<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">scires</journal-id><journal-title-group><journal-title xml:lang="ru">Научные исследования экономического факультета. Электронный журнал</journal-title><trans-title-group xml:lang="en"><trans-title>Scientific Research of Faculty of Economics. Electronic Journal</trans-title></trans-title-group></journal-title-group><issn pub-type="epub">2078-3809</issn><publisher><publisher-name>Moscow State University</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.38050/2078-3809-2025-17-4-136-150</article-id><article-id custom-type="elpub" pub-id-type="custom">scires-427</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ФИНАНСОВАЯ ЭКОНОМИКА</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>FINANCIAL ECONOMICS</subject></subj-group></article-categories><title-group><article-title>Моделирование уровня потерь по розничному портфелю необеспеченных кредитов банков</article-title><trans-title-group xml:lang="en"><trans-title>Loss Given Default Modelling for a Bank’s Retail Portfolio of Unsecured Loans.</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Фролова</surname><given-names>Д. Д.</given-names></name><name name-style="western" xml:lang="en"><surname>Frolova</surname><given-names>D. D.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Фролова Дарья Дмитриевна, студентка магистратуры, экономический факультет</p><p>г. Москва</p></bio><bio xml:lang="en"><p>Daria D. Frolova, Master's student, Faculty of Economics</p><p>Moscow</p></bio><email xlink:type="simple">0001609000@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>МГУ имени М.В. Ломоносова</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Lomonosov Moscow State University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>05</day><month>04</month><year>2026</year></pub-date><volume>17</volume><issue>4</issue><fpage>136</fpage><lpage>150</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Фролова Д.Д., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Фролова Д.Д.</copyright-holder><copyright-holder xml:lang="en">Frolova D.D.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://scires.elpub.ru/jour/article/view/427">https://scires.elpub.ru/jour/article/view/427</self-uri><abstract><p>Грамотное моделирование потерь по розничному кредитному портфелю в случае дефолта (Loss given default – LGD) является важной задачей коммерческих банков. Актуальность исследования обусловлена активным расширением кредитования физических лиц за последние 5 лет. Увеличение объема розничного портфеля с 17,6 до 36,9 трлн р. с 1 января 2020 г. по 1 января 2025 г. способствовало росту кредитного риска российских банков. Дополнительные сложности возникают в связи с высоким уровнем ключевой ставки Банка России и ужесточением макропруденциальной политики в сегменте необеспеченных кредитов физических лиц.В работе описаны основные подходы к моделированию LGD. На основе данных по необеспеченным потребительским кредитам одного из российских банков за период с декабря 2020 г. по март 2025 г., которые содержат более 700 тыс. наблюдений, предложена двухэтапная методика оценки LGD. Подход включает в себя винтажный анализ и применение моделей машинного обучения градиентного бустинга (XGBoost и LightGBM) для оценки и прогнозирования потерь при дефолте с учетом новых макроэкономических факторов: курса доллара к рублю на рынке Форекс и среднемесячной заработной платы работников в РФ.</p></abstract><trans-abstract xml:lang="en"><p>Proper modelling of loss given default (LGD) is an important task for commercial banks. The relevance of the study is due to the active expansion of retail lending over the past 5 years. The increase in the volume of the retail portfolio from 17.6 to 36.9 trillion rubles from the 1st of January until the 1st of January 2025 contributed to an increase in the credit risk of Russian commercial banks. Additional difficulties arise due to the high level of the Bank of Russia's key interest rate and the tightening of macroprudential policy in the segment of unsecured retail loans. The paper describes the main approaches to LGD modelling. Based on data on unsecured consumer loans from one of the Russian banks for the period from December 2020 to March 2025, which contain more than 700,000 observations, a two-stage LGD assessment methodology has been proposed. The approach includes vintage analysis and the use of machine learning models (XGBoost and LightGBM) to assess and predict LGD considering new macroeconomic factors: the USD/RUB exchange rate on the Forex market and the average monthly salary of Russian employees.