Assessment of Support Vector Machine performance for default prediction and credit rating
-
Received December 25, 2021;Accepted March 18, 2022;Published April 2, 2022
-
Author(s)Link to ORCID Index: https://orcid.org/0000-0003-2999-6473Link to ORCID Index: https://orcid.org/0000-0003-2502-2356
-
DOIhttp://dx.doi.org/10.21511/bbs.17(1).2022.14
-
Article InfoVolume 17 2022, Issue #1, pp. 161-175
- TO CITE АНОТАЦІЯ
-
Cited by5 articlesJournal title: Corporate Ownership and ControlArticle title: Artificial intelligence applications in auditing processes in the banking sectorDOI: 10.22495/cocv21i3art3Volume: 21 / Issue: 3 / First page: 35 / Year: 2024Contributors: Rana Albahsh, Mohammad F. Al-AnaswahJournal title: Economics & SociologyArticle title: Predicting bankruptcy using artificial intelligence: The case of the engineering industryDOI: 10.14254/2071-789X.2023/16-4/8Volume: 16 / Issue: 4 / First page: 178 / Year: 2023Contributors: Stanislav Letkovsky, Sylvia Jencova, Petra Vasanicova, Stefan Gavura, Radovan BacikJournal title:Article title:DOI:Volume: / Issue: / First page: / Year:Contributors:Journal title: Global Knowledge, Memory and CommunicationArticle title: Mapping the fintech revolution: how technology is transforming credit risk managementDOI: 10.1108/GKMC-12-2023-0492Volume: / Issue: / First page: / Year: 2024Contributors: Haitham Nobanee, Nejla Ould Daoud Ellili, Dipanwita Chakraborty, Hiba Zaki ShantiJournal title: MathematicsArticle title: Ensemble-Based Machine Learning Algorithm for Loan Default Risk PredictionDOI: 10.3390/math12213423Volume: 12 / Issue: 21 / First page: 3423 / Year: 2024Contributors: Abisola Akinjole, Olamilekan Shobayo, Jumoke Popoola, Obinna Okoyeigbo, Bayode Ogunleye
- 1094 Views
-
294 Downloads
This work is licensed under a
Creative Commons Attribution 4.0 International License
Predicting the creditworthiness of bank customers is a major concern for banking institutions, as modeling the probability of default is a key focus of the Basel regulations. Practitioners propose different default modeling techniques such as linear discriminant analysis, logistic regression, Bayesian approach, and artificial intelligence techniques. The performance of the default prediction is evaluated by the Receiver Operating Characteristic (ROC) curve using three types of kernels, namely, the polynomial kernel, the linear kernel and the Gaussian kernel. To justify the performance of the model, the study compares the prediction of default by the support vector with the logistic regression using data from a portfolio of particular bank customers. The results of this study showed that the model based on the Support Vector Machine approach with the Radial Basis Function kernel, performs better in prediction, compared to the logistic regression model, with a value of the ROC curve equal to 98%, against 71.7% for the logistic regression model. Also, this paper presents the conception of a support vector machine-based rating tool designed to classify bank customers and determine their probability of default. This probability has been computed empirically and represents the proportion of defaulting customers in each class.
- Keywords
-
JEL Classification (Paper profile tab)C13, G21, G32
-
References63
-
Tables16
-
Figures4
-
- Figure B1. Performance of the LR model (ROC)
- Figure B2. ROC curve of the linear kernel
- Figure B3. ROC curve of the Poly kernel
- Figure B4. ROC curve of the Poly kernel
-
- Table 1. Design of the scoring tool
- Table 2. Portfolio allocation
- Table 3. Confusion matrix
- Table 4. Coefficients (w*i)
- Table 5. Parameters of the selected kernels
- Table 6. The three error ratios of the three kernels
- Table 7. Portfolio allocation
- Table 8. Conception of the rating tool
- Table A1. Univariate analysis table
- Table A2. The correlation table of the independent variables
- Table A3. Wald test table
- Table A4. Wald test table
- Table A5. Test of the SVM-RBF parameters by the Gird-Search function
- Table A6. Test of the SVM-Poly parameters by the function Gird-Search
- Table A7. The confusion matrix of the three kernels
- Table A8. Number of support vectors (RBF-SVM)
-
- Aboobyda, J. H., & Tarig, A. M. (2016). Developing Prediction Model of Loan Risk in Banks Using Data Mining. Machine Learning and Applications: An International Journal (MLAIJ), 3(1), 1-9.
