Predicting financial distress of property and real estate companies using optimized support vector machine - particle swarm optimization (SVM-PSO)

Ni Wayan Dewinta Ayuni; Ni Nengah  Lasmini; Kadek Cahya Dewi

doi:10.31763/businta.v8i1.667

Authors

Ni Wayan Dewinta Ayuni Politeknik Negeri Bali
Ni Nengah Lasmini Politeknik Negeri Bali
Kadek Cahya Dewi Politeknik Negeri Bali

DOI:

https://doi.org/10.31763/businta.v8i1.667

Keywords:

Financial Distress, Support Vector Machine, Particle Swarm Optimization, Property and Real Estate Companies

Abstract

Financial distress is a critical phenomenon in a company that has significant implications for the business itself, employees, investors, and creditors, and can also impact the economy of a country. Predicting the financial distress of a company, including property and real estate companies, becomes one of the crucial things to be studied. The Support Vector Machine (SVM) is said to be the most effective model for prediction and classification among other machine learning methods. However, it is difficult to determine the parameters of the SVM model. Thus, the SVM model's parameters must be improved for higher accuracy results. This research aims to increase the accuracy of the SVM model in predicting the financial distress of property and real estate companies. The optimization method used is Particle Swarm Optimization (PSO). PSO is one of the most well-known techniques for enhancing SVM parameters. The PSO approach takes its cues from how a group of insects or birds interacts to maintain life. Initialized in a D-dimensional search space, the PSO algorithm uses a population of random particles that are considered as points. Each particle modifies its direction using the best experience it discovers (pbest) and the best experience discovered by all other members (gbest) to arrive at the ideal outcome. As a result, throughout the search process, particles will move through multidimensional space to more advantageous locations. The result of this research showed that the SVM model has the highest accuracy at 80.47% while when the PSO method was implemented in the SVM model, the accuracy increased into 83.16%. It can be concluded that the PSO method successfully optimized the parameters and increased the accuracy of SVM model in predicting the financial distress of property and real estate companies listed in Indonesian Stock Exchange.

References

G. Giannopoulos and S. Sigbjørnsen, “Prediction of Bankruptcy Using Financial Ratios in the Greek Market,” Theor. Econ. Lett., vol. 09, no. 04, pp. 1114–1128, Mar. 2019, doi: 10.4236/tel.2019.94072.

H. Cahyadi, A. Andy, H. Wijaya, S. Salim, A. I. P., and J. Gabriella, “Factors Affecting Financial Difficulty,” in Proceedings of the tenth International Conference on Entrepreneurship and Business Management 2021 (ICEBM 2021), May 2022, vol. 653, pp. 170–177, doi: 10.2991/aebmr.k.220501.027.

Y. Li and Y. Wang, “Machine Learning Methods of Bankruptcy Prediction Using Accounting Ratios,” Open J. Bus. Manag., vol. 06, no. 01, pp. 1–20, Nov. 2018, doi: 10.4236/ojbm.2018.61001.

I. Nurfahrudin and R. A. Rahadi, “Application of Bankruptcy Prediction Models for Real Estate Companies Listed on The Indonesia Stock Exchange (IDX),” Syntax Lit. ; J. Ilm. Indones., vol. 6, no. 10, p. 5088, Oct. 2021, doi: 10.36418/syntax-literate.v6i10.4264.

“EVERGRANDE: International bond investors facing 22.5 billion USD write-offs,” DMSA Deutsche Markt Screening Agentur GmbH, 2021. [Online]. Available at: https://www.newswire.ca/news-releases/evergrande-international-bond-investors-facing-22-5-billion-usd-write-offs-837954337.html.

Z. Wang, K. Ye, and D. Zhu, “Financial Crisis Analysis of Evergrande Group from the Perspective of Game Theory,” in Proceedings of the 2022 2nd International Conference on Enterprise Management and Economic Development (ICEMED 2022), 2022, pp. 262–274, doi: 10.2991/aebmr.k.220603.045.

