摘要
通过改进的随机分块模型(SBM)链路预测算法,研究电子商务网络的演化过程与社团结构。针对原始SBM模型块之间的度分布为二项式分布,引入度衰减参数使得随机分块模型中块之间的度分布遵循幂律分布。针对原始SBM模型中节点之间的连接仅仅取决于节点所属块的假设,引入度控制参数使其更接近真实网络的度数分布。基于此提出优化后的随机分块模型,并利用阿里巴巴淘宝数据集验证该算法,结果显示该算法精确度高于随机分块模型(SBM)、度修正的随机分块模型(DCSBM)以及层次结构模型(HBM)。说明改进后的算法能较好地刻画电商网络中的社团结构,准确地发现网络中的缺失链接。
To study the evolution process and community structure of e-commerce networks,this paper used an improved stochastic block model(SBM)link prediction algorithm.Since the degree distribution among blocks in the original SBM model was binomial,to make the degree distribution among blocks follow the power law distribution in the stochastic block model,this paper introduced the degree attenuation parameter.Aiming at the assumption that the connection between nodes depended only on the block to which nodes belong in the original SBM model,to make the degree distribution closer to the real network,the paper introduced the degree control parameter.Based on this,the paper proposed an optimized random block model,and used the Alibaba Taobao data set to verify the proposed algorithm.The results show that the accuracy of the proposed algorithm is higher than the SBM,the degree-corrected stochastic block model(DCSBM)and the hierarchical structure model(HBM).It shows that the improved algorithm can describe the community structure of the e-commerce network well and find the missing link in the network accurately.
作者
史玉林
钱晓东
Shi Yulin;Qian Xiaodong(School of Economics&Management,Lanzhou Jiaotong University,Lanzhou 730070,China)
出处
《计算机应用研究》
CSCD
北大核心
2024年第3期824-830,847,共8页
Application Research of Computers
基金
国家自然科学基金资助项目(71461017)。
关键词
随机分块模型
电商网络
链路预测
推荐
stochastic block model(SBM)
e-commerce network
link prediction
recommendation