Please wait a minute...
Advanced Search
数据分析与知识发现  2021, Vol. 5 Issue (4): 103-114     https://doi.org/10.11925/infotech.2096-3467.2020.0349
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
基于用户行为自适应推荐模型研究 *
向卓元1(),刘志聪2,吴玉1
1中南财经政法大学信息与安全工程学院 武汉 430073
2中国建设银行运营数据中心 武汉 430073
Adaptive Recommendation Model Based on User Behaviors
Xiang Zhuoyuan1(),Liu Zhicong2,Wu Yu1
1School of Information and Safety Engineering, Zhongnan University of Economics and Law, Wuhan 430073, China
2Data Center of China Construction Bank, Wuhan 430073, China
全文: PDF (1006 KB)   HTML ( 6
输出: BibTeX | EndNote (RIS)      
摘要 

【目的】 针对用户类型多样性和推荐模型专一性的问题,提出基于用户行为自适应推荐模型。【方法】 通过构建三层协同结构来规范推荐过程。第一层对用户分类,形成不同推荐通道;第二层根据通道匹配经过改进的推荐子算法;第三层引入特征加权形成推荐池,并在其中筛选项目推荐给用户;最终实现自适应推荐。【结果】 与主流推荐模型进行对比,本文所提推荐模型的准确率、召回率、覆盖率、流行度分别是0.24、0.17、0.50、4.40,说明本文模型在各项指标上均有很好的表现。【局限】 推荐算法以显性的评分为基础,无法直接预测无评分数据的数据集,需要构造偏好模型预测出隐式数据的评分,再进行预测,故在实际应用中会有一定的局限性。【结论】 本文模型能够适应不同类型用户的偏好,并实现合理的推荐。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
向卓元
刘志聪
吴玉
关键词 三层协同自适应推荐相似度混合机器学习    
Abstract

[Objective] This paper proposes an adaptive recommendation model based on user’s behaviors, aiming to address the issues of one model only working for one user type. [Methods] We standardized the recommendation process with a three-tier collaborative structure. The first layer classified users to create different recommendation channels. The second layer matched the improved recommendation sub-algorithm with corresponding channels. The third layer introduced feature weighting to form a recommendation pool, from which the items were selected and recommended to users. [Results] The accuracy, recall, coverage and popularity of the proposed model were 0.24, 0.17, 0.50 and 4.40, which were better than the mainstream models. [Limitations] Our recommendation algorithm cannot work on datasets without scores. [Conclusions] The proposed model can learn the preferences of users and make better recommendations.

Key wordsThree-Layer Collaboration    Adaptive Recommendation    Similarity Mixing    Machine Learning
收稿日期: 2020-04-22      出版日期: 2021-05-17
ZTFLH:  G353  
基金资助:*国家自然科学基金项目的研究成果之一(61702553)
通讯作者: 向卓元     E-mail: xzyhytxbw@163.com
引用本文:   
向卓元,刘志聪,吴玉. 基于用户行为自适应推荐模型研究 *[J]. 数据分析与知识发现, 2021, 5(4): 103-114.
Xiang Zhuoyuan,Liu Zhicong,Wu Yu. Adaptive Recommendation Model Based on User Behaviors. Data Analysis and Knowledge Discovery, 2021, 5(4): 103-114.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2020.0349      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2021/V5/I4/103
Fig.1  三层协同框架
Fig.2  三个表形成星型模型
Fig.3  用户特征重要性系数
Fig.4  α,β参数设置
Fig.5  整体模型比较(准确率)
Fig.6  整体模型比较(召回率)
Fig.7  整体模型比较(覆盖率)
Fig.8  整体模型比较(流行度)
指标 本文 UserCF ItemCF CB Mix
准确率 0.24 0.09 0.08 0.04 0.08
召回率 0.17 0.17 0.16 0.08 0.16
覆盖率 0.50 0.42 0.41 0.59 0.49
流行度 4.40 4.93 4.91 3.56 4.86
Table 1  不同指标下模型表现
[1] Persson P. Attention Manipulation and Information Overload[J]. Behavioural Public Policy, 2018,2(1):78-106.
