?
Consumer credit defaults in Russia: Credit scoring
P. 613–627.
Most of existing scoring systems are based on binary choice models with sample selection. This setting does not allow for up-to-date information about loans to be used and a lot of observations becomes lost. In the paper a model of binary choice with sample selection is extended to the case of many periods. This extension allows for defaults to be modeled for each period that solves the problem of lost observations. This setting also can be used to estimate the effectiveness of existing scoring system of a bank. The model is estimated using data granted by one of commercial banks of Nizhny Novgorod. Sample consists of observations from January 2009 to March 2012.
In book
Bratislava: Publishing House EKONOM, 2012.
Sofiia Dolgikh, Potanin B., Journal of Economic Studies 2026 Vol. 53 No. 1 P. 107–122
The purpose of this study is to empirically investigate gender differences in the returns to different levels of education and studying in STEM fields in Mexico. Specifically, we estimate the effects of education on employment and income. We use data about more than 4.5 m individuals in the year 2020 in Mexico to estimate the average ...
Added: January 31, 2025
Yuri A. Zelenkov, Elizaveta V. Lashkevich, Business Informatics 2024 Vol. 18 No. 3 P. 24–40
A counterfactual explanation is the generation for a particular sample of a set of instances that belong
to the opposite class but are as close as possible in the feature space to the factual being explained.
Existing algorithms that solve this problem are usually based on complicated models that require a large
amount of training data and significant ...
Added: October 13, 2024
Маракуева М. А., Финансы и бизнес 2021 Т. 17 № 4 С. 3–17
The article discusses the most common mistakes in banking practice when constructing scoring models for assessing the credit risk of individuals. For a detail description, we have selected the most significant ones from the point of view of generating retail profit. With the example of logistic regression we show how much the price of each ...
Added: April 8, 2023
Dolgikh S., Potanin B., Проблемы прогнозирования 2023 № 3 С. 146–157
The study is devoted to the analysis of dividend policy of Russian firms. This policy is considered as a two-step process. First, firm makes a decision whether to pay dividends. Second, it decides how much to pay. To estimate the influence of various factors on these decisions we have proposed a two-step estimation procedure that ...
Added: January 11, 2023
Kossova E. V., Potanin B., Прикладная эконометрика 2022 № 3(67) С. 121–143
We propose a two-step estimation procedure for multinomial endogenous switching model assuming joint normality of random errors. Simulated data analysis suggests that our method outperforms popular alternatives when independence of irrelevant alternatives (IIA) assumption is violated. We also apply our method to estimate marriage male premium. We have found statistical evidence that this premium is ...
Added: October 5, 2022
Anton Markov, Zinaida Seleznyova, Victor Lapshin, Journal of Finance and Data Science 2022 Vol. 8 P. 180–201
Credit risk is the most significant risk by impact for any bank and financial institution.
Accurate credit risk assessment affects an organisation’s balance sheet and income
statement, since credit risk strategy determines pricing, and might even influence
seemingly unrelated domains, e.g. marketing, and decision-making. This article aims at
providing a systemic review of the most recent (2016–2021) articles, identifying ...
Added: July 28, 2022
Seleznyova Z., Journal of Corporate Finance Research 2021 Vol. 15 No. 3 P. 5–13
Researchers have been improving credit scoring models for decades. The reason for this is following: an increase in the predictive ability of scoring even by small values can save a financial institution from a significant losses. As a result, many researchers have conclude that ensembles of classifiers or aggregated scorings have greater performance. However, ensembles ...
Added: August 25, 2021
Тихонов Р. Ю., Masyutin A., Анпилогов В. В., Деньги и кредит 2021 № 2 С. 76–95
Model risk in credit scoring can be understood as the bank’s losses associated with a model quality deterioration. Deterioration in model quality entails an incorrect assessment of the creditworthiness of borrowers and leads to an increase in potentially defaulting applications in the loan portfolio, as the bank relies on the model performance when making lending ...
Added: July 8, 2021
Kossova E. V., Куприянова Л. А., Potanin B., Прикладная эконометрика 2020 Т. 57 С. 119–139
В статье рассматриваются параметрические и полупараметрические методы коррекции смещения отбора и проводится их сопоставление в случае двумерного механизма отбора наблюдений. Сравнение осуществляется на симулированных данных. Исследуется точность оценок параметрических и полупараметрических методов при распределениях случайных ошибок, существенно отличающихся от нормального несимметричностью, наличием «тяжелых хвостов» или бимодальностью. Делается вывод о высокой точности параметрических методов даже при ...
Added: March 19, 2020
Potanin B., Studies on Russian Economic Development, United States of America, Pleiades Publishing, Ltd 2019 Vol. 30 No. 3 P. 319–326
This paper proposes a new method for estimating the effect of education on an employee’s wage:
with the help of the generalized Heckman model with switching. Application of this method makes it possible
to avoid the selection bias due to the endogenous accounting for nonrandom consideration of individuals
both as employed and having higher education. This model makes ...
Added: May 8, 2019
Filipenkov N., Siddiqi N., Akhadov A., Risk and Compliance 2019 No. JAN-MAR P. 3–14
The New Age of Credit Scoring and Decisioning ...
Added: January 16, 2019
Kossova E. V., Potanin B., Прикладная эконометрика 2018 Т. 50 С. 114–143
The article is devoted to simultaneous estimation of one continuous and various binary equations under assumption of disturbances joint normality. It generalizes Heckman selection and switch-probit models to multivariate case. Following Heckman’s univariate model implementation both two step and maximum likelihood procedures are provided. In order to test model performance and correctness we execute analysis ...
Added: July 3, 2018
Romanyuk K., Экономические науки 2015 № 125 С. 109–116
Рассмотрен вопрос информативности оценки кредитоспособности физических лиц, получаемой банком при использовании методов кредитного скоринга для принятия управленческих решений, например дифференциации цены кредита. Предложен метод кредитного скоринга с оценкой кредитоспособности по непрерывной шкале. Вычислена оценка кредитоспособности предложенным методом по частной информации физических лиц. Показано, как по данной оценке банк может принять решение о дифференциации цены кредита ...
Added: November 20, 2017
Romanyuk K., , in: Proceedings of the 2016 Future Technologies Conference.: IEEE, 2017. P. 254–259.
In the given paper the aggregated randomized indices method is modified for credit scoring. Coefficients of the modified method can be calibrated on a massive training set in comparison with a standard version. Different credit scoring models are analyzed, i.e. with a binary scale and a continuous one. The Monte Carlo method is applied to ...
Added: November 20, 2017
Romanyuk K., , in: SAI Intelligent Systems Conference 2015 (IntelliSys 2015).: L.: IEEE, 2015. P. 105–111.
Loan provision is associated with a credit risk. Banks assess the creditworthiness of potential borrowers to lower a credit risk. Creditworthiness assessment is carried out by credit scoring methods. Most of these methods classify individuals into two categories: `good' or `bad' creditworthiness. Decision support system for loan granting based on these methods fail to differentiate ...
Added: November 19, 2017