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>потери при дефолте по кредитным обязательствам</kwd><kwd>розничный портфель</kwd><kwd>коммерческие банки</kwd><kwd>необеспеченные кредиты физических лиц</kwd><kwd>моделирование</kwd><kwd>винтажный анализ</kwd><kwd>машинное обучение.</kwd></kwd-group><kwd-group xml:lang="en"><kwd>Loss Given Default</kwd><kwd>retail portfolio</kwd><kwd>commercial banks</kwd><kwd>unsecured retail loans</kwd><kwd>modelling</kwd><kwd>vintage analysis</kwd><kwd>machine learning.</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Афанасьев С., Молоканов И., Ахметсафин И., Смирнова А. Разработка LGD-моделей для розничного кредитования. Ч. 1: подготовка данных // Риск-менеджмент в кредитной организации. 2021. №. 3. С. 4–23.</mixed-citation><mixed-citation xml:lang="en">Afanas'ev S., Molokanov I., Akhmetsafin I., Smirnova A. Razrabotka LGD-modeley dlya roznichnogo kreditovaniya. Ch. 1: podgotovka dannykh. Risk-menedzhment v kreditnoy organizatsii. 2021. №. 3. S. 4–23. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Ишмуратова Т.В. Математическое моделирование потерь в случае наступления дефолта на уровне кредитного обязательства // Вестник Чувашского университета. 2018. № 3. С. 192–205.</mixed-citation><mixed-citation xml:lang="en">Ishmuratova T.V. Matematicheskoe modelirovanie poter' v sluchae nastupleniya defolta na urovne kreditnogo obyazatel'stva. Vestnik Chuvashskogo universiteta. 2018. № 3. S. 192–205. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Помазанов М.В. Моделирование потерь в случае дефолта в концепции минимизации остаточного риска // Управление финансовыми рисками. 2021. №. 3. С. 170–187.</mixed-citation><mixed-citation xml:lang="en">Pomazanov M.V. Modelirovanie poter' v sluchae defolta v kontseptsii minimizatsii ostatochnogo riska. Upravlenie finansovymi riskami. 2021. №. 3. S. 170–187. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Bakshi G., Gao X., Zhong Z. Decoding default risk: A review of modeling approaches, findings, and estimation methods // Annual Review of Financial Economics. 2022. Vol. 14. No. 1. P. 391–413.</mixed-citation><mixed-citation xml:lang="en">Bakshi G., Gao X., Zhong Z. Decoding default risk: A review of modeling approaches, findings, and estimation methods. Annual Review of Financial Economics. 2022. Vol. 14. No. 1. P. 391– 413.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Bellotti T., Crook J. Loss given default models incorporating macroeconomic variables for credit cards // International Journal of Forecasting. 2012. Vol. 28. No. 1. P. 171–182.</mixed-citation><mixed-citation xml:lang="en">Bellotti T., Crook J. Loss given default models incorporating macroeconomic variables for credit cards. International Journal of Forecasting. 2012. Vol. 28. No. 1. P. 171–182.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Caivano S.B.G. Econometric approach for Basel III Loss Given Default Estimation: from discount rate to final multivariate model. 2016.</mixed-citation><mixed-citation xml:lang="en">Caivano S.B.G. Econometric approach for Basel III Loss Given Default Estimation: from discount rate to final multivariate model. 2016.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Delgado-Vaquero D., Morales-Diaz J., Zamora-Ramírez C. IFRS 16 incremental borrowing rate: Comparability issues and a methodology proposal for loss given default adjustment // Accounting in Europe. 2022. Vol. 19. No. 2. P. 287–310.</mixed-citation><mixed-citation xml:lang="en">Delgado-Vaquero D., Morales-Diaz J., Zamora-Ramírez C. IFRS 16 incremental borrowing rate: Comparability issues and a methodology proposal for loss given default adjustment. Accounting in Europe. 