Gang Qiao1 and Lihui Du This email address is being protected from spambots. You need JavaScript enabled to view it.2

1Department of Economics and Management, Anhui Vocational College of Electronics and Information Technology, Bengbu 233060, P.R. China
2School of Economics and Trade, Hunan University, Changsha, P.R. China


Received: March 28, 2017
Accepted: October 16, 2018
Publication Date: March 1, 2019

Download Citation: ||  


In order to ensure the healthy and orderly development of enterprises, it is of great importance to effectively predict enterprise financial risk in advance, and then provide early warning information to enterprise’s managers.Firstly, we design an index system for enterprise financial risk early warning, which contains five aspects: 1) Profitability, 2) Debt paying ability, 3) Operation ability, 4) Growth ability, and 5) Non-financial indicators. Secondly, we propose a novel hybrid PSO-SVM model based enterprise financial risk early warning algorithm by converting the proposed problem to a classification problem. As the performance of SVM classifier highly relies on parameter selection, we introduce the PSO algorithm to estimate optimal parameters for SVM. Thirdly, we choose several ST companies of the listed companies in China as financial crisis enterprises, and compare their running states with Non-ST companies. Main contributions of this paper lie in that we propose a hybrid PSO-SVM model based enterprise financial risk early warning algorithm by solving a classification problem. Experimental results show that the proposed algorithm is able to effectively provide early warning information for enterprise financial risk, and performs better than BP neural network and SVM without parameter optimization.

Keywords: Enterprise Financial Risk, Risk Early Warning, Particle Swarm Optimization, Support Vector Machine


