The design of financial risk control system platform for private lending logistics information
- 147 Downloads
With the increasing popularity of credit, credit fraud is gradually increasing. Based on this, this paper takes use of computer technology and designs a credit fraud prediction model based on clustering analysis and integration improved support vector machine. First of all, adjust and reduce the imbalance based on K-means clustering analysis combined with more-than-half random sampling. Secondly, the idea of integrated learning was used to further deal with the imbalance of data and increase the attention of classifiers to minority classes. Finally, we tested the algorithm. The results showed that the algorithm effectively reduced the cost of accidental injury and provided a great possibility for the effective reduction of economic losses caused by credit fraud. It also provided a good theoretical basis for practical application.
KeywordsCluster analysis Integration improvement Support vector machine Credit risk
- 4.Tanaka, Y., Takahashi, M.: Dynamic time warping-based cluster analysis and support vector machine-based prediction of solar irradiance at multi-points in a wide area. In: Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications, pp. 210–215 (2016)CrossRefGoogle Scholar
- 10.Kianmehr, K., Alhajj, R.: A fuzzy prediction model for calling communities. Int. J. Netw. Virtual Organ. 8(7), 75–97 (2017)Google Scholar