Please wait a minute...
Advanced Search
数据分析与知识发现  2018, Vol. 2 Issue (7): 72-80     https://doi.org/10.11925/infotech.2096-3467.2017.0857
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
考虑时间动态性和序列模式的个性化推荐算法*
李杰1(), 杨芳1, 徐晨曦2
1河北工业大学经济管理学院 天津 300401
2京东集团公司 北京 100176
A Personalized Recommendation Algorithm with Temporal Dynamics and Sequential Patterns
Li Jie1(), Yang Fang1, Xu Chenxi2
1School of Economics and Management, Hebei University of Technology, Tianjin 300401, China
2Jingdong Group, Beijing 100176, China
全文: PDF (527 KB)   HTML ( 1
输出: BibTeX | EndNote (RIS)      
摘要 

目的】在电子商务个性化推荐中考虑商品销售的时间动态性和序列模式问题, 提高推荐效果。【方法】提出一种改进的个性化推荐算法: 引入时间系数和热门系数, 改进评分相似性函数, 提出新的用户兴趣相似度计算方法; 加入商品序列模式, 给出二项序列模式挖掘算法, 用序列模式对推荐结果进行筛选排序。【结果】利用2004年-2005年亚马逊图书评论数据进行测试, 与基于修正余弦的协同过滤算法相比较, 改进算法的推荐准确率和F值分别提高1.89%和0.73%。【局限】该算法没有考虑用户评价分数高低个人倾向的影响。【结论】改进的相似性函数和通过序列模式对结果进行筛选两个方面均能提高个性化推荐效果。

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
李杰
杨芳
徐晨曦
关键词 个性化推荐时间动态性序列模式协同过滤热门系数    
Abstract

[Objective] This study is to improve the effectiveness of merchandise recommendation based on temporal dynamics and sequential patterns of sales. [Methods] We developed an improved personalized recommendation algorithm for electronic commerce. First, we introduced a new similarity calculation function with time and hot coefficients. Then, we proposed an algorithm with the two-item sequential pattern, which modified the recommended list based on the sequential patterns. [Results] We examined the new method with book review data of Amazon.com from 2004-2005, and found its precision and F values were 1.89% and 0.73% higher than the collaborative filtering algorithm with adjusted cosine similarity. [Limitations] The proposed model did not examine the violations of consumers’ review scores. [Conclusions] Both the similarity function and sequential patterns can improve the effectiveness of personalized recommendation algorithms for e-commerce.

Key wordsPersonalized Recommendation    Temporal Dynamics    Sequential Patterns    Collaborative Filtering    Hot Coefficient
收稿日期: 2017-08-24      出版日期: 2018-08-15
ZTFLH:  TP311  
基金资助:*本文系国家社会科学基金项目“电子商务环境下的消费者认知与行为研究”(项目编号: 16FGL014)和河北省自然科学基金项目“电子商务个性化推荐中的动态模式挖掘理论与应用研究”(项目编号: G2014202148)的研究成果之一
引用本文:   
李杰, 杨芳, 徐晨曦. 考虑时间动态性和序列模式的个性化推荐算法*[J]. 数据分析与知识发现, 2018, 2(7): 72-80.
Li Jie,Yang Fang,Xu Chenxi. A Personalized Recommendation Algorithm with Temporal Dynamics and Sequential Patterns. Data Analysis and Knowledge Discovery, 2018, 2(7): 72-80.
链接本文:  
http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2017.0857      或      http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2018/V2/I7/72
  改进的个性化推荐算法测试步骤
TopN 相似度函数 准确率 召回率 F值
5 皮尔逊 7.25% 6.33% 6.76%
余弦相似 7.98% 8.06% 8.02%
修正余弦 8.26% 8.11% 8.18%
本文改进函数 8.24% 9.34% 8.76%
10 皮尔逊 10.38% 9.96% 10.17%
余弦相似 11.24% 10.01% 10.59%
修正余弦 12.22% 11.88% 12.05%
本文改进函数 13.58% 11.79% 12.62%
20 皮尔逊 10.38% 10.48% 10.43%
余弦相似 11.24% 10.84% 11.04%
修正余弦 11.98% 12.65% 12.43%
本文改进函数 11.79% 13.05% 12.39%
  相似度计算函数比较
TopN 相似度函数 序列模式 准确率 召回率 F值
10 本文改进函数 使用 14.11% 11.68% 12.78%
不使用 13.58% 11.79% 12.62%
  协同过滤中序列模式的应用比较
[1] 李杰, 徐勇, 王云峰, 等. 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, 29(8): 144-152.
