Given that the traditional methods cannot perform clustering analysis on the Internet financial credit reporting directly and effectively, a kind of precise clustering analysis of internet financial credit reporting dependent on multidimensional attribute sparse large data is proposed. By measuring the overall distance between Internet financial credit reporting through the sparse large data with multidimensional attributes, the multidimensional attribute sparse large data are used to perform clustering analysis on the overall distance matrix and the component approximate distance matrix between the data, respectively. The correlation relationship between the Internet financial credit reporting under these two perspectives is taken into comprehensive consideration. Multidimensional attribute sparse large data pairs are used to reflect the comprehensive relationship matrix of the original Internet financial credit reporting to achieve clustering with relatively high quality. Numerical experiments show that compared with the traditional clustering methods, the method proposed in this paper can not only reflect the overall data features effectively, but also improve the clustering effect of the original Internet financial credit reporting data through the analysis of the correlation relationship between the important component attribute sequences.

鉴于传统方法不能直接，有效地对互联网金融信用报告进行聚类分析，提出了一种基于多维属性稀疏大数据的精确的互联网金融信用报告聚类分析方法。通过测量具有多维属性的稀疏大数据的互联网金融信用报告之间的总体距离，多维属性稀疏大数据分别用于对数据之间的总体距离矩阵和分量近似距离矩阵进行聚类分析。综合考虑了这两种观点下的互联网金融信用报告之间的相关关系。多维属性稀疏大数据对用于反映原始互联网金融信用报告的综合关系矩阵，以实现较高质量的聚类。数值实验表明，与传统的聚类方法相比，本文提出的方法不仅可以有效地反映总体数据特征，而且可以通过分析两者之间的相关关系来提高原始互联网金融信用报告数据的聚类效果。重要组件属性序列。