信用风险评估中DKIPSO-SVC组合模型的仿真研究

系统仿真学报 ›› 2015, Vol. 27 ›› Issue (8): 1875-1880.

信用风险评估中DKIPSO-SVC组合模型的仿真研究

万振海, 刘铁英, 张扬, 李吉双

内蒙古大学计算机学院, 呼和浩特 010021

收稿日期:2015-05-15 修回日期:2015-07-19 出版日期:2015-08-08 发布日期:2020-08-03
作者简介:万振海(1988-), 男, 甘肃人, 硕士生, 研究方向为运筹与智能决策;刘铁英(1957-), 男, 内蒙古人, 硕士, 教授, 研究方向为运筹与智能决策; 张扬(1990-), 男, 湖北人, 硕士生, 研究方向为运筹与智能决策。
基金资助:
国家自然科学基金项目(61363079)

Simulation and Application of DKIPSO-SVC Combined Model for Credit Risk Assessment

Wan Zhenhai, Liu Tieying, Zhang Yang, Li Jishuang

College of Computer Science, Inner Mongolia University, Hohhot 010021, China

Received:2015-05-15 Revised:2015-07-19 Online:2015-08-08 Published:2020-08-03

摘要/Abstract

摘要： 借助于支持向量分类机(SVC)的强泛化能力与鲁棒性,针对GDS-SVC、DIPSO-SVC选取参数的低效性,在改进的粒子群算法(DIPSO)位置更新过程中引入缩减因子(DKIPSO),建立基于DKIPSO自动选取SVC参数的DKIPSO-SVC组合模型,并将其应用于商业银行的信用评估。仿真结果表明,DKIPSO-SVC模型的鲁棒性优于DIPSO-SVC;DKIPSO-SVC分类精度为96.6049%,高于DIPSO-SVC93.8272%和GDS-SVC92.5926%。DKIPSO-SVC模型把第2类误判率从8.5526%降低到1.9737%,降低幅度近76.9228%,这将在极大程度上规避了商业银行的信用风险。

关键词: 信用评估, 支持向量机, 粒子群算法, DKIPSO-SVC模型

Abstract: In order to improve the problem of inefficient parameter selection of the GDS-SVC model and DIPSO-SVC model, and utilize the generalization ability and robustness of support vector classification (SVC), the reduction factor of location updating was introduced based on the dynamic improvement Particle Swarm Optimization (DIPSO), and then the DKIPSO-SVC of parameters selecting in SVC was established based on DKIPSO. The method was applied to credit scoring of commercial banks. The simulation results demonstrate that the robustness of the DKIPSO-SVC model is better than DIPSO-SVC. But beyond that, the accuracy of DKIPSO-SVC model achieves 96.6049%, higher than that of DIPSO-SVC and GDS-SVC model, which is 93.8272% and 92.5926%. More importantly, the type II error rate was reduced significantly from 8.5526% to1.9737%, about 76.9228% lower than current model.

Key words: credit scoring, support vector machine, particle swarm optimization, DKIPSO-SVC model

中图分类号:

TP391.9
F830

万振海, 刘铁英, 张扬, 李吉双. 信用风险评估中DKIPSO-SVC组合模型的仿真研究[J]. 系统仿真学报, 2015, 27(8): 1875-1880.

Wan Zhenhai, Liu Tieying, Zhang Yang, Li Jishuang. Simulation and Application of DKIPSO-SVC Combined Model for Credit Risk Assessment[J]. Journal of System Simulation, 2015, 27(8): 1875-1880.