  1. [1] Liu, D. S., G. L. Zhou, K. N. Zhu, and C. H. Xu (2013) The regional financial risk early-warning model integrating the regression of lagging factors, Applied Mathematics & Information Sciences 7(3), 10351041 doi: 10.12785/amis/070322
  2. [2] Koyuncugil, A. S., and N. Ozgulbas (2012) financial early warning system model and data mining application for risk detection, Expert Systems with Applications 39(6), 62386253. doi: 10.1016/j.eswa.2011.12. 021
  3. [3] Su, J. X., and E. Furman (2017) Aform of multivariate pareto distribution with applications to financial risk measurement, Astin Bulletin 47(1), 331357. doi: 10. 1017/asb.2016.22
  4. [4] Hu, Y. J., and J. J. Pang (2008) Financial crisis earlywawning based on spport vector machine, 2008 International Joint Conference on Neural Networks (IJCNN 2008), 24352440.
  5. [5] Zhang, C., W. D. He, and R. Hao (2016) Comprehensive estimation of the financial risk of iron and steel enterprise-based on carbon emission reduction, Journal of Scientific & Industrial Research 75(3), 143149.
  6. [6] Xu, Q. F., X. Liu, C. X. Jiang, and K. M. Yu (2016) Nonparametric conditional autoregressive expectile model via neural network with applications to estimating financial risk, Applied Stochastic Models in Business and Industry 32(6), 882908. doi: 10.1002/asmb. 2212
  7. [7] Vijverberg, C. P. C., W. P. M. Vijverberg, and S. Taspinar (2016) Linking Tukey’s legacy to financial risk measurement, Computational Statistics & Data Analysis 100, 595615. doi: 10.1016/j.csda.2015.08. 018
  8. [8] Taylor, J. W., and K. M. Yu (2016) Using auto-regressive logit models to forecast the exceedance probability for financial risk management, Journal of the Royal Statistical Society Series a-Statistics in Society 179(4), 10691092. doi: 10.1111/rssa.12176
  9. [9] Dai, W. (2011) Establishing financial crisis early warning models for listed companies, 2011 International Conference of Information Technology, ComputerEngineering and Management Sciences, 195198. doi: 10.1109/ICM.2011.123
  10. [10] Santibanez-Aguilar, J. E., G. Guillen-Gosalbez, R. Morales-Rodriguez,L.Jimenez-Esteller,A.Castro-Montoya, and J. M. Ponce-Ortega (2016) Financial risk assessment and optimal planning of biofuels supply chains under uncertainty, BioEnergy Research 9(4), 1053 1069. doi: 10.1007/s12155-016-9743-1
  11. [11] Retchin, S. M. (2016) Responding to the marketplace: workforce balance and financial risk at academic health centers, Academic Medicine 91(7), 908909. doi: 10.1097/ACM.0000000000001241
  12. [12] Pan, I., A. Korre, and S. Durucan (2016) A systems based approach for financial risk modelling and optimisation of the mineral processing and metal production industry, Computers & Chemical Engineering 89, 84105. doi: 10.1016/j.compchemeng.2016.03.010
  13. [13] Bensusan, H., N. El Karoui, S. Loisel, and Y. Salhi (2016) Partial splitting of longevity and financial risks: the longevity nominal choosing swaptions, Insurance Mathematics & Economics 68, 6172. doi: 10.1016/ j.insmatheco.2016.02.001
  14. [14] Wang, Y. (2012) Z-score model on financial crisis early-warning of listed real estate companies in China: a financial engineering perspective, Systems Engineering Procedia 3, 153–157. doi: 10.1016/j.sepro.2011.11. 021
  15. [15] Anzilli, L., and G. Facchinetti (2016) Afuzzy quantity mean-variance view and its application to a client financial risk tolerance model, International Journal of Intelligent Systems 31(10), 963988. doi: 10.1002/ int.21812
  16. [16] Li, S. J., and S. Wang (2014) Afinancial early warning logit model and its efficiency verification approach, Knowledge-Based Systems 70, 78–87. doi: 10.1016/j. knosys.2014.03.017
  17. [17] Wu, S. H., (2014) A novel company financial risk warning method based on BP neural networks,20147th International Conference on Intelligent Computation Technology and Automation, pp. 3235. doi: 10.1109/ ICICTA.2014.15
  18. [18] Raj, S., K. C. Ray, and O. Shankar (2016) Cardiac arrhythmia beat classification using DOSTand PSO tuned SVM,” Computer Methods and Programs in Biomedicine 136, 163177. doi: 10.1016/j.cmpb.2016.08. 016
  19. [19] Zhou, C., K. L. Yin, Y. Cao, and B. Ahmed (2016) Application of time series analysis and PSO-SVM model in predicting the Bazimen landslide in the three Gorges reservoir, China,” Engineering Geology 204, 108 120. doi: 10.1016/j.enggeo.2016.02.009
  20. [20] Zhang, C. L., Y. G. He, L. F. Yuan, W. He, S. Xiang, and Z. G. Li (2016) A novel approach for diagnosis of analog circuit fault by using GMKL-SVM and PSO, Journal of Electronic Testing-Theory and Applications 32(5), 531540. doi: 10.1007/s10836-016-5616-y
  21. [21] Xu, F., Y. J. Fang, and Z. M. Kong (2016) Afault diagnosis method based on MBSE and PSO-SVM for roller bearings, Journal of Vibration Engineering & Technologies 4(4), 383394.
  22. [22] Sun, F. Y., Y. B. Tian, and Z. L. Ren (2016) Modeling the resonant frequency of compact microstrip antenna by the PSO-based SVM with the hybrid kernel function,” International Journal of Numerical ModellingElectronic Networks Devices and Fields 29(6), 1129 1139. doi: 10.1002/jnm.2171
