DATA MINING APPLICATION FOR FINANCIAL DECISION OPTIMIZATION AT RISK

Year 2021, , 195 - 209, 31.08.2021

Enes Koçoğlu , Filiz Ersöz

https://doi.org/10.46519/ij3dptdi.950062

Abstract

Financial decisions can add value to the existence of businesses or individuals, as well as a wrong financial decision can cause businesses to cease to exist. Hence, financial decision or financial assumptions are vital for businesses or individuals. In financial assumptions, risk refers to the probability of losing as a result of an investment made in an asset. Measures can be taken against possible risks in the future through financial assumptions. In this study, the logistic regression analysis (LR) method, one of the traditional methods, and the machine learning algorithm support vector machines (SVM) method, which is one of the new approaches, are compared in the loaning process. It is aimed to determine the importance of the compared methods, the accuracy of the model, the estimation power of the model, the estimation performance of the model, the determination of the importance of the independent variables that affect the non-repayment of the loan, and the superiority of the methods. According to the analysis results, the SVM method is superior to the LR method in calculating accuracy rate and prediction rate, and the LR method is superior to the SVM method in assumption performance calculation. The most significant variable in the SVM method is "Lending policy", the most significant variable in the LR method is "Interest rate", the second significant variable is "Interest rate" in the SVM method, and "Lending Policy" as the second important variable in the LR method. It is seen that the third most crucial variable in the two methods is the "Income" variable. The determination of the SVM method as the more important variable of the loan policy is deemed more suitable to the opinion of the banking expert. Detecting more realistic results of the SVM method compared to the LR method has shown the superiority of the SVM method.

Keywords

Support Vector Machines, Logistic Regression, Data Mining, Decision Making Under Risk

