Research Article
BibTex RIS Cite

On the Financial Situation Analysis with KNN and Naive Bayes Classification Algorithms

Year 2020, Volume: 10 Issue: 4, 2881 - 2888, 15.12.2020
https://doi.org/10.21597/jist.703004

Abstract

Classification, a data mining technique, has been applied on the financial parameters used in the Altman Z-Score formulas for a certain number of selected firms in manufacturing industry. The Altman Z-Score is used to estimate a firm's financial difficulties. The Z-Score value shows whether the financial position of the firm is good, moderate or risky. In this study, KNN and Naive Bayes algorithms are used as classification methods. The Z-Score values of all firms are calculated and a certain number of data for all three types are selected and taught to the system as learning data. Algorithms are run on the financial parameters in the Z-Score formulas of companies not taught to the system. Over all data, The KNN and Naive Bayes algorithms achieve 84–88% and 75–86% success, respectively. This study, where data mining techniques are applied on a finance model and successful results are achieved, will contribute to the application of different technologies in many different analysis processes of the financial sector.

Supporting Institution

Ege University Scientific Research Projects Directorate

Project Number

21759

Thanks

This study is supported by Ege University Scientific Research Projects Directorate with the Project Number 21759.

References

  • Agrawal R, Imielinski T, Swami A, 1993. Database mining: A performance perspective. IEEE transactions on knowledge and data engineering, 5(6): 914-925.
  • Altman EI, 1968. Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The journal of finance, 23(4): 589-609.
  • Aktaş R, 2003. Mali Başarısızlığın Öngörülmesi: İstatistiksel Yöntemler ve Yapay Sinir Ağı Karşılaştırılması. Ankara Üniversitesi SBF Dergisi, 58(04).
  • Beaver WH, 1966. Financial ratios as predictors of failure. Journal of accounting research, 71-111.
  • Dasarathy BV, 1991. Nearest neighbor (NN) norms: NN pattern classification techniques. IEEE Computer Society Tutorial.
  • Dewi A, Hadri M, 2017. Financial distress prediction in Indonesia companies: finding an alternative model. Russian Journal of Agricultural and Socio-Economic Sciences, 61(1).
  • Fathi S, Saif S, Heydari Z, 2018. Predicting bankruptcy of companies using data mining models and comparing the results with Z Altman model. International journal of finance & managerial accounting, 3(10): 33-46.
  • Kaygın CY, Tazegül A, Yazarkan H, 2016. İşletmelerin Finansal Başarılı ve Başarısız Olma Durumlarının Veri Madenciliği ve Lojistik Regresyon Analizi ile Tahmin Edilebilirliği. Ege Academic Review, 16(1).
  • Kürklü E, Türk Z, 2017. Financial failure estimate in bist companies with Altman (Z-score) and Springate (S-score) models. Osmaniye Korkut Ata Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 1(1): 1-14.
  • Ohlson JA, 1980. Financial ratios and the probabilistic prediction of bankruptcy. Journal of accounting research, 109-131.
  • Patil TR, Sherekar SS, 2013. Performance analysis of Naive Bayes and J48 classification algorithm for data classification. International journal of computer science and applications, 6(2): 256-261.
  • Özkan M, Boran L, 2014. Veri Madenciliğinin Finansal Kararlarda Kullanımı. Çankırı Karatekin Üniversitesi İİBF Dergisi, 4(1): 59-82.
  • Wu X, Kumar V, Ross Quinlan J, et al. 2008. Top 10 algorithms in data mining. Knowledge and information systems, 14: 1-37.

KNN ve Naive Bayes Sınıflandırma Algoritmaları ile Finansal Durum Analizi Üzerine

Year 2020, Volume: 10 Issue: 4, 2881 - 2888, 15.12.2020
https://doi.org/10.21597/jist.703004

Abstract

Bu çalışmada veri madenciliği tekniklerinden biri olan sınıflandırma, imalat sanayi sektöründe hizmet veren belirli sayıda seçilmiş firmaların Altman Z-Skor formülünde kullanılan finans parametreleri üzerinde uygulanmıştır. Altman Z-Skor değeri bir firmanın finansal zorluklarla karşılaşma durumunun tahminlemesinde kullanılır. Z-Skor değeri, firmanın finansal durumunun iyi, orta veya riskli olup olmadığı hakkında yorum yapar. Bu makalede sınıflandırma yöntemi için KNN ve Naive Bayes algoritmaları kullanılmıştır. Bütün firmaların Z-Skor değerleri hesaplanmış ve her 3 tipten belirli sayıda veri seçilerek öğrenme verisi olarak sisteme öğretilmiştir. Algoritmalar sisteme öğretilmemiş firmaların Z-Skor formülündeki finans parametreleri üzerinde çalıştırılmıştır. Tüm veri üzerinde KNN algoritması yaklaşık %84-88, Naive Bayes algoritması ise %75-86 aralığında başarı ile sonuçlanmıştır. Veri madenciliği tekniklerinin bir finans modeli üzerinde uygulandığı ve başarılı sonuçların elde edildiği bu proje, farklı teknolojilerin finans sektörünün bir çok farklı analiz süreçlerinde uygulanmasına katkı sağlayacaktır.