2022. Vol. 19. No. 2. P. 287–310.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Fan M., Wu T.H., Zhao Q. Assessing the loss given default of bank loans using the Hybrid Algorithms Multi-Stage model // Systems. 2023. Vol. 11. No. 10. P. 505.</mixed-citation><mixed-citation xml:lang="en">Fan M., Wu T.H., Zhao Q. Assessing the loss given default of bank loans using the Hybrid Algorithms Multi-Stage model. Systems. 2023. Vol. 11. No. 10. P. 505.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Galow B., Georgescu O.M., Ponte Marques A. Loss-Given-Default and Macroeconomic Conditions // ECB Working Paper. 2024. No. 2024/2954.</mixed-citation><mixed-citation xml:lang="en">Galow B., Georgescu O.M., Ponte Marques A. Loss-Given-Default and Macroeconomic Conditions // ECB Working Paper. 2024. No. 2024/2954.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Gupton G.M. et al. LossCalc: Model for predicting loss given default (LGD). 2002.</mixed-citation><mixed-citation xml:lang="en">Gupton G.M. et al. LossCalc: Model for predicting loss given default (LGD). 2002.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Li A., Li Z., Bellotti A. Predicting loss given default of unsecured consumer loans with timevarying survival scores // Pacific-Basin Finance Journal. 2023. Vol. 78. P. 101949.</mixed-citation><mixed-citation xml:lang="en">Li A., Li Z., Bellotti A. Predicting loss given default of unsecured consumer loans with timevarying survival scores. Pacific-Basin Finance Journal. 2023. Vol. 78. P. 101949.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Li K. et al. Predicting loss given default using post-default information // Knowledge-Based Systems. 2021. Vol. 224. P. 107068.</mixed-citation><mixed-citation xml:lang="en">Li K. et al. Predicting loss given default using post-default information. Knowledge-Based Systems. 2021. Vol. 224. P. 107068.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Loterman G. et al. Benchmarking regression algorithms for loss given default modeling // International Journal of Forecasting. 2012. Vol. 28. No. 1. P. 161–170.</mixed-citation><mixed-citation xml:lang="en">Loterman G. et al. Benchmarking regression algorithms for loss given default modeling. International Journal of Forecasting. 2012. Vol. 28. No. 1. P. 161–170.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Loterman G. Predicting loss given default. Ghent University, 2013.</mixed-citation><mixed-citation xml:lang="en">Loterman G. Predicting loss given default. Ghent University, 2013.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Porretta P. et al. Credit risk management in bank. Impacts of IFRS 9 and Basel 3 // Risk Governance and Control: Financial Markets and Institutions. 2020. Vol. 10. No. 2. P. 29–44.</mixed-citation><mixed-citation xml:lang="en">Porretta P. et al. Credit risk management in bank. Impacts of IFRS 9 and Basel 3. Risk Governance and Control: Financial Markets and Institutions. 2020. Vol. 10. No. 2. P. 29–44.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Rantanen J. Modeling loss given default on unsecured consumer loans: case study of a Finnish financial institution. 2023.</mixed-citation><mixed-citation xml:lang="en">Rantanen J. Modeling loss given default on unsecured consumer loans: case study of a Finnish financial institution. 2023.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Schuermann T. What do we know about loss given default? 2004.</mixed-citation><mixed-citation xml:lang="en">Schuermann T. What do we know about loss given default? 2004.</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Статистические показатели банковского сектора Российской Федерации» // Банк России: официальный сайт: URL: https://www.cbr.ru/statistics/bank_sector/review/ (дата обращения: 07.04.2025).</mixed-citation><mixed-citation xml:lang="en">Statisticheskie pokazateli bankovskogo sektora Rossiyskoy Federatsii». Bank Rossii: ofitsial'nyy sayt: Available at: https://www.cbr.ru/statistics/bank_sector/review/ (accessed: 07.04.2025). (In Russ.).</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