References

• 1. Kökdemir, D., ''Belirsizlik Durumlarında Karar Verme ve Problem Çözme'', Doktora Tezi, [Decision Making and Problem Solving Under Uncertainty Situatons][Thesis in Turkish], Ankara Üniversitesi, Ankara, 2003.
• 2. Koçi, E., ''Riskli Ortamlarda Karar Verme'', Yüksek Lisans Tezi, [Decision Making in Risky Environments] [Thesis in Turkish], Ankara Üniversitesi, Ankara, 2009.
• 3. Bilgütay, H., Deniz, M., ''Risk Kültürünün Karar Verme Sürecine Etkisi'' [The Effect of Risk Culture on the Decision - Making Process] [article in Turkish], Finans Ekonomi ve Sosyal Araştırmalar Dergisi, Vol 4, Issue 2, Pages 128 - 140, 2019.
• 4. Nazari, M., Alidadi, M., ''Measuring Credit Risk of Bank Customers Using Artificial Neural Network'', Journal of Management Research, Vol 5, Issue 2, 2013.
• 5. Maldonado, S., Bravo, C., Lopez, J., Perez, J., ''Integrated Framework for Profit-Based Feature Selection and DVM Classification in Credit Scoring'', Decision Support Systems, Vol 104, Pages 113-121, 2017.
• 6. Ersöz, F., ''Dijitalleşme Çağında Büyük Veri ve Analitiği: Sektörel Uygulamalar'', 4th International Congress on 3D Printing Technologies and Digital Industry, 2019.
• 7. Ersöz, F., ''Veri Madenciliği Teknikleri ve Uygulamaları'', Seçkin Yayıncılık, Ankara, 2019.
• 8. Ersöz, F., ''Research Article Data Mining and Text Mining with Big Data: Review of Differences'', International journal of Recent Advances in Multidisciplinary Research, Vol 6, no 1, Pages 4391- 4396, 2019.
• 9. Khojasteh, G., Karimzadeh, S, ''Credit Risk Measurement of Trusted Customers Using Lojistic Regression and Neural Networks'', Journal of System Management, Issue 3, Pages 91-104, 2019.
• 10. Keramati, M. A., Shaeri, M., ''Assessment of Credit Risk Management and Managerial Efficiency of Banks Using Data Envelopment Analysis (DEA) Network'', Biological Forum - An International Journal, Vol 6, Issue 2, Pages 320-328, 2014.
• 11. Kapdan, F., Akta, M.G., ''Durum Tabanlı Çıkarsama Yöntemi ile Finansal Risk Tahmini'', Innovations in Intelligent Systems and Applications Conference, 2019.
• 12. Mandacı, P.E., ''Türk Bankacılık Sektörünün Taşıdığı Riskler ve Finansal Krizi Aşmada Kullanılan Risk Ölçüm Teknikleri'' [The Risks that the Turkish Banking Sector Faced and The Risk Measurement Models in Overcoming the Crisis] [article in Turkish], Dokuz Eylül Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, Vol 5, Issue 1, Pages 67-84, 2003.
• 13. Parvizi, R., Adibi, M.A., ''Assessing and Validating Bank Customers Using Data Mining Algorithms for Loan Home'', International journal of Industrial Engineering and Operational Research, Vol 2, Issue 1, 2020.
• 14. Asareh, B., Ghaeli, M.R., ''Valuation and Assesment of Customers in Banking Industry Using Data Mining Techniques'', International Journal of Data and Network Science, Vol 3, Issue 2, Pages 93-102, 2019.
• 15. Saia, R., Carta, S., Fenu, G., ''A Wavelet-based Data Analysis to Credit Scoring'', ACM International Conference Proceeding Series, 2018.
• 16. Kawa, D., Punyani, S., Nayak, P., Karkera, A., Jyotinagar, V., ''Credit Risk Assessment from Combined Bank Records Using Federated Learning'', International Research Journal of Engineering and Technology, Vol 6, Issue 4, Pages 1355-1358, 2019.
• 17. Dereliolu, G., Gürgen, F., ''Knowledge Discovery Using Neural Approach for SME's Credit Risk Analysis Problem in Turkey'', Expert Systems with Applications, Vol 38, Issue 8, Pages 9313-9318, 2011.
• 18. Golbayani, P., Florescu, I., Chatterjee, R., ''A Comparative Study of Forecasting Corporate Credit Ratings Using Neural Networks, Support Vector Machines, and Decision Trees'', Nort American Journal of Economics and Finance, Vol 54, 2020.