- Altman, E. I., Marco, G., & Varetto, F. (1994). Corporate distress diagnosis: Comparisons using linear discriminant analysis and neural networks (the Italian experience). Journal of Banking & Finance, 18(3), 505-529.
- Altman, E., Haldeman, R., & Narayaman, P. (1977). ZETA analysis: a new model to identify bankruptcy risk of corporations. Journal of Banking and Finance, 1, 29-51.
- Amzile, K., & Amzile, R. (2021). Using SVM for Smart Direct Marketing (SDM): A case of predicting bank customers interested in the Term Deposits. International Journal of Accounting, Finance, Auditing, Management and Economics, 2(5), 525-537.
- Baesens, B., Van Gestel, T., Viaene, S., Stepanova, M., Suykens, J., & Vanthienen, J. (2003). Benchmarking state-of-the-art classification algorithms for credit scoring. Journal of the Operational Research Society, 54(6), 627-635.
- Barron, A. R. (1993). Universal approximation bounds for superpositions of a sigmoidal function. IEEE Transactions on Information Theory, 39(3), 930-945.
- Bassey, P. (2019). Logistic Regression Vs Support Vector Machines (SVM).
- Bellotti, T., & Crook, J. (2009). Support vector machines for credit scoring and discovery of significant features. Expert Systems with Applications, 36(2), 3302-3308.
- Benbachir, S., & Habachi, M. (2018). Assessing the Impact of Modelling on the Expected Credit Loss (ECL) of a Portfolio of Small and Medium-sized Enterprises. Universal Journal of Management, 6(10), 409-431.
- Bewick, V., Cheek, L., & Ball, J. (2004). Statistics review 13: Receiver operating characteristic curves. Critical Care, 8, 508.
- Chen, T.-H. (2020). Do you know your customer? Bank risk assessment based on machine learning. Applied Soft Computing, 86, 105779.
- Çığşar, B., & Ünal, D. (2019). Comparison of Data Mining Classification Algorithms Determining the Default Risk. Scientific Programming, 2019, 1-8.
- Coakley, J. R., & Brown, C. E. (2000). Artificial neural networks in accounting and finance: modeling issues. Intelligent Systems in Accounting, Finance and Management, 9(2), 119-144.
- Coats, P. K., & Fant, L. F. (1993). Recognizing Financial Distress Patterns Using a Neural Network Tool. Financial Management, 22(3), Fall.
- Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273-297.
- Cybenko, G. (1989). Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals and Systems, 2, 303-314.
- Danenas, P., & Garsva, G. (2015). Selection of Support Vector Machines based classifiers for credit risk domain. Expert Systems with Applications, 42(6), 3194-3204.
- Dimitras, A. I., Zanakis, C., & Zopounidis, S. H. (1996). A survey of business failures with an emphasis on prediction methods and industrial applications. European Journal of Operational Research, 90(3), 487-513.
- El Sanharawi, M., & Naudet, F. (2013). Understanding logistic regression. Journal Français d’Ophtalmologie, 36(8), 710-715.
- Feng, J., Wang, Y., Peng, J., Sun, M., Zeng, J., & Jiang, H. (2019). Comparison between logistic regression and machine learning algorithms on survival prediction of traumatic brain injuries. Journal of Critical Care, 54, 110-116.
- Francoeur, D. (2010). Support vector machines: an introduction.
- Frezza-Buet, H. (2013). Vector Machines Supports Tutorial.
- Goh, R. Y., & Lee, L. S. (2019). Credit Scoring: A Review on Support Vector Machines and Metaheuristic Approaches. Advances in Operations Research, 2019, 1-30.
- Guyon, I., Weston, J., Barnhill, S., & Vapnik, V. (2002). Gene Selection for Cancer Classification using Support Vector Machines. Machine Learning, 46, 389-422.
- Habachi, M., & Benbachir, S. (2019). Combination of linear discriminant analysis and expert opinion for the construction of credit rating models: The case of SMEs. Cogent Business & Management, 6(1), 1685926.
- Habachi, M., & El Haddad, S. (2021). Impact of Covid-19 on SME portfolios in Morocco: Evaluation of banking risk costs and the effectiveness of state support measures. Investment Management and Financial Innovations, 18(3), 260-276.