E. I. Altman, “Financial Ratios, Discriminant Analysis And The Prediction Of Corporate Bankruptcy,” J. Finance, vol. 23, no. 4, pp. 589–609, Sep. 1968, doi: 10.1111/j.1540-6261.1968.tb00843.x.

J. A. Ohlson, “Financial Ratios and the Probabilistic Prediction of Bankruptcy,” J. Account. Res., vol. 18, no. 1, p. 109, 1980, doi: 10.2307/2490395.

R. C. West, “A factor-analytic approach to bank condition,” J. Bank. Financ., vol. 9, no. 2, pp. 253–266, Jun. 1985, doi: 10.1016/0378-4266(85)90021-4.

C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, Sep. 1995, doi: 10.1007/BF00994018.

T. A. Cardona and E. A. Cudney, “Predicting Student Retention Using Support Vector Machines,” Procedia Manuf., vol. 39, pp. 1827–1833, Jan. 2019, doi: 10.1016/j.promfg.2020.01.256.

Y. Niu and S. Ye, “Data Prediction Based on Support Vector Machine (SVM)—Taking Soil Quality Improvement Test Soil Organic Matter as an Example,” IOP Conf. Ser. Earth Environ. Sci., vol. 295, no. 2, p. 012021, Jul. 2019, doi: 10.1088/1755-1315/295/2/012021.

F. Janan and S. K. Ghosh, “Prediction of Student’s Performance Using Support Vector Machine Classifier,” Proc. Int. Conf. Ind. Eng. Oper. Manag., vol. 11, no. 1, pp. 7078–7088, Mar. 2021, doi: 10.46254/AN11.20211237.

B. Yassin, C. Mohamed, and A.-A. Yassine, “A Nonlinear Support Vector Machine Analysis Using Kernel Functions for Nature and Medicine,” E3S Web Conf., vol. 319, p. 01103, Nov. 2021, doi: 10.1051/e3sconf/202131901103.

J. Horak, J. Vrbka, and P. Suler, “Support Vector Machine Methods and Artificial Neural Networks Used for the Development of Bankruptcy Prediction Models and their Comparison,” J. Risk Financ. Manag., vol. 13, no. 3, p. 60, Mar. 2020, doi: 10.3390/jrfm13030060.

S. Kim, B. M. Mun, and S. J. Bae, “Data depth based support vector machines for predicting corporate bankruptcy,” Appl. Intell., vol. 48, no. 3, pp. 791–804, Mar. 2018, doi: 10.1007/s10489-017-1011-3.

M. Vochozka and V. Machová, “Determination of Value Drivers for Transport Companies in the Czech Republic,” Naše more, vol. 65, no. 4, pp. 197–201, Nov. 2018, doi: 10.17818/NM/2018/4SI.6.

W. Xu, H. Fu, and Y. Pan, “A Novel Soft Ensemble Model for Financial Distress Prediction with Different Sample Sizes,” Math. Probl. Eng., vol. 2019, pp. 1–12, Apr. 2019, doi: 10.1155/2019/3085247.

J. Du, Y. Liu, Y. Yu, and W. Yan, “A Prediction of Precipitation Data Based on Support Vector Machine and Particle Swarm Optimization (PSO-SVM) Algorithms,” Algorithms, vol. 10, no. 2, p. 57, May 2017, doi: 10.3390/a10020057.

S. Saikin, S. Fadli, and M. Ashari, “Optimization of Support Vector Machine Method Using Feature Selection to Improve Classification Results,” JISA(Jurnal Inform. dan Sains), vol. 4, no. 1, pp. 22–27, Jun. 2021, doi: 10.31326/JISA.V4I1.881.

L. Demidova, E. Nikulchev, and Y. Sokolova, “The SVM Classifier Based on the Modified Particle Swarm Optimization,” Int. J. Adv. Comput. Sci. Appl., vol. 7, no. 2, 2016, doi: 10.14569/IJACSA.2016.070203.

Q. Huang, “Application of SVM Algorithm for Particle Swarm Optimization in Apple Image Segmentation,” in Proceedings of the 2015 International Conference on Computational Science and Engineering, Jul. 2015, vol. 17, pp. 12–16, doi: 10.2991/iccse-15.2015.3.