doi: 10.1017/bpp.2017.10
[2] Aswani R, Kar A K, Ilavarasan P V, et al. Search Engine Marketing is Not All Gold: Insights from Twitter and SEOClerks[J]. International Journal of Information Management, 2018,38(1):107-116.
doi: 10.1016/j.ijinfomgt.2017.07.005
[3] Lu J, Wu D, Mao M, et al. Recommender System Application Developments: A Survey[J]. Decision Support Systems, 2015,74:12-32.
doi: 10.1016/j.dss.2015.03.008
[4] Lika B, Kolomvatsos K, Hadjiefthymiades S. Facing the Cold Start Problem in Recommender Systems[J]. Expert Systems with Applications, 2014,41(4):2065-2073.
doi: 10.1016/j.eswa.2013.09.005
[5] Feng J, Fengs X, Zhang N, et al. An Improved Collaborative Filtering Method Based on Similarity[J]. PLoS ONE, 2018,13(9):e0204003.
doi: 10.1371/journal.pone.0204003
[6] Jamali M, Ester M. TrustWalker: A Random Walk Model for Combining Trust-Based and Item-Based Recommendation[C]//Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2009: 397-406.
[7] Lu J, Shambour Q, Xu Y, et al. A Web-Based Personalized Business Partner Recommendation System Using Fuzzy Semantic Techniques[J]. Computational Intelligence, 2013,29(1):37-69.
doi: 10.1111/coin.2013.29.issue-1
[8] Bobadilla J, Ortega F, Hernando A, et al. A Collaborative Filtering Approach to Mitigate the New User Cold Start Problem[J]. Knowledge-Based Systems, 2012,26:225-238.
doi: 10.1016/j.knosys.2011.07.021
[9] Ahn H J. A New Similarity Measure for Collaborative Filtering to Alleviate the New User Cold-Starting Problem[J]. Information Sciences, 2008,178(1):37-51.
doi: 10.1016/j.ins.2007.07.024
[10] Liu H, Hu Z, Mian A, et al. A New User Similarity Model to Improve the Accuracy of Collaborative Filtering[J]. Knowledge-Based Systems, 2014,56:156-166.
doi: 10.1016/j.knosys.2013.11.006
[11] Son L H. HU-FCF: A Hybrid User-Based Fuzzy Collaborative Filtering Method in Recommender Systems[J]. Expert Systems with Applications: An International Journal, 2014,41(15):6861-6870.
doi: 10.1016/j.eswa.2014.05.001
[12] Karahodza B, Donko D. Feature Enhanced Time-Aware Recommender System[C]//Proceedings of the 25th International Conference on Information, Communication and Automation Technologies. IEEE, 2015: 1-6.
[13] Xia C, Jiang X, Liu S, et al. Dynamic Item-Based Recommendation Algorithm with Time Decay[C]//Proceedings of the 6th International Conference on Natural Computation. IEEE, 2010,1:242-247.
[14] Karahodza B, Supic H, Donko D. An Approach to Design of Time-Aware Recommender System Based on Changes in Group User's Preferences[C]//Proceedings of the 10th International Symposium on Telecommunications. IEEE, 2014: 1-4.
[15] 兰艳, 曹芳芳. 面向电影推荐的时间加权协同过滤算法的研究[J]. 计算机科学, 2017,44(4):295-301, 322.
[15] ( Lan Yan, Cao Fangfang. Research of Time Weighted Collaborative Filtering Algorithm for Movie Recommendation[J]. Computer Science, 2017,44(4):295-301, 322.)
[16] Xing S, Liu F, Wang Q, et al. A Hierarchical Attention Model for Rating Prediction by Leveraging User and Product Reviews[J]. Neurocomputing, 2019,332:417-427.
doi: 10.1016/j.neucom.2018.12.027
[17] Wang J, Lü J. Tag-Informed Collaborative Topic Modeling for Cross Domain Recommendations[J]. Knowledge-Based Systems, 2020,203:106119.
doi: 10.1016/j.knosys.2020.106119
[18] Kala A, Zayani C, Amous I, et al. Social Collaborative Service Recommendation Approach Based on User’s Trust and Domain-Specific Expertise[J]. Future Generation Computer Systems, 2018,80:355-367.
doi: 10.1016/j.future.2017.05.036
[19] 罗海媛, 章牧. 基于用户多属性加权和兴趣相似度的协同过滤算法研究[J]. 情报探索, 2018(5):1-7.