  23. [23] Zhan, L. W., and C. W. Li (2017) A hybrid PSOSVM-based method for predicting the friction coefficient between aircraft tire and coating, Measurement Science and Technology 28(2), 5863. doi: 10.1088/ 1361-6501/aa506d
  24. [24] Nieto, P. J. G., E. Garcia-Gonzalo, J. R. A. Fernandez, and C. D. Muniz (2016) A hybrid PSO optimized SVM-based model for predicting a successful growth cycle of the spirulina platensis from raceway experiments data, Journal of Computational and Applied Mathematics 291, 293303. doi: 10.1016/ 01.009
  25. [25] Nieto, P. J. G., E. Garcia-Gonzalo, G. Arbat, M. DuranRos, F. R. de Cartagena, and J. Puig-Bargues (2016) A new predictive model for the filtered volume and outlet parameters in micro-irrigation sand filters fed with effluents using the hybrid PSO-SVM-based approach, Computers and Electronics in Agriculture 125, 74 80. doi: 10.1016/j.compag.2016.04.031
  26. [26] Du, Y. J., X. B. Lu, L. Chen, and W. L. Zeng (2016) An interval type-2 T-S fuzzy classification system based on PSO and SVM for gender recognition, Multimedia Tools and Applications 75(2), 9871007. doi: 10.1007/ s11042-014-2338-y
  27. [27] Chang, B. M., H. H. Tsai, and C. Y. Yen (2016) SVMPSO based rotation-invariant image texture classification in SVD and DWT domains, Engineering Applications of Artificial Intelligence 52, 96107. doi: 10. 1016/j.engappai.2016.02.005
  28. [28] Aburomman, A. A., and M. B. I. Reaz (2016) A novel SVM-kNN-PSO ensemble method for intrusion detection system, Applied Soft Computing 38, 360372. doi: 10.1016/j.asoc.2015.10.011
  29. [29] Nieto, P. J. G., E. Garcia-Gonzalo, F. S. Lasheras, and F. J. D. Juez (2015) “Hybrid PSO-SVM-based method for forecasting of the remaining useful life for aircraft engines and evaluation of its reliability, Reliability Engineering & System Safety 138, 219231. doi: 10. 1016/j.ress.2015.02.001
  30. [30] Nieto, P. J. G., J. R. A. Fernandez, V. M. G. Suarez, C. D. Muniz, E. Garcia-Gonzalo, and R. M. Bayon (2015) Ahybrid PSO optimized SVM-based method for predicting of the cyanotoxin content from experimental cyanobacteria concentrations in the trasona reservoir: a case study in northern Spain, Applied Mathematics and Computation 260, 170187. doi: 10.1016/j.amc. 2015.03.075
  31. [31] Jian, Q. P., and Z. J. Ai (2015) Internal and external defect identification of pipelines using the PSO-SVM method,” Insight 57(2), 8591. doi: 10.1784/insi.2014. 57.2.85
  32. [32] Xue, Z. H., P. J. Du, and H. J. Su (2014) Harmonic analysis for hyperspectral image classification integrated with PSO optimized SVM, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 7(6), 21312146. doi: 10.1109/JSTARS. 2014.2307091
  33. [33] Sudheer, C., R. Maheswaran, B. Panigrahi, and S. Mathur (2014) A hybrid SVM-PSO model for forecasting monthly streamflow, Neural Computing & Applications 24(6), 13811389. doi: 10.1007/s00521013-1341-y
  34. [34] Selakov, A., D. Cvijetinovic, L. Milovic, S. Mellon, and D. Bekut (2014) Hybrid PSO-SVM method for shortterm load forecasting during periods with significant temperature variations in city of Burbank, Applied Soft Computing 16, 8088. doi: 10.1016/j.asoc.2013. 12.001
  35. [35] Nieto, P. J. G., E. Garcia-Gonzalo, J. R. A. Fernandez, and C. D. Muniz (2014) Hybrid PSO-SVM-based method for long-term forecasting of turbidity in the Nalon River Basin: a case study in northern Spain, Ecological Engineering 73, 192200. doi: 10.1016/j. ecoleng.2014.09.042
  36. [36] A hybrid GA-GSA algorithm for optimizing the performance of an industrial systemby utilizing uncertain data, in Handbook of Research on Artificial Intelligence Techniques and Algorithms, IGI Global, USA, Ch. 20, pp. 625659 (2014).
  37. [37] Garg, H. (2016) A hybrid PSO-GA algorithm for constrained optimization problems, Applied Mathematics & Computation 274(11), 292305. doi: 10.1016/j.amc. 2015.11.001
  38. [38] Garg, H. (2014) Solving structural engineering design optimization problems using an artificial bee colony algorithm, Journal of Industrial & Management Optimization 10(3), 777794.
  39. [39] Garg, H. (2016) Performance analysis of an industrial system using soft computing based hybridized technique, Journal of the Brazilian Society of Mechanical Sciences & Engineering 39(4), 111.
  40. [40] Narang, N., R. S. Patwal, and H. Garg (2018) A novel TVAC-PSO based mutation strategies algorithm for generation scheduling of pumped storage hydrothermal system incorporating solar units, Energy, 822 837. doi: 10.1016/
  41. [41] Garg, H. (2015) An efficient biogeography based optimization algorithm for solving reliability optimization problems, Swarm & Evolutionary Computation 24, 1 10. doi: 10.1016/j.swevo.2015.05.001
  42. [42] Shah, H., O. N. Tairan, and H. Garg (2018) A quick Gbest guided artificial bee colony algorithm for stock market prices prediction, Symmetry 10(7), 292. doi: 10.3390/sym10070292