基于子空间多核学习的企业财务困境预测方法

doi:10.12005/orms.2021.0026

摘要/Abstract

摘要： 财务指标的异构性是影响企业财务困境预测精度的重要因素,现有多核学习方法能够用于解决异构数据学习问题。本文首先介绍了子空间多核学习财务困境预测理论框架,在此基础上根据子空间学习的最大化方差准则、类别可分性最大化准则、非线性子空间映射原理,提出了三种子空间多核学习方法,分别为最大化方差投影子空间多核学习、类别可分性最大化子空间多核学习、非线性子空间多核学习。利用采集的我国上市公司数据进行实验,对比所提出的方法同现有代表性财务困境预测方法,并对实验结果进行分析。实验结果表明,本文提出的子空间多核学习财务困境预测框架行之有效,该框架下所构造的子空间多核学习预测方法能够有效地提升财务困境预测精度。

关键词: 财务困境预测, 核方法, 支持向量机, 多核学习

Abstract: Heterogeneity of financial indicators is an important factor affecting the accuracy of financial distress prediction. Existing multiple kernel learning (MKL) methods can be used to solve the problem of heterogeneous data learning. Firstly, this paper introduces the theoretical framework of financial distress prediction based on subspace MKL. On this basis, three subspace MKL methods are proposed according to the maximization variance criterion, the maximization of class separability criterion and the principle of non-linear subspace mapping. They are maximization variance projection subspace MKL, separability maximization subspace MKL, and nonlinear subspace MKL, respectively. Using the collected data of Listed Companies in China, the proposed methods are compared with the existing representative financial distress prediction methods, and the experimental results are analyzed. The experimental results show that the proposed subspace MKL financial distress prediction framework is effective, and the subspace MKL prediction methods constructed under this framework can effectively improve the accuracy of financial distress prediction.

Key words: prediction of financial distress, kernel methods, support vector machine, multiple kernel learning

中图分类号:

F273

张向荣. 基于子空间多核学习的企业财务困境预测方法[J]. 运筹与管理, 2021, 30(1): 184-191.

ZHANG Xiang-rong. Subspace Multiple Kernel Learning Methods for Prediction of Financial Distress[J]. Operations Research and Management Science, 2021, 30(1): 184-191.

参考文献

[1] Wanke P, Baros C P, Faria J R. Financial distress drivers in Brazilian banks: a dynamic slacks approach[J]. European Journal of Operational Research, 2014, 240(1): 258-268.
[2] Hua Z, Wang Y, Xu X, et al. Predicting corporate financial distress based onIntegration of support vector machine and logistic regression[J]. Expert Systemswith Applications, 2007, 33: 434-440.
[3] Purnanandam. Financial distress and corporate risk management: theory and evidence[J]. Journal of Financial Economics, 2008, 87: 706-739.
[4] Fehle F, Tsyplakov S. Dynamic risk management: theory and evidence[J]. Journal of Financial Economics, 2005, 78: 3-47.
[5] 田宝新,王建琼.基于财务与非财务要素的上市公司财务困境预警实证研究[J].金融评论,2017,5:103-115.
[6] 陈磊.任若恩.时间序列判别分析技术和指数加权移动平均控制图模型在公司财务危机预警中的应用[J].系统管理学报,2009,(4):241-251.
[7] 赵冠华.基于邻域粗糙集属性约简的对偶约束式LS-SVM财务困境预测模型研究[J].运筹与管理.2011,20(3):132-139.
[8] 鲍新中,傅宏宇.基于变精度加权平均粗糙度决策树的财务预警研究[J].运筹与管理,2015,24(3):189-196.
[9] 王鲁,吴冲.基于自组织映射和模糊隶属度的财务危机预警研究[J].运筹与管理,2017,26(12):119-125.
[10] 吴冲,刘佳明,郭志达.基于改进粒子群算法的模糊聚类-概率神经网络模型的企业财务危机预警模型研究[J].运筹与管理,2018,27(2):106-114.
[11] 彭韶兵,邢精平.公司财务危机论[M].清华大学出版社,2005,(9):50-62
[12] Odom M, Sharda R. A neural networks model for bankruptcy prediction[C]. Proceedings of the IEEE International Conference on Neural Network, 1990, 2: 163-168.
[13] Liu X Y, Liu H J. Genetic neural network based financial distress prediction[C]. Advanced Materials Research, 2014, 933: 921-925.
[14] Hsuan-Ming Feng, Hsiang-Chai Chou. Evolutional RBFNs prediction systems generation in the applicationsof financial time series data[J]. Expert Systems with Applications, 2011, 38: 8285-8292.
[15] Mu-Yen Chen. A hybrid ANFIS model for business failure prediction utilizing particle swarm optimization and subtractive clustering[J]. Information Sciences, 2013, 220: 180-195.
[16] Ligang Zhou, Kin Keung Lai, Jerome Yen. Empirical models based on features ranking techniques for corporate financial distress prediction[J]. Computers and Mathematics with Applications, 2012, 64: 2484-2496.
[17] Arindam Chaudhuri, Kajal De. Fuzzy Support Vector Machine for bankruptcy prediction[J]. Applied Soft Computing, 2011, 11: 2472-2486.
[18] Tsung-Jung Hsieh, Hsiao-FenHsiao, Wei-ChangYeh. Mining financial distress trend data using penalty guided support vector machines based on hybrid of particle swarm optimization and artificial bee colony algorithm[J]. Neurocomputing, 2012, 82: 196-206.
[19] Ching-Chiang Yeh, Der-Jang Chi, Ming-Fu Hsu. A hybrid approach of DEA, rough set and support vector machines for business failure prediction[J]. Expert Systems with Applications, 2010, 37: 1535-1541.
[20] Fengyi Lin, Ching-Chiang Yeh, Meng-Yuan Lee. The use of hybrid manifold learning and support vector machines in theprediction of business failure[J]. Knowledge-Based Systems, 2011, 24: 95-101.
[21] Tony VanGestel, BartBaesens, DavidMartens. From linear to non-linear kernel based classifiers for bankruptcy prediction[J]. Neurocomputing, 2010, 73: 2955-2970.
[22] Shian-Chang Huang, Yu-Cheng Tang, Chih-Wei Lee, Ming-Jen Chang. Kernel local Fisher discriminant analysis based manifold-regularized SVM modelfor financial distress predictions[J]. Expert Systems with Applications, 2012, 39: 3855-3861.
[23] Gönen M, Alpaydln E. Multiple Kernel Learning Algorithms[J]. Journal of Machine Learning Research, 2011, 12: 2181-2238.
[24] Gu Y, Wang C, You D, et al. Representative multiple kernel learning for classification in hyperspectral imagery[J]. Geoscience and Remote Sensing, IEEE Transactions on, 2012, 50(7): 2852-2865.
[25] Zhang X, Hu L. An efficient multiple kernel computation method for regression analysis of economic data[J]. Neurocomputing, 2013, 118: 58-64.
[26] Zhang X, Hu L. A nonlinear subspace multiple kernel learning for financial distress prediction of chinese listed companies[J]. Neurocomputing, 2016, 177: 636-642.
[27] Yeh Y R, Lin T C, Chung Y Y, et al. A novel multiple kernel learning framework for heterogeneous feature fusion and variable selection[J]. Multimedia, IEEE Transactions on, 2012, 14(3): 563-574.
[28] Wang Q, Gu Y, Tuia D. Discriminative multiple kernel learning for hyperspectral image classification[J]. IEEE Transaction on Geoscience and Remote Sensing, 2016, 54(7): 3912-3927.