- Hassan, A., & Jayousi, R. (2020). Financial Services Credit Scoring System Using Data Mining. 2020 IEEE 14th International Conference on Application of Information and Communication Technologies (AICT) (pp. 1-7).
- Hosmer, D. W., Lemeshow, S., & Sturdivant, R. X. (2013). Applied logistic regression (3rd ed.).
- Huang, C.-L., Chen, M.-C., & Wang, C.-J. (2007). Credit scoring with a data mining approach based on support vector machines. Expert Systems with Applications, 33(4), 847-856.
- Jones, S., & Hensher, D. A. (2007). Corporate failure: A multinomial nested logit analysis for unordered outcomes. The British Accounting Review, 39(1), 89-107.
- Khashman, A. (2010). Neural networks for credit risk evaluation: Investigation of different neural models and learning schemes. Expert Systems with Applications, 37(9), 6233-6239.
- Lai, K. K., Yu, L., Wang, S., & Zhou, L. (2006). Credit Risk Analysis Using a Reliability-Based Neural Network Ensemble Model. In S. Kollias, A. Stafylopatis, W. Duch, & E. Oja (Eds.), Artificial Neural Networks - ICANN 2006 (pp. 682-690). Springer Berlin Heidelberg.
- Lee, T., Chiu, C., Lu, C., & Chen, I. (2002). Credit scoring using the hybrid neural discriminant technique. Expert Systems with Applications, 23(3), 245-254.
- Lejeune, M. (2010). Statistics – Theory and its applications. Sumy: Springer.
- Loan Thi Vu, Lien Thi Vu, Nga Thu Nguyen, Phuong Thi Thuy Do, & Dong Phuong Dao (2019). Feature selection methods and sampling techniques to financial distress prediction for Vietnamese listed companies. Investment Management and Financial Innovations, 16(1), 276-290.
- Musa, A. B. (2013). Comparative study on classification performance between support vector machine and logistic regression. International Journal of Machine Learning and Cybernetics, 4(1), 13-24.
- Narayan, Y. (2021). Direct comparison of SVM and LR classifier for SEMG signal classification using TFD features. Materials Today: Proceedings, 45(2), 3543-3546.
- Noble, W. S. (2006). What is a support vector machine? Nature Biotechnology, 24(12), 1565-1567.
- Ohlson, J. A. (1980). Financial Ratios and the Probabilistic Prediction of Bankruptcy. Journal of Accounting Research, 18(1), 109-131.
- Pavlyshenko, B. (2016). Machine learning, linear and Bayesian models for logistic regression in failure detection problems. 2016 IEEE International Conference on Big Data (Big Data) (pp. 2046-2050).
- Pławiak, P., Abdar, M., & Acharya, U. R. (2019). Application of new deep genetic cascade ensemble of SVM classifiers to predict the Australian credit scoring. Applied Soft Computing, 84, 105740.
- Rahman, M. S. (2016). The Advantages and Disadvantages of Using Qualitative and Quantitative Approaches and Methods in Language “Testing and Assessment” Research: A Literature Review. Journal of Education and Learning, 6(1), 102-112.
- Rakotomalala, R. (2016). SVM: Support vector machine. Supervised Learning - Classification.
- Ravi Kumar, P., & Ravi, V. (2007). Bankruptcy prediction in banks and firms via statistical and intelligent techniques – A review. European Journal of Operational Research, 180(1), 1-28.
- Revel, A. (2016). S´eparateurs `a vaste marge [Support Vector Machines].
- Ribeiro, B., Silva, C., Chen, N., Vieira, A., & das Neves, J. C. (2012). Enhanced default risk models with SVM+. Expert Systems with Applications, 39(11), 10140-10152.
- Ruiz, S., Gomes, P., Rodrigues, L., & Gama, J. (2017). Credit Scoring in Microfinance Using Non-traditional Data. In E. Oliveira, J. Gama, Z. Vale, & H. Lopes Cardoso (Eds.), Progress in Artificial Intelligence (pp. 447-458). Springer International Publishing.
- Salazar, D. A., Vélez, J. I., & Salazar, J. C. (2012). Comparison between SVM and Logistic Regression: Which One is Better to Discriminate? Expert Systems with Applications, 35(2), 223-237.
