期刊文献+

基于CS-RF模型的微额信贷风险预测 被引量:1

下载PDF
导出
摘要 在金融市场中,互联网征信是规避损失风险的重要参考依据,其中违约用户识别率的准确性对征信来说则更为重要。从这一角度出发,本文提出了改进的随机森林算法(CS-RF)。利用金融公司的实际数据,从随机森林原模型基础上加以改进,在训练样本生成决策树后引入代价敏感函数,为多类样本和少类样本的错误分类赋予不同的代价,搜索出更优的决策树集成。通过实证分析,将预测结果与Logistic回归模型,决策树,传统随机森林,BP神经网络进行对比,得出CS-RF模型预测效果最优。
出处 《时代金融》 2019年第8期174-177,共4页 Times Finance
基金 国家自然科学基金资助项目(11471218)
  • 相关文献

参考文献3

二级参考文献34

  • 1石晓军,肖远文,任若恩.Logistic违约率模型的最优样本配比与分界点研究[J].财经研究,2005,31(9):38-48. 被引量:49
  • 2THOMAS L C. A survey of credit and behavioural scoring: forecasting financial risk of lending to consumers[ J]. International Journal of Forecasting, 2000,16 ( 2 ) : 149-172.
  • 3FRIEDMAN N, GEIGER D, GOLDSZMIDT M. Bayesian network classifiers[ J]. Machine Learning, 1997,29 (2-3) : 131-163.
  • 4KANE M J, SAVAKIS A A. Bayesian network structure learning and inference in indoor vs. outdoor image classification [ C ]//Proc of the 17th International Conference on Pattern Recognition. Washington DC : IEEE Computer Society, 2004:479-482.
  • 5NG G, ONG K. Using a qualitative probabilistic networks to explain diagnostic reasoning in an expert system for chest pain diagnosis[ J]. Computers in Cardiology, 2000,27:569-573.
  • 6SAHAMI M, DUMAIS S, HECKERMAN D, et al. A Bayesian approach to filtering junk e-mail, WS- 98- 05 [ R ]. Madison : AAAI, 1998.
  • 7BAESENS B, VERSTRAETEN G, POEL D V, et al. Bayesian network classifiers for identifying the slope of the customer lifecycle of long-life customers [ J]. European Journal of Operational Research, 2004,156(2) :508-523.
  • 8CHICKERING D M, HECKERMAN D. A decision theoretic approach to targeted advertising, MSR-TR-2000-17 [ R ]. Redmond : Microsoft Research, 2000.
  • 9DUDA R O, HART P E, STORK D G. Pattern classification [ M ].影印版.北京:中信出版社,2003.
  • 10HECKERMAN D, GEIGER D. Learning Bayesian networks:the combination of knowledge and statistical data, MSR-TR-94-09 [ R]. Redmond : Microsoft Research, 1994.

共引文献93

同被引文献2

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部