K-means algorithm and its application for clustering companies listed in Zhejiang province

Y. Qian
2006 WIT Transactions on Information and Communication Technologies   unpublished
There exist many problems in the credit market where we have data that needs to be classified into distinct groups. This paper will introduce a financial K-means algorithm, which based on the historical financial ratios, applies the cluster analysis technology to analyze the listed enterprises in Zhejiang province. We analyze indicators related to financial attributes and choose nine finance indicators. According to better valuation on the companies listed, we apply "trial and error" and choose
more » ... d error" and choose four as the number of clustering. Testing shows that companies belong to cluster 2 and cluster 3 add up to 71 companies, including 87% in all. They are all companies worthy of making loans, which is inconsistent with the good economic situation of Zhejiang province. Category 4 has nine companies including 11% that are judged as high risk business. So banks should provide these customers for loans with a mortgage or guarantee.
doi:10.2495/data060041 fatcat:rvatceq5ubfmfasrluj7bes6ku