- Savas, C., & Dovis, F. (2019). The Impact of Different Kernel Functions on the Performance of Scintillation Detection Based on Support Vector Machines. Sensors, 19(23), 5219.
- Suykens, J. A. K., & Vandewalle, J. (1998). Least Squares Support Vector Machine Classifiers. Kluwer Academic Publishers.
- Svabova, L., Michalkova, L., Durica, M., & Nica, E. (2020). Business Failure Prediction for Slovak Small and Medium-Sized Companies. Sustainability, 12(11), 4572.
- Thi Vu, L., Thi Vu, L., Thu Nguyen, N., Thi Thuy Do, P., & Phuong Dao, D. (2019). Feature selection methods and sampling techniques to financial distress prediction for Vietnamese listed companies. Investment Management and Financial Innovations, 16(1), 276-290.
- Tsai, M.-C., Lin, S.-P., Cheng, C.-C., & Lin, Y.-P. (2009). The consumer loan default predicting model – An application of DEA–DA and neural network. Expert Systems with Applications, 36(9), 11682-11690.
- Verplancke, T., Van Looy, S., Benoit, D., Vansteelandt, S., Depuydt, P., De Turck, F., & Decruyenaere, J. (2008). Support vector machine versus logistic regression modeling for prediction of hospital mortality in critically ill patients with haematological malignancies. BMC Medical Informatics and Decision Making, 8(1), 56.
- Wen, Z., & Li, T. (Eds.) (2013). Practical Applications of Intelligent Systems. Proceedings of the Eighth International Conference on Intelligent Systems and Knowledge Engineering, Shenzhen, China. Heidelberg: Springer Berlin Heidelberg.
- West, D. (2000). Neural network credit scoring models. Computers & Operations Research, 27(11-12), 1131-1152.
- Worth, A., & Cronin, M. (2003). The use of discriminant analysis, logistic regression and classification tree analysis in the development of classification models for human health effects. Journal of Molecular Structure: THEOCHEM, 622, 97-111.
- Xiao, W., Zhao, Q., & Fei, Q. (2006). A comparative study of data mining methods in consumer loans credit scoring management. Journal of Systems Science and Systems Engineering, 15(4), 419-435.
- Yao, J.-R., & Chen, J.-R. (2019). A New Hybrid Support Vector Machine Ensemble Classification Model for Credit Scoring. Journal of Information Technology Research, 12(1), 77-88.
- Zhang, L., Hu, H., & Zhang, D. (2015). A credit risk assessment model based on SVM for small and medium enterprises in supply chain finance. Financial Innovation, 1(1), 14.
- Zhang, Q., Wang, J., Lu, A., Wang, S., & Ma, J. (2018). An improved SMO algorithm for financial credit risk assessment – Evidence from China’s banking. Neurocomputing, 272, 314-325.
- Zhou, L., Lai, K. K., & Yen, J. (2009). Credit Scoring Models with AUC Maximization Based on Weighted SVM. International Journal of Information Technology & Decision Making, 8(4), 677-696.
- Zizi, Y., Oudgou, M., & El Moudden, A. (2020). Determinants and Predictors of SMEs’ Financial Failure: A Logistic Regression Approach. Risks, 8(4), 107.
