trust information[J]. Neural Computing & Applications, 2018(5):1-8. DOI:10.1007/s00521-018-3509-y.
[20] LI L, ZHOU Y, XIONG H, et al. Collaborative filtering based on user attributes and user ratings for restaurant recommendation[C] // 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference(IAEAC), IEEE, 2017. DOI: 10.1109/IAEAC.2017.8054493.
[21] ZHU J H, MING Q, LI U Y. Trust-distrust-aware point-of-interest recommendation in location-based social network[M] // Wireless Algorithms, Systems, and Applications, Springer, Cham, 2018. DOI: 10.1007/978-3-319-94268-1_58.
[22] DANG Y, WANG Z Z, LIU X Z. Design of outdoor recommendation algorithm based on user location[C] // IEEE International Conference on Computer & Communications, IEEE, 2017. DOI:10.1109/CompComm.2016.7925020.
[23] 林建辉,严宣辉,黄波.基于SVD与模糊聚类的协同过滤推荐算法[J]. 计算机系统应用, 2016, 25(11):156-163.DOI:10.15888/j.cnki.csa.005474.
[24] 袁正午,陈然.基于多层次混合相似度的协同过滤推荐算法[J]. 计算机应用, 2018, 38(3):633-638. DOI: 10.11772/j.issn.1001-9081.2017071718.
[25] 郝德华,关维国, 邹林杰,等. 基于Pearson相关系数的快速虚拟网格匹配定位算法[J]. 计算机应用, 2018, 38(3):763-768. DOI: 10.11772/j.issn.1001-9081.2017071760.
[26] 刘华锋,景丽萍,于剑.融合社交信息的矩阵分解推荐方法研究综述[J].软件学报, 2018, 29(2):340-362. DOI: 10.13328/j.cnki.jos.005391.
[27] LIU H, XU Q, JIN G W, et al. MIMO antenna polynomial weighted average design method of downward-looking array, SAR[J]. International Journal of Antennas and Propagation, 2017:1-18. DOI: 10.1155/2017/3029847.
[28] 谢荻帆,杜子芳. 中国电影线上评分系统的改进[J].计算机应用, 2018, 38(4):1218-1222. DOI: CNKI:SUN:JSJY.0.2018-04-051.
[29] LIU Y N, LIU D S, XIE H H, et al. A research on the improved slope one algorithm for collaborative filtering[J]. International Journal of Computing Science and Mathematics, 2016, 7(3):245. DOI: 10.1504/IJCSM.2016.077865.

一种改进的协同过滤推荐算法

An improved collaborative filtering recommendation algorithm

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

本文评价

[1]	任志波,王亚文,魏翔宇,管成康. 融合多视角信任的个性化推荐算法[J]. 河北大学学报(自然科学版), 2020, 40(5): 552-560.
[2]	何丹丹,吴树芳,徐建民. 基于文档关系改进的向量空间模型[J]. 河北大学学报(自然科学版), 2020, 40(3): 322-327.
[3]	田俊峰,蔡红云. 托攻击与推荐系统安全[J]. 河北大学学报(自然科学版), 2018, 38(6): 640-647.
[4]	张锡忠,徐建民. 基于术语同义关系的文档相似度研究[J]. 河北大学学报(自然科学版), 2017, 37(1): 108-112.
[5]	徐建民,李腾飞,吴树芳. 一种基于用户交互行为的微博社区发现方法[J]. 河北大学学报(自然科学版), 2016, 36(2): 189-196.
[6]	刘庆,王昌. 基于Vague软集相似度量的快速估算模型[J]. 河北大学学报(自然科学版), 2014, 34(5): 460-466,474.
[7]	刘海博,郗亚辉,王煜. 用于文本分类的快速KNN算法[J]. 河北大学学报(自然科学版), 2008, 28(3): 322-326.
[8]	田大增,崔玮,哈明虎,高林庆. 基于相似度的模糊粗糙近似算子[J]. 河北大学学报(自然科学版), 2008, 28(1): 92-95.