Project Number

21759

References

  • Agrawal R, Imielinski T, Swami A, 1993. Database mining: A performance perspective. IEEE transactions on knowledge and data engineering, 5(6): 914-925.
  • Altman EI, 1968. Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The journal of finance, 23(4): 589-609.
  • Aktaş R, 2003. Mali Başarısızlığın Öngörülmesi: İstatistiksel Yöntemler ve Yapay Sinir Ağı Karşılaştırılması. Ankara Üniversitesi SBF Dergisi, 58(04).
  • Beaver WH, 1966. Financial ratios as predictors of failure. Journal of accounting research, 71-111.
  • Dasarathy BV, 1991. Nearest neighbor (NN) norms: NN pattern classification techniques. IEEE Computer Society Tutorial.
  • Dewi A, Hadri M, 2017. Financial distress prediction in Indonesia companies: finding an alternative model. Russian Journal of Agricultural and Socio-Economic Sciences, 61(1).
  • Fathi S, Saif S, Heydari Z, 2018. Predicting bankruptcy of companies using data mining models and comparing the results with Z Altman model. International journal of finance & managerial accounting, 3(10): 33-46.
  • Kaygın CY, Tazegül A, Yazarkan H, 2016. İşletmelerin Finansal Başarılı ve Başarısız Olma Durumlarının Veri Madenciliği ve Lojistik Regresyon Analizi ile Tahmin Edilebilirliği. Ege Academic Review, 16(1).
  • Kürklü E, Türk Z, 2017. Financial failure estimate in bist companies with Altman (Z-score) and Springate (S-score) models. Osmaniye Korkut Ata Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 1(1): 1-14.
  • Ohlson JA, 1980. Financial ratios and the probabilistic prediction of bankruptcy. Journal of accounting research, 109-131.
  • Patil TR, Sherekar SS, 2013. Performance analysis of Naive Bayes and J48 classification algorithm for data classification. International journal of computer science and applications, 6(2): 256-261.
  • Özkan M, Boran L, 2014. Veri Madenciliğinin Finansal Kararlarda Kullanımı. Çankırı Karatekin Üniversitesi İİBF Dergisi, 4(1): 59-82.
  • Wu X, Kumar V, Ross Quinlan J, et al. 2008. Top 10 algorithms in data mining. Knowledge and information systems, 14: 1-37.
There are 13 citations in total.

Details

Primary Language English
Subjects Computer Software, Mathematical Sciences
Journal Section Matematik / Mathematics
Authors

Oğuzcan Uludağ 0000-0002-2681-5828

Arif Gürsoy 0000-0002-0747-9806

Project Number 21759
Publication Date December 15, 2020
Submission Date March 12, 2020
Acceptance Date July 4, 2020
Published in Issue Year 2020 Volume: 10 Issue: 4

Cite

APA Uludağ, O., & Gürsoy, A. (2020). On the Financial Situation Analysis with KNN and Naive Bayes Classification Algorithms. Journal of the Institute of Science and Technology, 10(4), 2881-2888. https://doi.org/10.21597/jist.703004
AMA Uludağ O, Gürsoy A. On the Financial Situation Analysis with KNN and Naive Bayes Classification Algorithms. J. Inst. Sci. and Tech. December 2020;10(4):2881-2888. doi:10.21597/jist.703004
Chicago Uludağ, Oğuzcan, and Arif Gürsoy. “On the Financial Situation Analysis With KNN and Naive Bayes Classification Algorithms”. Journal of the Institute of Science and Technology 10, no. 4 (December 2020): 2881-88. https://doi.org/10.21597/jist.703004.
EndNote Uludağ O, Gürsoy A (December 1, 2020) On the Financial Situation Analysis with KNN and Naive Bayes Classification Algorithms. Journal of the Institute of Science and Technology 10 4 2881–2888.
IEEE O. Uludağ and A. Gürsoy, “On the Financial Situation Analysis with KNN and Naive Bayes Classification Algorithms”, J. Inst. Sci. and Tech., vol. 10, no. 4, pp. 2881–2888, 2020, doi: 10.21597/jist.703004.
ISNAD Uludağ, Oğuzcan - Gürsoy, Arif. “On the Financial Situation Analysis With KNN and Naive Bayes Classification Algorithms”. Journal of the Institute of Science and Technology 10/4 (December 2020), 2881-2888. https://doi.org/10.21597/jist.703004.
JAMA Uludağ O, Gürsoy A. On the Financial Situation Analysis with KNN and Naive Bayes Classification Algorithms. J. Inst. Sci. and Tech. 2020;10:2881–2888.
MLA Uludağ, Oğuzcan and Arif Gürsoy. “On the Financial Situation Analysis With KNN and Naive Bayes Classification Algorithms”. Journal of the Institute of Science and Technology, vol. 10, no. 4, 2020, pp. 2881-8, doi:10.21597/jist.703004.
Vancouver Uludağ O, Gürsoy A. On the Financial Situation Analysis with KNN and Naive Bayes Classification Algorithms. J. Inst. Sci. and Tech. 2020;10(4):2881-8.