doi: 10.3321/j.issn:1000-6788.2009.08.017
[1] (Li Jie, Xu Yong, Wang Yunfeng, et al.Strongest Association Rules Mining for Personalized Recommendation[J]. Systems Engineering—Theory & Practice, 2009, 29(8): 144-152.)
doi: 10.3321/j.issn:1000-6788.2009.08.017
[2] 朱夏, 宋爱波, 东方, 等. 云计算环境下基于协同过滤的个性化推荐机制[J]. 计算机研究与发展, 2014, 51(10): 2255-2269.
doi: 10.7544/issn1000-1239.2014.20130056
[2] (Zhu Xia, Song Aibo, Dong Fang, et al.A Collaborative Filtering Recommendation Mechanism for Cloud Computing[J]. Journal of Computer Research and Development, 2014, 51(10): 2255-2269.)
doi: 10.7544/issn1000-1239.2014.20130056
[3] De Campos L M, Fernández-Luna J M, Huete J F, et al. Combining Content-Based and Collaborative Recommendations: A Hybrid Approach Based on Bayesian Networks[J]. International Journal of Approximate Reasoning, 2010, 51(7): 785-799.
doi: 10.1016/j.ijar.2010.04.001
[4] 冷亚军, 陆青, 梁昌勇. 协同过滤推荐技术综述[J]. 模式识别与人工智能, 2014, 27(8): 720-734.
doi: 10.3969/j.issn.1003-6059.2014.08.007
[4] (Leng Yajun, Lu Qing, Liang Changyong.Survey of Recommendation Based on Collaborative Filtering[J]. Pattern Recognition and Artificial Intelligence, 2014, 27(8): 720-734.)
doi: 10.3969/j.issn.1003-6059.2014.08.007
[5] 邓晓懿, 金淳, 韩庆平. 基于情境聚类和用户评级的协同过滤推荐模型[J]. 系统工程理论与实践, 2013, 33(11): 2945-2953.
[5] (Deng Xiaoyi, Jin Chun, Han Qingping.Improved Collaborative Filtering Model Based on Context Clustering and User Ranking[J]. Systems Engineering—Theory & Practice, 2013, 33(11): 2945-2953.)
[6] 杨芳, 潘一飞, 李杰, 等. 一种改进的协同过滤推荐算法[J]. 河北工业大学学报, 2010, 39(3): 82-87.
doi: 10.3969/j.issn.1007-2373.2010.03.019
[6] (Yang Fang, Pan Yifei, Li Jie, et al.An Adaptive Algorithm for Collaborative Filtering Recommendation[J]. Journal of Hebei University of Technology, 2010, 39(3): 82-87.)
doi: 10.3969/j.issn.1007-2373.2010.03.019
[7] 薛福亮, 刘君玲. 基于用户间信任关系改进的协同过滤推荐方法[J]. 数据分析与知识发现, 2017, 1(7): 90-99.
[7] (Xue Fuliang, Liu Junling.Improving Collaborative Filtering Recommendation Based on Trust Relationship Among Users[J]. Data Analysis and Knowledge Discovery, 2017, 1(7): 90-99.)
[8] 涂海丽, 唐晓波. 基于标签的商品推荐模型研究[J]. 数据分析与知识发现, 2017, 1(9): 28-39.
[8] (Tu Haili, Tang Xiaobo.Building Product Recommendation Model Based on Tags[J]. Data Analysis and Knowledge Discovery, 2017, 1(9): 28-39.)
[9] 侯银秀, 李伟卿, 王伟军, 等. 基于用户偏好与商品属性情感匹配的图书个性化推荐研究[J]. 数据分析与知识发现, 2017, 1(8): 9-17.
[9] (Hou Yinxiu, Li Weiqing, Wang Weijun, et al.Personalized Book Recommendation Based on User Preferences and Commodity Features[J]. Data Analysis and Knowledge Discovery, 2017, 1(8): 9-17.)
[10] 韦素云, 业宁, 杨旭兵. 结合项目类别和动态时间加权的协同过滤算法[J]. 计算机工程, 2017, 40(6): 206-210.
[10] (Wei Suyun, Ye Ning, Yang Xubing.Collaborative Filtering Algorithm Combining Item Category and Dynamic Time Weighting[J]. Computer Engineering, 2017, 40(6): 206-210.)