• 19. Hsu, M., W., Lessmann, S., Suang, M.C., Ma, T., Johnson, J.E.V., ''Bridging the Divide in Financial Market Forecasting: Machine Learners vs. Financial Economists'', Expert Systems with Applications, Vol 61, Pages 215-234, 2016.
• 20. Nawai, N., Shariff, M.N.M., ''Factors Affecting Repayment Performance in Microfinance Programs in Malaysia'', Procedia - Social and Behavioral Sciences, Vol 62, Pages 806-811, 2012.
• 21. Unver, M., Sahin, B., Ersöz, F., ''An Application of Logistics Regression Model to Determining the Credit Suitability and Impacting Factors in a Special Bank Branch'', Vol 12, Issue 1, Pages 1-12, 2018.
• 22. Ersöz, T., Ersöz, F., Özbilge, S., ''Determination of the Bank's Customer Risk Profile: Data Mining Applications'', Vol 10, Issue 6, Pages 2199-2203, 2016.
• 23. Plawiak, P., Abdar, M., Rajendra Acharya, U., ''Application of New Deep Genetic Cascade Ensemble of SVM Classifiers to Predict the Australian Credit Scoring'', Applied Soft Computing Journal, Vol 84, 2019.
• 24. Bellotti, T., Matousek, R., Stewart, C., ''A Note Comparing Support Vector Machines and Ordered Choice Models' Predictions of İnternational Banks' Ratings'', Decision Support Systems, Vol 51, Issue 3, Pages 682-687, 2011.
• 25. Kara, M., ''Yapay Zeka Modeliyle Genişletilmiş Hibrit Black - Litterman Model Önerisi, Borsa İstanbul BIST-30 Endeks Verileri ile Test Edilmesi'', Doktora Tezi, [Hybrid - Litterman Model Proposal Extended with Artificial Intelligence Model, Testing with Borsa İstanbul BIST-30 Index Data] [Thesis in Turkish], Hacettepe Üniversitesi, Ankara, 2017.
• 26. Chen, Z., Matousek, R., Wanke, P., ''Chinese Bank Efficiency During The Global Financial Crisis: A Combined Approach Using Satisficing DEA and Support Vector Machines'', North American Jouranl of Economics and Finance, Vol 43, Pages 71-86, 2018.
• 27. Hasan, A., ''Derin Öğrenme ve Makine Öğrenmesi Yöntemleriyle Borsa Alım Satım Davranışlarının Modellenmesi'', Doktora Tezi, [Modeling Stock Exchange Trading Behaviors with Deep Learning and Machine Learning Methods] [Thesis in Turkish], Yıldız Teknik Üniversitesi, İstanbul, 2020.
• 28. Korkmaz, G., ''Yapay Zekâ Yöntemleriyle Sınıflandırma ve Finans Sektöründe Kurumsal Müşterilere Dönük Bir Uygulama'' [Classfication with Artificial Intelligence Methods and An Application For Corporate Customers in the Finance Sector] [article in Turkish], Akademik Yaklaşımlar Dergisi, Vol 11, Issue 2, Pages 91-109, 2020.
• 29. Bilik, M., Aydın, Ü., ''Konut Sahibi Olma Kararlarını Etkileyen Faktörler: Lojistik Regresyon ve Destek Vektör Makinelerinin Karşılaştırılması'' [Factors Affecting The Housing Demand: A Comparison of Logistics Regression and Support Vector Machines] [article in Turkish], Dumlupınar Üniversitesi Sosyal Bilimler Dergisi, Vol 62, Pages 184-199, 2019.
• 30. Demirci, İ., Retrived from https://www.kaggle.com/izemdemirci/lendingloans, 2 Ocak, 2021.
• 31. Finlay, S.M., ''Predictive Models of Expenditure and Over - Indebtedness for Assessing the Affordability of New Consumer Credit Applications'', Journal of the Operational Research Society,Vol 57, Issue 6, Pages 655-669, 2006.
• 32. Verbraken, T., Bravo, C., Weber, R., Baesens, B., ''Development and Application of Consumer Credit Scoring Models Using Profit-Based Classification Measures'', Europen Journal of Operational Research, Vol 238, Issue 2, Pages 505-513, 2014.
• 33. Louzada, F., Ara, A., Femandes, G.B., ''Classification Methods Applied to Credit Scoring: Systematic Review and Overall Comparison'', Surveys in Operations Research and Management Science, Vol 21, Issue 2, Pages 117-134, 2016.
• 34. Jean Paul, B., Loezer, L., Enembreck, F., Lanzuolo, R., ''Lessons Learned From Data Stream Classification Applied to Credit Scoring'', Expert Systems With Applications, Vol 162, 2020.