[19] ( Luo Haiyuan, Zhang Mu. Collaborative Filtering Algorithm Based on Users’ Multi-attribute Weighting and Interests Similarity[J]. Information Research, 2018(5):1-7.)
[20] 付芬, 豆育升, 韩鹏, 等. 基于隐式评分和相似度传递的学习资源推荐[J]. 计算机应用研究, 2017,34(12):3725-3729.
[20] ( Fu Fen, Dou Yusheng, Han Peng, et al. Learning Resource Recommendation Based on Implicit Scoring and Similarity Propagation[J]. Application Research of Computers, 2017,34(12):3725-3729.)
[21] 徐元萍, 陈翔. 推荐系统中的新颖性问题研究[J]. 计算机应用研究, 2020,37(8):2310-2314.
[21] ( Xu Yuanping, Chen Xiang. Research on Novelty Problems in Recommendation Systems[J]. Application Research of Computers, 2020,37(8):2310-2314.)
[22] Jamali M, Ester M. A Matrix Factorization Technique with Trust Propagation for Recommendation in Social Networks[C]// Proceedings of the ACM Conference on Recommender Systems. 2010.
[1] 王寒雪,崔文娟,周园春,杜一. 基于机器学习的食源性疾病致病菌识别方法*[J]. 数据分析与知识发现, 2021, 5(9): 54-62.
[2] 陈东华,赵红梅,尚小溥,张润彤. 数据驱动的大型医院手术室运营预测与优化方法研究*[J]. 数据分析与知识发现, 2021, 5(9): 115-128.
[3] 车宏鑫,王桐,王伟. 前列腺癌预测模型对比研究*[J]. 数据分析与知识发现, 2021, 5(9): 107-114.
[4] 苏强, 侯校理, 邹妮. 基于机器学习组合优化方法的术后感染预测模型研究*[J]. 数据分析与知识发现, 2021, 5(8): 65-75.
[5] 曹睿,廖彬,李敏,孙瑞娜. 基于XGBoost的在线短租市场价格预测及特征分析模型*[J]. 数据分析与知识发现, 2021, 5(6): 51-65.
[6] 钟佳娃,刘巍,王思丽,杨恒. 文本情感分析方法及应用综述*[J]. 数据分析与知识发现, 2021, 5(6): 1-13.
[7] 柴国荣,王斌,沙勇忠. 基于多机器学习方法联合的公共卫生风险预测研究——以兰州市流感预测为例*[J]. 数据分析与知识发现, 2021, 5(1): 90-98.
[8] 陈东,王建冬,李慧颖,蔡思航,黄倩倩,易成岐,曹攀. 融合机器学习算法和多因素的禽肉交易量预测方法研究 *[J]. 数据分析与知识发现, 2020, 4(7): 18-27.
[9] 梁野,李小元,许航,胡伊然. CLOpin:一种面向舆情分析与预警领域的跨语言知识图谱架构*[J]. 数据分析与知识发现, 2020, 4(6): 1-14.
[10] 杨恒,王思丽,祝忠明,刘巍,王楠. 基于并行协同过滤算法的领域知识推荐模型研究*[J]. 数据分析与知识发现, 2020, 4(6): 15-21.
[11] 王树义,刘赛,马峥. 基于深度迁移学习的微博图像隐私分类研究*[J]. 数据分析与知识发现, 2020, 4(10): 80-92.
[12] 王若佳,张璐,王继民. 基于机器学习的在线问诊平台智能分诊研究[J]. 数据分析与知识发现, 2019, 3(9): 88-97.
[13] 李纲,周华阳,毛进,陈思菁. 基于机器学习的社交媒体用户分类研究 *[J]. 数据分析与知识发现, 2019, 3(8): 1-9.
[14] 胡佳慧,方安,赵琬清,杨晨柳,任慧玲. 面向知识发现的中文电子病历标注方法研究 *[J]. 数据分析与知识发现, 2019, 3(7): 123-132.
[15] 张金柱,胡一鸣. 融合表示学习与机器学习的专利科学引文标题自动抽取研究*[J]. 数据分析与知识发现, 2019, 3(5): 68-76.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn