Title :
Fuzzy clustering of clients´ credit risk for futures company
Author :
Ye, Zhongxing ; Zehao Shen
Author_Institution :
School of Business Information Management, Shanghai Institute of Foreign Trade, China
Abstract :
Based on the real clients´ transaction data, several characteristic indices are defined and computed first. These indices then serve as basic variables for clustering. K-means clustering and improved fuzzy clustering approaches are applied to client classification. The final classification is obtained by using intersection-based clustering combination algorithm. The clustering result provides the scientific base for futures companies to improve the clients´ risk management.
Keywords :
Futures; K-means clustering; credit risk; fuzzy clustering;
Conference_Titel :
Automatic Control and Artificial Intelligence (ACAI 2012), International Conference on
Conference_Location :
Xiamen
Electronic_ISBN :
978-1-84919-537-9
DOI :
10.1049/cp.2012.1166