• 35. Yang, R., Yu, L., Zhao, Y., Yu, H., Xu, G., Wu, Y., Liu, Z., ''Big Data Analytics For Financial Market Volatility Forecast Based on Support Vector Machine'', International Journal of Information Management, Vol 50, Pages 452-462, 2020.
• 36. Ayhan, S., ''Kaba Küme ve Destek Vektör Makineleri Kullanılarak Nitelik İndirgeme ve Sınıflandırma Problemlerinin Çözümü için Bütünleşik Bir Yaklaşım'', Doktora Tezi, [An Integrated Approach for Solving Attribute Reduction and Classification Problems Using Rough Set and Support Vector Machines] [Thesis in Turkish], Eskişehir Osmangazi Üniversitesi, Eskişehir, 2013.
• 37. Altıntop, M.Y.,''Dalgacık Dönüşümü ve Destek Vektör Makineleri ile Tahmin: Bıst Üzerine Bir Uygulama'', Doktora Tezi, [Estimation with Wavelet Transform and Support Vector Machines: An Application on Bust] [Thesis in Turkish], Uşak Üniversitesi, Uşak, 2016.
• 38. Janardhanan, P., Heena, L., Sabika, F.,''Effectiveness of Support Vector Machines in Medical Data Mining'', Journal of Communicatıons Software and Systems, Vol 11, Issue 1, Pages 25-30, 2015.
• 39. https://en.wikipedia.org/wiki/Support-vector_machine, 18 Nisan, 2021.
• 40. Haykin, S., ''Neural Networks, a Comprehensive Foundation'', Preditice Hall, Englewood Cliffs, New Jersey, 2001.
• 41. Jote, G.G.,''Determinants of Loan Repayment: The Case of Microfinance Institutions in Gedeo Zone, SNNPRS, Ethiopia '', Universal Journal of Accounting and Finance, Vol 6, Issue 3, Pages 108-122, 2018.
• 42. Cankurt, M., Miran, B., Ahmet, Ş., ''Sığır Eti Tercihlerini Etkileyen Faktörlerin Belirlenmesi Üzerine Bir Araştırma: İzmir ili örneği'' [Determining of the Effective Factors on Cattle Meat Preferences: The Case of İzmir], [article in Turkish], Hayvansal Üretim, Vol 51, Issue 2, Pages 16-22, 2010.
• 43. Shannon, M.D., Davenport, A.M., ''Using SPSS to Solve Statistical Problems: A self-Instruction Guide'', Prentice Hall, ABD, 2001.
• 44. Kalaycı, Ş., ''SPSS Uygulamalı Çok Değişkenli İstatistik Teknikleri'', Asil Yayınlar, Ankara, 2009.
• 45. Sperandei, S., ''Understanding Logistic Regression Analysis'', Biochemia Medica, Vol 24, Issue 1, Pages 8-12, 2014.
• 46. Zweig, M.H., Campbell, G., ''Receiver-Operating Characteristic (ROC) Plots: a Fundamental Evaluation Tool in Clinical Medicine'', Clinical Chemistry, Vol 39, 1993.
• 47. Verbakel, J. Y., Steyerberg, E. W., Uno, H., De Cock, B., Wynants, L., Collins, G. S., Van Calster, B., ''ROC Curves for Clinical Prediction Models Series'', Journal of Clinical Epidemiology, Vol 126, Pages 207-2016, 2020.
• 48. Witten, I. H., Frank, E., ''Credibility: Evaluating What's Been Learned, Data Mining: Practical Machine Learning Tools and Techniques'', Morgan Kaufmann Publıshers, San Francisco, 2005.
• 49. Dondurmacı, G., ''Veri Madenciliği'nde Regresyon Ağaçları ile Sınıflandırma ve Bir Uygulama'', Doktora Tezi, [Classifıcation with Regression Trees and an Application in Data Mining] [Thesis in Turkish], Mimar Sinan Güzel Sanatlar Üniversitesi, İstanbul, 2011.
• 50. Yürük, M.F., Ekşi, İ.H., ''Yapay Zeka Yöntemleri ile İşletmelerin Finansal Başarısızlığının Tahmin Edilmesi: BİST İmalat Sektörü Uygulaması’[Financial Failure Prediction of Companies Using Artificial Intelligence Methods: An Application in BIST Manufacturing Sector] [article in Turkish], Mukaddime, Vol 10, Issue 1, Pages 393 - 422, 2019.
• 51. Tayyar, N., Tekin, S.,'' İMKB-100 Endeksinin Destek Vektör Makineleri ile Günlük, Haftalık ve Aylık Veriler Kullanarak Tahmin Edilmesi'' [Forecasting ISE-100 Index Using Support Vector Machines with Daily, Weekly and Monthly Data] [article in Turkish], AİBÜ Sosyal Bilimler Enstitüsü Dergisi, Vol 13, Issue 1, Pages 189 - 217, 2013.