参考文献

[1] Qin R, Liu L L, Xie J.An application of improved BP neural network in personal credit scoring[C]// Proceedings of the second International Conference on Computer Modeling and Simulation. Sanya, Hainan: IEEE, 2010: 238-241.
[2] Lyn C, Thomas. A survey of credit and behavioral scoring: forecasting financial risk of lending to consumers[J]. International Journal of Forecasting (S0169-2070), 2000, 16(2): 149-172.
[3] Lin W Y, Hu Y H, Tsai C F.Machine learning in financial vrisis prediction: a survey[J]. Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on (S1094-6977), 2012, 42(4): 421-436.
[4] Akihiro N, Hideharu F, Shinichi M.Weighted majority decision among several region rules for scientific discovery[J]. Discovery Science (S0302-9743), 1999, 1721(3): 17-29.
[5] Tony V G, Bart B, Joao G, Peter V D.A Support Vector Machines approach to credit scoring[J]. Bank en Financiewezen, 2003, 2(3): 73-82.
[6] 高尚, 刘夫成. 与K均值混合的支持向量机的个人信用评估[J]. 中南大学学报(自然科学版), 2013, 44(2): 169-173.
[7] 余乐安, 姚潇. 基于中心化支持向量机的信用风险评估模型[C]//第六届中国管理学年会-商务智能分会场论文集, 中国管理现代化研究会, 2011.
[8] Tang C L, Huang Y R, Qu L G, Ling L Y.Research on improved particle swarm algorithms and its application in function optimization[C]// Proceedings of the 2010 International Conference on Broadcast Technology and Multimedia Communication. India: Springer, 2010: 343-346.
[9] Xue Z H, Du P J, Su H J.Harmonic analysis for hyper-spectral image classification integrated with PSO optimized SVM[J]. IEEE Journal of selected topics in applied earth observations and remote sensing (S1939-1404), 2014, 7(6): 2131-2146.
[10] Hasseim A A, Sudirman R, Khalid P I.Handwriting classification based on Support Vector Machine with cross validation[J]. Engineering (S1947-3931), 2013, 5: 84-87.
[11] 姜明辉, 袁绪川, 冯玉强. PSO-SVM模型的构建与应用[J]. 哈尔滨工业大学学报, 2009, 41(2): 169-171.
[12] 肖本贤, 王晓伟, 刘一福. MPSO-RBF优化策略在锅炉过热系统辨识中的仿真研究[J]. 系统仿真学报, 2007, 19(6): 1382-1389.
[13] Shi Y H, Eberhart R C.A modified Particle Swarm Optimization[C]// Proceedings of the IEEE International Conference on Evolutionary Computation. Anchorage, Alaska, USA: IEEE,1998: 69-73.
[14] Clerc M, The swarm and the queen: towards a deterministic and adaptive particle swarm optimization[C]// Proceedings of the 1999 Congress on Evolutionary Computation (CEC 99). Washington, USA: IEEE, 1999, 3: 1951-1957.

[1]	马立新, 程颍. 计及可中断负荷的园区综合能源系统优化调度[J]. 系统仿真学报, 2022, 34(4): 817-825.
[2]	张凯庆, 嵇启春. 速度时变的多中心半开放式车辆路径问题研究[J]. 系统仿真学报, 2022, 34(4): 836-846.
[3]	陈魁, 毕利, 王文雅. 柔性作业车间AGV与机器双资源集成调度研究[J]. 系统仿真学报, 2022, 34(3): 461-469.
[4]	孙晓安, 栾小丽, 刘飞. 基于智能优化灰色模型的电子固废预测[J]. 系统仿真学报, 2022, 34(3): 536-542.
[5]	李晖, 云昊, 岳红丽. 基于SVM逆系统的PMSM云模型整定PID控制[J]. 系统仿真学报, 2021, 33(8): 1846-1855.
[6]	魏腾飞, 潘庭龙. 基于改进PSO优化LSTM网络的短期电力负荷预测[J]. 系统仿真学报, 2021, 33(8): 1866-1874.
[7]	牛侃, 李冰, 付强. 基于混沌扰动机制粒子群算法的战场频率分配方法[J]. 系统仿真学报, 2021, 33(8): 1905-1913.
[8]	孟建军, 王终军, 胥如迅, 李德仓. 基于模糊复合策略的高速列车主动悬挂控制研究[J]. 系统仿真学报, 2021, 33(7): 1554-1564.
[9]	魏瑞轩, 吴子沉. 无人机集群实时任务分配方法研究[J]. 系统仿真学报, 2021, 33(7): 1574-1581.
[10]	位晶晶, 刘勤明, 叶春明, 李冠林. 基于GA-SVR的小样本数据缺失下的设备故障诊断[J]. 系统仿真学报, 2021, 33(6): 1342-1349.
[11]	刘晓琳, 吴竟祎. 飞机舵机电液加载系统控制补偿器设计与仿真[J]. 系统仿真学报, 2021, 33(5): 1031-1038.
[12]	汪润鸿, 王红军, 邹湘军, 曾泽钦, 李慧, 黄钊丰, 刘伟良. 基于混合粒子群算法的组合式变速箱传动比优化研究[J]. 系统仿真学报, 2021, 33(4): 825-836.
[13]	陈魁, 毕利. 改进粒子群算法在考虑运输时间下的FJSP研究[J]. 系统仿真学报, 2021, 33(4): 845-853.
[14]	孙宇贞, 唐毅伟, 李帅. 基于改进粒子群算法的超超临界燃煤机组负荷系统建模[J]. 系统仿真学报, 2021, 33(4): 875-882.
[15]	邵诚, 孙宏远, 张林. 基于PSO-LSSVM的反舰导弹自控弹道仿真[J]. 系统仿真学报, 2021, 33(4): 918-926.