[11] Liu C C.Search Recommendation Model Based on User Search Behavior and Gradual Forgetting Collaborative Filtering Strategy[J]. Journal of China Universities of Posts and Telecommunications, 2010, 17(3): 110-117.
[12] 邹永贵, 望靖, 刘兆宏, 等. 基于项目之间相似性的兴趣点推荐方法[J]. 计算机应用研究, 2012, 29(1): 116-118, 126.
doi: 10.3969/j.issn.1001-3695.2012.01.032
[12] (Zou Yonggui, Wang Jing, Liu Zhaohong, et al.Point of Interest Recommendation Method Based on Similarity Between Items[J]. Application Research of Computers, 2012, 29(1): 116-118, 126.)
doi: 10.3969/j.issn.1001-3695.2012.01.032
[13] Liu S Z, Luo Z D, Liu Y A.Spreading Code Design for Downlink Space-Time-Frequency Spreading CDMA[J]. IEEE Transactions on Vehicular Technology, 2008, 57(5): 2933-2946.
doi: 10.1109/TVT.2008.917234
[14] Resnick P, Varian H R.Recommender System[J]. Communications of the ACM, 1997, 40(3): 56-58.
[15] Koren Y.Collaborative Filtering with Temporal Dynamics[J]. Communications of the ACM, 2010, 53(4): 89-97.
doi: 10.1145/1721654.1721677
[16] 宋文君, 郭强, 刘建国. 时间窗口对个性化推荐算法的影响研究[J]. 复杂系统与复杂性科学, 2015, 12(1): 28-32.
[16] (Song Wenjun, Guo Qiang, Liu Jianguo.Effect of the Time Window on the Personalized Recommendation Algorithm[J]. Complex Systems and Complexity Science, 2015, 12(1): 28-32.)
[17] 邹凌君, 陈崚, 李娟. 时间加权的混合推荐算法[J]. 计算机科学, 2016, 43(11A): 451-454.
[17] (Zou Lingjun, Chen Jun, Li Juan.Time-Weighted Hybrid Recommender Algorithm[J]. Computer Science, 2016, 43(11A): 451-454.)
[18] 谭黎立, 聂瑞华, 梁军, 等. 基于动态时间的个性化推荐模型[J]. 华南师范大学学报:自然科学版, 2017, 49(3): 123-128.
doi: 10.6054/j.jscnun.2017015
[18] (Tan Lili, Nie Ruihua, Liang Jun, et al.Personalized Recommendation Model Based on Dynamic Time[J]. Journal of South China Normal University:Natural Science Edition, 2017, 49(3): 123-128.)
doi: 10.6054/j.jscnun.2017015
[19] 李道国,李连杰,申恩平. 基于用户评分时间改进的协同过滤推荐算法[J]. 现代图书情报技术, 2016(9): 65-69.
[19] (Li Daoguo, Li Lianjie, Shen Enping.New Collaborative Filtering Recommendation Algorithm Based on User Rating Time[J]. New Technology of Library and Information Service, 2016(9): 65-69.)
[20] 覃幸新,王荣波,黄孝喜, 等. 基于多权值的Slope One协同过滤算法[J]. 数据分析与知识发现, 2017, 1(6): 65-71.
[20] (Qin Xingxin, Wang Rongbo, Huang Xiaoxi, et al.Slope One Collaborative Filtering Algorithm Based on Multi-Weights[J]. Data Analysis and Knowledge Discovery, 2017, 1(6): 65-71.)
[21] 李杰,王娜娜,李志鹏,等.面向个性化交通信息服务的车辆行驶路径关联规则挖掘[J].系统工程理论与实践, 2013, 33(12): 3209-3215.
doi: 10.3969/j.issn.1000-6788.2013.12.027
[21] (Li Jie, Wang Nana, Li Zhipeng, et al.Association Rules Mining of Vehicle Routing for Personalized Traffic Information Service[J]. Systems Engineering—Theory & Practice, 2013, 33(12): 3209-3215.)
doi: 10.3969/j.issn.1000-6788.2013.12.027
[22] 付沙. 基于序列模式挖掘的图书馆用户借阅行为分析[J]. 情报理论与实践, 2014, 37(6): 103-106.
[22] (Fu Sha.Analysis of Library Users Borrowing Behaviors Based on Sequential Patterns Mining[J]. Information Studies: Theory & Application, 2014, 37(6): 103-106.)
