USING MACHINE LEARNING ALGORITHMS FOR PREDICTION OF LOAN RETURN ABILITY

ilhomjonqodirov02

Authors

         Nizamitdinov A.I. – Doctor of philosophy (PhD), Department of Digital Economy, Polytechnic Institute of Tajik Technical University, Khujand, Republic of Tajikistan, ahlidin@gmail.com

        Sanginov S.I. – the second year master student of specialization 1-400301- Artificial Intelligence, Polytechnic Institute of Tajik Technical University, Khujand,  Republic of Tajikistan, saidikbols@gmail.com

Annotation

       This article discusses the process of prediction the risk probability of non-payment of a loan by bank customers. In connection with the increase in competition in the market of credit services, the development of new algorithms for issuing this process and a more accurate assessment of the risk of liquidity of loans is an urgent issue. The purpose of the study is to improve the methodology for predicting the probability of repayment of loans by bank customers based on the use of modern machine learning methods and the formation of an optimal lending solution. The loan repayment probability is analyzed based on the known characteristics of the borrower using predictive machine learning algorithms (clustering, regression analysis and classification). These algorithms allow the use of individual models and their possible combinations. The article uses common machine learning algorithms to solve classification problems such as logistic regression, simple Bayes classifiers, support vector machines, and decision trees.

A set of models using machine learning algorithms makes forecasting the probability of liquidity more accurate improves the quality of risk assessment and optimizes the lending process.

Key words

 machine learning algorithms, creditworthiness, credit scoring, artificial intelligence, machine learning, discriminant analysis, logistic regression.

Language

english

Type

technical

Year

2021

Page

19-20

References

    1. Aivazyan S.A., Buchstaber V.M., Enyukov I.S., Meshalkin L.D. Applied Statistics: Classification and Dimension Reduction. M.: Finance and statistics, 1989. 607 p.
    2. Aivazyan S.A., Enyukov I.S., Meshalkin L.D. Applied statistics. Fundamentals of modeling and primary data processing. M.: Finance and statistics, 1983. 471 p.
    3. Andreeva G.V. Scoring as a method for assessing credit risk // Banking technologies. 2000. No. 6. S. 14–19.
    4. Vagin V.N., Golovina E.Yu., Zagoryanskaya A.A., Fomina M.V. Reliable and plausible conclusion in intelligent systems / ed. V.N. Vagina, D.A. Pospelov. M.: FIZMAT LIT, 2004. 704 p.
    5. Valeev S.G. Regression modeling in data processing. Kazan: FEN, 2001. 296 p.
    6. Vapnik V.N. Recovery of dependences on empirical data. M.: Nauka, 1979. 448 p.
    7. Vasiliev N.P., Egorov A.A. Experience in calculating the parameters of logistic regression by the Newton-Raphson method for assessing the winter hardiness of plants // Mathematical biology and bioinformatics. 2011. V. 6. No. 2. S. 190–199.
    8. Gotovkin I. Complex scoring model for assessing client default // Banking technologies. 2006. No. 1. S. 27–35.
    9. Draper N., Smith G. Applied regression analysis. Multiple regression. M.: Dialectika, 2007. 912 p.
    10. Dubrov A.M., Mkhitaryan V.S., Troshin L.I. Multivariate statistical methods: textbook. M.: Finance and statistics, 2003. 352 p.
    11. Ishina I.V., Sazonova M.N. Scoring – a model for assessing credit risk // Audit and financial analysis. 2007. No. 4. S. 297–304.
    12. Litvinova S.A. Scoring systems as a means of minimizing the bank’s credit risk // Audit and financial analysis. 2010. No. 2. S. 396–397.
    13. Little R.J. A., Rubin D.B. Statistical analysis of data with gaps. M.: Finance and statistics, 1990. 336 p.
    14. Malyugin V.I., Grin N.V. On the effectiveness of statistical algorithms for credit scoring // Bankaўskі vesnik. No. 31. 2010. P. 39–46.
    15. Sorokin A.S. Construction of scoring maps using a logistic regression model // Naukovedenie. URL: http://naukovedenie.ru/PDF/180EVN214.pdf.
    16. Wasserman F. Neurocomputer technology: Theory and practice. M.: Mir, 1992. 184 p.
    17. Cherny I.M. Credit scoring: the Russian version of development // Banking services. 2006. No. 4. P. 12–17.
    18. Yakupov A.I. Application of decision trees for modeling the creditworthiness of commercial bank clients // Artificial Intelligence. 2008. No. 4. S. 208–213.
    19. Dingyu Xue, Yangquan Chen. Solving applied mathematical problems with MATLAB. London: Taylor & Francis Group, 2009. 418 p.
    20. Powers D.M.W. Evaluation: from Precision, Recall and F-measure to ROC, Informedness, Markedness and Correlation // Journal of Machine Learning Technologies. 2011 Vol. 2. Iss. 1. P. 37–63.

Publication date

2023-10-02