计算机应用 ›› 2014, Vol. 34 ›› Issue (4): 1114-1117.DOI: 10.11772/j.issn.1001-9081.2014.04.1114

• 人工智能 • 上一篇    下一篇

融合时间综合影响的轮盘赌游走个性化推荐算法

赵婷,肖如良,孙聪,陈洪涛,李源鑫,李洪恩   

  1. 福建师范大学 软件学院,福州 350108
  • 收稿日期:2013-09-29 修回日期:2013-11-10 出版日期:2014-04-01 发布日期:2014-04-29
  • 通讯作者: 肖如良
  • 作者简介:赵婷(1989-),女,湖南湘潭人,硕士研究生,主要研究方向:Web智能推荐、数据挖掘;
    肖如良(1966-),男,湖南娄底人,教授,博士,CCF高级会员,主要研究方向:计算智能、软件工程;
    孙聪(1989-),男,湖南娄底人,硕士研究生,主要研究方向:软件工程;
    陈洪涛(1989-),男,湖北咸宁人,硕士研究生,主要研究方向:推荐系统、机器学习;
    李源鑫(1990-),女,福建福州人,硕士研究生,主要研究方向:Web智能推荐、数据挖掘;
    李宏恩(1987-),男,江苏南京人,硕士研究生,主要研究方向:推荐系统、机器学习。
  • 基金资助:

    教育部规划基金项目;福建省科技计划重大项目

Personalized recommendation algorithm integrating roulette walk and combined time effect

ZHAO Ting,XIAO Ruliang,SUN Cong,CHEN Hongtao,LI Yuanxin,LI Hongen   

  1. Faculty of Software, Fujian Normal University, Fuzhou Fujian 350108, China
  • Received:2013-09-29 Revised:2013-11-10 Online:2014-04-01 Published:2014-04-29
  • Contact: XIAO Ruliang
  • Supported by:

    Planning fund project of Ministry of Education

摘要:

传统的基于图的推荐算法忽略了时间综合信息影响从而导致推荐质量不高。针对这一问题,提出一种融合时间综合影响的轮盘赌游走个性化推荐算法。该算法以用户项目二分图为基础,引入衰减函数,将时间综合信息对推荐的影响量化成图节点的关联概率;然后采用轮盘赌模型根据关联概率选择游走目标;最终对每个用户做出top-N推荐。实验结果表明:该算法比传统基于图的随机游走PersonalRank算法在推荐的准确度、召回率以及覆盖率指标上都有明显提高。

Abstract:

The traditional graph-based recommendation algorithm neglects the combined time factor which results in the poor recommendation quality. In order to solve this problem, a personalized recommendation algorithm integrating roulette walk and combined time effect was proposed. Based on the user-item bipartite graph, the algorithm introduced attenuation function to quantize combined time factor as association probability of the nodes; Then roulette selection model was utilized to select the next target node according to those associated probability of the nodes skillfully; Finally, the top-N recommendation for each user was provided. The experimental results show that the improved algorithm is better in terms of precision, recall and coverage index, compared with the conventional PersonalRank random-walk algorithm.

中图分类号: