Financial Distress Prediction Based on Support Vector Machine with a Modified Kernel Function

Abstract For the financial distress prediction model based on support vector machine, there are no theories concerning how to choose a proper kernel function in a data-dependent way. This paper proposes a method of modified kernel function that can availably enhance classification accuracy. We apply an information-geometric method to modifying a kernel that is based on the structure of the Riemannian geometry induced in the input space by the kernel. A conformal transformation of a kernel from input space to higher-dimensional feature space enlarges volume elements locally near support vectors that are situated around the classification boundary and reduce the number of support vectors. This paper takes the Gaussian radial basis function as the internal kernel. Additionally, this paper combines the above method with the theories of standard regularization and non-dimensionalization to construct the new model. In the empirical analysis section, the paper adopts the financial data of Chinese listed companies. It uses five groups of experiments with different parameters to compare the classification accuracy. We can make the conclusion that the model of modified kernel function can effectively reduce the number of support vectors, and improve the classification accuracy.

[1]  Yan Xi Li,et al.  Stock Price Index Prediction Based on Improved SVM , 2011 .

[2]  Abhishek Vaish,et al.  Feature extraction using emprical mode decomposition for biometric system , 2014, 2014 International Conference on Signal Propagation and Computer Technology (ICSPCT 2014).

[3]  Hui Li,et al.  Statistics-based wrapper for feature selection: An implementation on financial distress identification with support vector machine , 2014, Appl. Soft Comput..

[4]  Gang Hu,et al.  Study on Improving Z-score Model Based on the Logistic Model: Evidence from Listed Companies in China , 2009, 2009 International Conference on Information Management, Innovation Management and Industrial Engineering.

[5]  E. Altman,et al.  ZETATM analysis A new model to identify bankruptcy risk of corporations , 1977 .

[6]  Li Xiang,et al.  Research on financial distress prediction of China real estate public companies based on Z-Score model , 2011, 2011 International Conference on Management Science & Engineering 18th Annual Conference Proceedings.

[7]  Yi Hsien Wang,et al.  Financial Information Fraud Risk Warning for Manufacturing Industry - Using Logistic Regression and Neural Network , 2011 .

[8]  Vladimir Vapnik,et al.  Universal learning technology : Support vector machines , 2005 .

[9]  Chen Yanjun,et al.  The bankruptcy prediction study under the financial crisis: The case of Chinese export-oriented enterprises , 2010, 2010 2nd IEEE International Conference on Information and Financial Engineering.

[10]  Han Meng,et al.  Parameter selection in SVM with RBF kernel function , 2012, World Automation Congress 2012.

[11]  Xiang Yu,et al.  Financial distress prediction based on SVM and MDA methods: the case of Chinese listed companies , 2011 .

[12]  Gora Chand Nandi,et al.  Less computationally intensive fuzzy logic (type-1)-based controller for humanoid push recovery , 2015, Robotics Auton. Syst..

[13]  Tzong-Huei Lin,et al.  A cross model study of corporate financial distress prediction in Taiwan: Multiple discriminant analysis, logit, probit and neural networks models , 2009, Neurocomputing.

[14]  Kateřina Pitrová,et al.  Possibilities of the Altman zeta model application to czech firms , 2011 .

[15]  Ping-Feng Pai,et al.  Incorporating support vector machines with multiple criteria decision making for financial crisis analysis , 2012, Quality & Quantity.

[16]  Abhishek Vaish,et al.  Brainwave's energy feature extraction using wavelet transform , 2014, 2014 IEEE Students' Conference on Electrical, Electronics and Computer Science.

[17]  Mingliang Wang,et al.  Prediction of Banking Systemic Risk Based on Support Vector Machine , 2013 .

[18]  Soo Y. Kim,et al.  Prediction of hotel bankruptcy using support vector machine, artificial neural network, logistic regression, and multivariate discriminant analysis , 2011 .

[19]  Min-Yuan Cheng,et al.  Optimizing parameters of support vector machine using fast messy genetic algorithm for dispute classification , 2014, Expert Syst. Appl..

[20]  W. Beaver.  Financial Ratios As Predictors Of Failure , 1966 .

[21]  Zhongsheng Hua,et al.  Predicting corporate financial distress based on integration of support vector machine and logistic regression , 2007, Expert Syst. Appl..

[22]  Zied Elouedi,et al.  Classification systems based on rough sets under the belief function framework , 2011, Int. J. Approx. Reason..

[23]  Gora Chand Nandi,et al.  Biometric gait identification based on a multilayer perceptron , 2015, Robotics Auton. Syst..

[24]  Jordán Pascual Espada,et al.  Machine learning approach for text and document mining , 2014, ArXiv.

[25]  Xin Yao,et al.  A New Adaptive Merging and Growing Algorithm for Designing Artificial Neural Networks , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).