-
-
Conceptualization
Karim Amzile, Mohamed Habachi
-
Data curation
Karim Amzile, Mohamed Habachi
-
Formal Analysis
Karim Amzile, Mohamed Habachi
-
Funding acquisition
Karim Amzile
-
Investigation
Karim Amzile, Mohamed Habachi
-
Methodology
Karim Amzile, Mohamed Habachi
-
Project administration
Karim Amzile, Mohamed Habachi
-
Resources
Karim Amzile
-
Software
Karim Amzile
-
Supervision
Karim Amzile, Mohamed Habachi
-
Validation
Karim Amzile, Mohamed Habachi
-
Visualization
Karim Amzile, Mohamed Habachi
-
Writing – original draft
Karim Amzile, Mohamed Habachi
-
Writing – review & editing
Karim Amzile, Mohamed Habachi
-
Conceptualization
-
Fintech in the eyes of Millennials and Generation Z (the financial behavior and Fintech perception)
Mohannad A. M. Abu Daqar , Samer Arqawi , Sharif Abu Karsh doi: http://dx.doi.org/10.21511/bbs.15(3).2020.03Banks and Bank Systems Volume 15, 2020 Issue #3 pp. 20-28 Views: 6274 Downloads: 2137 TO CITE АНОТАЦІЯThis study investigates the Millennials and Gen Z perception toward Fintech services, their usage intention, and their financial behavior. The study took place in the Palestinian context with a global comparison among these generations. The authors used the questionnaire-based technique to meet the study objective. West Bank respondents were selected for this purpose; the study instrument was distributed through different social media channels. The findings show that reliability/trust and ease of use are the main issues in using a financial service. Millennials are more aware (48%) of Fintech services than Gen Z (38%), which is different from the global view where Gen Z is the highest. The smartphone penetration rate is 100% among both generations, while the financial inclusion ratio in Palestine is around 36.4%; these clear indicators are the main Fintech drivers to promote Fintech services in Palestine, and these are global indicators for Fintech adoption intention. Both generations (84%) intend to use e-wallet services, Millennials (87%) and Gen Z is (70%) prefer using real-time services. Half of the respondents see that Fintech plays a complementary role with banks. The majority see that Fintech services are cheaper than bank services. Wealth management, and robot advisor services, and both generations are looking to acquire them in the long run. The authors revealed that 85% of respondents from both generations trust banks, so it is recommended that banks digitize their financial services to meet the customers’ needs, considering that 90% of respondents see that promotions are a key issue in adopting Fintech services. Promoting e-wallet services by banks is highly recommended due to the massive rivalry with Fintech parties.
-
Evaluation of empirical attributes for credit risk forecasting from numerical data
Augustinos I. Dimitras , Stelios Papadakis , Alexandros Garefalakis doi: http://dx.doi.org/10.21511/imfi.14(1).2017.01Investment Management and Financial Innovations Volume 14, 2017 Issue #1 pp. 9-18 Views: 3548 Downloads: 1425 TO CITE АНОТАЦІЯIn this research, the authors proposed a new method to evaluate borrowers’ credit risk and quality of financial statements information provided. They use qualitative and quantitative criteria to measure the quality and the reliability of its credit customers. Under this statement, the authors evaluate 35 features that are empirically utilized for forecasting the borrowers’ credit behavior of a Greek Bank. These features are initially selected according to universally accepted criteria. A set of historical data was collected and an extensive data analysis is performed by using non parametric models. Our analysis revealed that building simplified model by using only three out of the thirty five initially selected features one can achieve the same or slightly better forecasting accuracy when compared to the one achieved by the model uses all the initial features. Also, experimentally verified claim that universally accepted criteria can’t be globally used to achieve optimal results is discussed.
-
Capitalization of banks: theory, practice and directions of ensuring
Mark Myronenko , Olena Polova , Olha Khaietska , Natalia Koval doi: http://dx.doi.org/10.21511/bbs.13(1).2018.16Banks and Bank Systems Volume 13, 2018 Issue #1 pp. 173-183 Views: 3156 Downloads: 333 TO CITE АНОТАЦІЯIn the article, the essence of the concept of a banking institution “capitalization” is revealed. The current state of capitalization level of domestic banks is investigated. The directions of strengthening the capitalization are offered, which will increase the com¬petitiveness of domestic banking institutions in the world financial market and will ensure the national economy stability on the way toward integration into the world economy.
It is proved that the prospects for the development of any bank are largely determined by its capitalization level. Lack of proper development inhibits both individual banks and the banking sector as a whole.
In the context of the recent financial crisis, the provision of sufficient capital for banks has been one of the key issues, because the lack of capital was the greatest threat to the banking system stability. With this in mind, the issue of the banking system capitaliza¬tion is particularly topical.
Today, the development of the Ukrainian banking system under economic instability has faced the increase in competitiveness of domestic banks compared with foreign ones, in order to preserve the national priorities of the banking system in general under conditions of foreign capital movement.
The processes of concentration in the banking system of Ukraine are analyzed using Herfindahl-Hirschman index in terms of assets and equity, allowing to estimate the level of monopolization and, therefore, the impact on economic development. To con¬sider the increase in the level of capitalization and reliability of the banking institutions of Ukraine, it would be advisable, first of all, for banks to improve the quality of capital and to ensure a sufficient level of coverage of risks taken by banks.