Journal article

ASSESSING CREDIT RISK USING MACHINE LEARNING METHODS

Year:

2019

Published in:

TOV “Hlobalnyi naukovyi potentsial”
credit risk
rating model
machine learning
discriminatory power
KolmogorovSmirnov test
logistic regression

The article is devoted to solving the problem of minimizing credit risks of the bank issuing loans to legal persons. This study presents a process for the development and implementation of risk prediction model, one that builds upon a foundation of statistics, data mining and machine learning principles. Statistical and data mining techniques and methodologies have been discussed in detail. The key phases that were covered are: the analysis of the bank's internal rating model, calculation of its discriminatory power, mathematical model based on the rating model was built to predict creditworthiness of future borrowers and assessment of model quality coefficients, the algorithm of data cleaning from anomalies and comparison of the model results was applied. The proposed approach to assessing the borrower's creditworthiness improved the quality of the rating model, as well as its ability to distinguish between reliable and unreliable clients, and reduced the number of default and no default clients. It has been defined that selected quality indexes of the classification models: Accuracy, Specificity, Sensitivity, Balanced accuracy, ROC-curve, AUROC and Gini index are higher for the improved model. A feature of the proposed approach is the application of machine learning methods to data analysis and processing in software R programming language. The practical value of the conducted study is the acquired knowledge on the importance of correct selection of data characterizing the rating model, which in the future will serve as one of the tools for prevention of losses from non-fulfillment of credit obligations. There is a need to devise strategies to not only identify customers who exhibit negative behavior (nonpayment, fraud), but also deal with them effectively to minimize further loss and recoup any monies owed, as quickly as possible.

Related by author

23 publications found

2022
Journal article

ПРОГНОЗУВАННЯ БАНКРУТСТВА ПІДПРИЄМСТВА ЗА ДОПОМОГОЮ АЛГОРИТМІВ МАШИННОГО НАВЧАННЯ

Publisher: Ltd “DKS Centre”

Authors: Ihor Miroshnychenko, Vladyslav Krupin

2019
Journal article

Neuro‑fuzzy model of country's investment potential assessment

Publisher: Fuzzy Economic

Authors: A. Matviychuk, O. Lukianenko, Ihor Miroshnychenko

2025
Journal article

Model of management of storage of educational environment data flows

Publisher: Scientific Perspectives

Authors: Ihor Miroshnychenko, Jesus Raychuk

2025
Conference proceedings

DEVELOPMENT OF DATA SCIENCE TECHNOLOGIES IN THE FIELD OF CLIMATE CHANGE RESEARCH

Publisher: Taras Shevchenko National University of Kyiv

Authors: Ihor Miroshnychenko, Andrii Ukrainets

2025
Conference proceedings

EVOLVING RUSSIAN CYBER ATTACKS: KEY TRENDS AND STRATEGIC DEFENSE SOLUTIONS FOR 2024

Publisher: Taras Shevchenko National University of Kyiv

Authors: Maksym Borysenko, Ihor Miroshnychenko

2019
Journal article

Risk and return for cryptocurrencies as alternative investment: Kohonen maps clustering

Publisher: Київський національний економічний університет імені Вадима Гетьмана

Authors: Ihor Miroshnychenko, Andrii Kaminskyi, Kostiantyn Pysanets

2021
Journal article

Forecasting electricity generation from renewable sources in developing countries (on the example of Ukraine)

Publisher: Kyiv National Economic University named after Vadym Hetman

Authors: Ihor Miroshnychenko

2025
Conference proceedings

STOCK PRICE FORECASTING USING ARTIFICIAL NEURAL NETWORKS

Publisher: Taras Shevchenko National University of Kyiv

Authors: Ihor Miroshnychenko, Yurii Levchenko

2025
Conference proceedings

Development of models and information technology for predicting TV viewing metrics using data science methods

Publisher: Slovak University of Technology in Bratislava

Authors: Oleksandr Ilchuk, Ihor Miroshnychenko

2025
Conference proceedings

INFORMATION ANALYTICS FOR FORMING AND SUPPORTING PRODUCTIVE HABITS

Publisher: Taras Shevchenko National University of Kyiv

Authors: Ihor Miroshnychenko, Maxim Suprunenko