[23] Mishra R, Kumar P, Bhasker B.A Web Recommendation System Considering Sequential Information[J]. Decision Support Systems, 2015, 75(C): 1-10.
doi: 10.1016/j.dss.2015.04.004
[24] Salehi M, Kamalabadi I N, Ghoushchi M B G. Personalized Recommendation of Learning Material Using Sequential Pattern Mining and Attribute Based Collaborative Filtering[J]. Education and Information Technologies, 2014, 19(4): 713-735.
doi: 10.1007/s10639-012-9245-5
[25] 郑翠翠, 李林. 协同过滤算法中的相似性度量方法研究[J]. 计算机工程与应用, 2014, 50(8): 147-149, 206.
doi: 10.3778/j.issn.1002-8331.1204-0749
[25] (Zheng Cuicui, Li Lin.Research on Method of Similarity Measurement in Collaborative Filter Algorithm[J]. Computer Engineering and Applications, 2014, 50(8): 147-149, 206. )
doi: 10.3778/j.issn.1002-8331.1204-0749
[26] Wu H C, Luk R W P, Wong K F, et al. Interpreting TF-IDF Term Weights as Making Relevance Decisions[J]. ACM Transactions on Information Systems, 2008, 26(3): 55-59.
[27] 吴军. 数学之美[M]. 第2版. 北京: 人民邮电出版社, 2014.
[27] (Wu Jun.Beauty of Mathematics[M]. The 2nd Edition. Beijing: Posts & Telecom Press, 2014.)
[28] 项亮. 推荐系统实践[M]. 北京: 人民邮电出版社, 2012.
[28] (Xiang Liang.Recommendation System Practice [M]. Beijing: Posts & Telecom Press, 2012.)
[1] 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.
[2] 苏庆,陈思兆,吴伟民,李小妹,黄佃宽. 基于学习情况协同过滤算法的个性化学习推荐模型研究*[J]. 数据分析与知识发现, 2020, 4(5): 105-117.
[3] 郑淞尹,谈国新,史中超. 基于分段用户群与时间上下文的旅游景点推荐模型研究*[J]. 数据分析与知识发现, 2020, 4(5): 92-104.
[4] 魏伟,郭崇慧,邢小宇. 基于语义关联规则的试题知识点标注及试题推荐*[J]. 数据分析与知识发现, 2020, 4(2/3): 182-191.
[5] 焦富森,李树青. 基于物品质量和用户评分修正的协同过滤推荐算法 *[J]. 数据分析与知识发现, 2019, 3(8): 62-67.
[6] 李珊,姚叶慧,厉浩,刘洁,嘎玛白姆. 基于ISA联合聚类的组推荐算法研究 *[J]. 数据分析与知识发现, 2019, 3(8): 77-87.
[7] 张怡文,张臣坤,杨安桔,计成睿,岳丽华. 基于条件型游走的四部图推荐方法*[J]. 数据分析与知识发现, 2019, 3(4): 117-125.
[8] 叶佳鑫,熊回香. 基于标签的跨领域资源个性化推荐研究*[J]. 数据分析与知识发现, 2019, 3(2): 21-32.
[9] 聂卉. 结合词向量和词图算法的用户兴趣建模研究 *[J]. 数据分析与知识发现, 2019, 3(12): 30-40.
[10] 丁浩,李树青. 基于用户多类型兴趣波动趋势预测分析的个性化推荐方法 *[J]. 数据分析与知识发现, 2019, 3(11): 43-51.
[11] 王道平, 蒋中杨, 张博卿. 基于灰色关联分析和时间因素的协同过滤算法*[J]. 数据分析与知识发现, 2018, 2(6): 102-109.
[12] 王永, 王永东, 郭慧芳, 周玉敏. 一种基于离散增量的项目相似性度量方法*[J]. 数据分析与知识发现, 2018, 2(5): 70-76.
[13] 花凌锋, 杨高明, 王修君. 面向位置的多样性兴趣新闻推荐研究*[J]. 数据分析与知识发现, 2018, 2(5): 94-104.
[14] 侯银秀, 李伟卿, 王伟军, 张婷婷. 基于用户偏好与商品属性情感匹配的图书个性化推荐研究*[J]. 数据分析与知识发现, 2017, 1(8): 9-17.
[15] 薛福亮, 刘君玲. 基于用户间信任关系改进的协同过滤推荐方法*[J]. 数据分析与知识发现, 2017, 1(7): 90-99.
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