T. Xue and Z. Jieru, “Application of Support Vector Machine Based on Particle Swarm Optimization in Classification and Prediction of Heart Disease,” in 2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP), Apr. 2022, pp. 857–860, doi: 10.1109/ICSP54964.2022.9778616.

Y. R. Nugraha, A. P. Wibawa, and I. A. E. Zaeni, “Particle Swarm Optimization – Support Vector Machine (PSO-SVM) Algorithm for Journal Rank Classification,” in 2019 2nd International Conference of Computer and Informatics Engineering (IC2IE), Sep. 2019, pp. 69–73, doi: 10.1109/IC2IE47452.2019.8940822.

W. Huang et al., “Railway dangerous goods transportation system risk identification: Comparisons among SVM, PSO-SVM, GA-SVM and GS-SVM,” Appl. Soft Comput., vol. 109, p. 107541, Sep. 2021, doi: 10.1016/j.asoc.2021.107541.

T. Cuong-Le, T. Nghia-Nguyen, S. Khatir, P. Trong-Nguyen, S. Mirjalili, and K. D. Nguyen, “An efficient approach for damage identification based on improved machine learning using PSO-SVM,” Eng. Comput., vol. 38, no. 4, pp. 3069–3084, Aug. 2022, doi: 10.1007/s00366-021-01299-6.

R. Eberhart and J. Kennedy, “A new optimizer using particle swarm theory,” in MHS’95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science, 1995, pp. 39–43, doi: 10.1109/MHS.1995.494215.

X. Chong, “Hybrid PSO-SVM for Financial Early-Warning Model of Small and Medium-Sized Enterprises,” in Proceedings of the 6th International Conference on Financial Innovation and Economic Development (ICFIED 2021), Mar. 2021, vol. 166, pp. 107–114, doi: 10.2991/aebmr.k.210319.020.

S. Zeng, Y. Li, W. Yang, and Y. Li, “A Financial Distress Prediction Model Based on Sparse Algorithm and Support Vector Machine,” Math. Probl. Eng., vol. 2020, pp. 1–11, Nov. 2020, doi: 10.1155/2020/5625271.

W. Li, “Design of Financial Crisis Early Warning Model Based on PSO-SVM Algorithm,” Math. Probl. Eng., vol. 2022, pp. 1–8, Sep. 2022, doi: 10.1155/2022/3241802.

N. W. D. Ayuni, N. N. Lasmini, and A. A. Putrawan, “Support Vector Machine (SVM) as Financial Distress Model Prediction in Property and Real Estate Companies,” in Proceedings of the International Conference on Applied Science and Technology on Social Science 2022 (iCAST-SS 2022), Paris: Atlantis Press SARL, 2022, pp. 397–402, doi: 10.2991/978-2-494069-83-1_72.

R. B. Whitaker, “The early stages of financial distress,” J. Econ. Financ., vol. 23, no. 2, pp. 123–132, Jun. 1999, doi: 10.1007/BF02745946.

N. Nurhayati, A. Mufidah, and A. N. Kholidah, “The Determinants of Financial Distress of Basic Industry and Chemical Companies Listed in Indonesia Stock Exchange,” Rev. Manag. Entrep., vol. 1, no. 2, pp. 19–26, Jul. 2018, doi: 10.37715/rme.v1i2.605.

O. Chamorro-Atalaya et al., “K-Fold Cross-Validation through Identification of the Opinion Classification Algorithm for the Satisfaction of University Students,” Int. J. Online Biomed. Eng., vol. 19, no. 11, pp. 122–130, Aug. 2023, doi: 10.3991/ijoe.v19i11.39887.

A. P. Piotrowski, J. J. Napiorkowski, and A. E. Piotrowska, “Population size in Particle Swarm Optimization,” Swarm Evol. Comput., vol. 58, p. 100718, Nov. 2020, doi: 10.1016/j.swevo.2020.100718.