SHI Lihong,TAO Hongcai.Personal Credit Evaluation based on HPSO-BP Neural Network[J].Journal of Chengdu University of Information Technology,2020,35(02):146-150.[doi:10.16836/j.cnki.jcuit.2020.02.004]
基于HPSO-BP神经网络的个人信用评估
- Title:
- Personal Credit Evaluation based on HPSO-BP Neural Network
- 文章编号:
- 2096-1618(2020)02-0146-05
- Keywords:
- BP neural network; standard PSO-BP; HPSO-BP; credit evaluation
- 分类号:
- TP389.1
- 文献标志码:
- A
- 摘要:
- 为了解决BP神经网络和标准PSO-BP神经网络模型收敛慢、易陷入局部最优值等问题,引入改进的粒子群算法HPSO,提出了基于HPSO-BP神经网络的信用评估模型。在PyCharm环境下,利用德国个人信用数据集,分别比较了BP神经网络模型、标准PSO-BP神经网络模型和文中的HPSO-BP神经网络模型。实验结果表明,基于HPSO-BP神经网络的评估模型在收敛速度和准确度上都优于另外两个模型。
- Abstract:
- To solve the problems such as slow convergence, local optimal of BP neural network and standard PSO-BP neural network credit evaluation models, this paper introduces an improved particle swarm algorithm HPSO, and proposes a credit evaluation model based on HPSO-BP neural network. Under PyCharm, by using the German personal credit data set, a comparing experiment is done on the BP neural network,the standard PSO-BP neural network and the HPSO-BP neural network. The results show that the credit evaluation model based on HPSO-BP neural network has better convergence speed and higher accuracy than the other two models.
参考文献/References:
[1] 姜金明.我国个人信用评估研究[D].广州:广东工业大学, 2006.
[2] 尤晓明.个人信用评分系统应用现状与展望[J].中国信用卡,2009(3):59-61.
[3] Khashman A.A Neural Network Model for Credit Risk Evaluation[J].International Journal of Neural Systems,2009,19(4):285-294.
[4] Harikrishna S,Farquad M A H,Shabana. Credit Scoring Using Support Vector Machine:A Comparative Analysis[J].Advanced Materials Research,2012:6527-6533.
[5] Jiang W L.Research and Application of Credit Score Based on Decision Tree Model[C].2010 The 3rd International Conference on Computational Intelligence and Industrial Application(PACIIA-2010),2010:279-283.
[6] Liu N,Xia E J,Yang L.Research and Application of PSO-BP Neural Networks in Credit Risk Assessment[C].Computational Intelligence and Design(ISCID),2010 International Symposium on IEEE,2010:103-106.
[7] Yue Wang,Hao Liu,ZhongXin Yu,et al.An improved artificial neural network based on human-behaviour particle swarm optimization and cellular automata[J].Expert System with Applications,2019,10.1016/j.eswa.2019.1862.
[8] 周俊,陈璟华,刘国祥.粒子群优化算法中惯性权重综述[J].广东电力,2013(7):13-16.
[9] 蒋维.基于改进PSO-BP神经网络的个人信用评价模型及算法研究[D].成都:电子科技大学,2018.
[10] 凌晓,徐鲁帅,梁瑞,等.基于改进PSO-BPNN的输油管道内腐蚀速率研究[J].中国安全生产技术,2019,15(10):63-68.
[11] 蔡荣辉,崔雨轩,薛培静.三层BP神经网络隐层节点数确定方法探究[J].电脑与信息技术,2017,25(5):29-33.
[12] 陈云,石松.基于PSO-BP集成的国内外企业信用风险评估[J].计算机应用研究,2014,31(9):2705-2710.
[13] 仝秋娟,李萌,赵岂.基于分类思想的改进粒子群优化算法[J].现代电子技术,2019,42(19):11-14.
[14] Zhan Z H,Zhang J,Li Y.Adaptive Particle Swarm Optimization[J].IEEE Transactions on Cybernetics.2010,39(6):1362-1381.
[15] 张德慧, 张德育, 刘清云,等.基于粒子群算法的BP神经网络优化技术[J].计算机工程与设计,2015,36(5):1321-1326.
备注/Memo
收稿日期:2019-12-26 基金项目:国家自然科学基金资助项目(61806170)