基于粒子群算法和核极限学习机的财务危机预测模型

详细信息    查看全文 | 推荐本文 |

英文篇名：Financial Crisis Prediction Model Based on Particle Swarm Optimization and Kernel Extreme Learning Machine 作者：张亚男 ; 刘人境 ; 陈慧灵 英文作者：Zhang Yanan;Liu Renjing;Chen Huiling;School of Management, Xi'an Jiaotong University;Computer Information Network Center,Changchun University of Technology;College of Physics and Electronic Information,Wenzhou University; 关键词：核极限学习机 ; 粒子群算法 ; 特征选择 ; 财务危机预测 英文关键词：kernel extreme learning machine;;particle swarm algorithm;;feature selection;;financial crisis prediction 中文刊名：TJJC 英文刊名：Statistics & Decision 机构：西安交通大学管理学院;长春工业大学计算机信息网络中心;温州大学物理与电子信息工程学院; 出版日期：2019-05-10 13:18 出版单位：统计与决策 年：2019 期：v.35;No.525 基金：国家社会科学基金资助项目(15BGL082);国家社会科学基金西部项目(15XGL001) 语种：中文; 页：TJJC201909016 页数：5 CN：09 ISSN：42-1009/C 分类号：69-73

摘要

文章提出了一种基于粒子群优化算法与核极限学习机的企业财务危机预测方法。考虑到在分类预测的过程中参数优化与特征选择之间的相互影响,利用粒子群优化算法优化核极限学习机参数的同时进行特征选择,从而优化出最优的核极限学习机模型并得到具有代表性的特征子集;最后,使用所提出的最优的核极限学习机模型对新数据集进行训练和预测。实验表明,与其他预测模型进行对比实验,该方法具有更好的性能,方法可行有效且实用。
        This paper proposes a method of financial crisis prediction based on particle swarm optimization(PSO) algorithm and kernel extreme learning machine. Considering the interaction between parameter optimization and feature selection in the process of classification prediction, the paper uses PSO algorithm to optimize the parameters of kernel extreme learning machine and simultaneously select the features so as to optimize the optimal kernel extreme learning machine model and obtain the representative feature subset. Finally, the paper uses the proposed optimal kernel extreme learning machine model to practice and predict the new data set. Experimental results show that this method is feasible, effective and practical, and also has better performance compared with other prediction models.

引文

[1]Sun J, Li H. Financial Distress Prediction Using Support Vector Machines:Ensemble vs. Individual[J]. Applied Soft Computing Journal,2012, 12(8).
    [2]王刚,刘元宁,陈慧灵等.粗糙集与支持向量机在肝炎诊断中的应用[J].吉林大学学报(工学版), 2011, 41(1).
    [3]李春香,张为民,钟碧良等.最小二乘支持向量机的参数优化算法研究[J].杭州电子科技大学学报, 2010, 30(4).
    [4]Huang G B, Zhou H, Ding X, et al. Extreme Learning Machine for Regression and Multiclass Classification[J]. IEEE Transactions on Systems Man&Cybernetics Part B, 2012, 42(2).
    [5]马超.基于元启发优化极限学习机的分类算法及其应用研究[D].长春:吉林大学博士论文, 2014.
    [6]王保义,赵硕,张少敏.基于云计算和极限学习机的分布式电力负荷预测算法[J].电网技术, 2014, 38(2).
    [7]江晟.混合交通视频检测关键技术研究[D].长春:吉林大学博士论文, 2013.
    [8]Horta R A M, Alves F J D S. Attribute Selection in Bankruptcy Prediction:Application and Evaluation Using Recent Brazilian Data[J].Ram Rev.adm.mackenzie, 2014, 15(1).
    [9]Eberhart R C, Shi Y. Particle Swarm Optimization:Development, Applications and Resources[C]. Evolutionary Computation, 2001. Proceedings of the 2001 Congress on. IEEE, 2001.
    [10]Chen H L, Yang B, Wang G, et al. A Novel Bankruptcy Prediction Model Based on an Adaptive Fuzzy, k-Nearest Neighbor Method[J].Knowledge-Based Systems, 2011, 24(8).
    [11]陈慧灵.面向智能决策问题的机器学习方法研究[D].长春:吉林大学博士论文, 2012.
    [12]Ratnaweera A, Halgamuge S K, Watson H C. Self-organizing Hierarchical Particle Swarm Optimizer With Time-varying Acceleration Coefficients[J]. IEEE Transactions on Evolutionary Computation,2004, 8(3).
    [13]Kennedy J, Eberhart R C. A Discrete Binary Version of the Particle Swarm Algorithm[C]. Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation, 1997 IEEE International Conference on. IEEE, 1997.
    [14]Wieslaw P. Application of Discrete Predicting Structures in an Early Warning Expert System for Financial Distress[D]. Szczecin:Szczecin Technical University, 2004.