Donetsk National Technical University
Please use this identifier to cite or link to this item:
https://ea.donntu.edu.ua/jspui/handle/123456789/26468| Title: | Использование инструментария Data mining в управлении кредитными рисками |
| Authors: | Слепнева, Л.Д. Кривоберец, В.Б. |
| Keywords: | КРЕДИТНЫЙ РИСК, DATA-MINING, КРЕДИТОСПОСОБНОСТЬ, ЛОГИТ-МОДЕЛЬ CREDIT RISK, DATA MINING, CREDITWORTHINESS, LOGIT |
| Issue Date: | 2013 |
| Publisher: | Науково-практичний журнал «Економіка промисловості». – Донецк: ІЕП НАН України, 2013, № 1-2 (61-62), с. 303 – 312. |
| Abstract: | Обоснована необходимость построения модели с бинарной зависимой переменной для оценивания и прогнозирования кредитоспособности физических лиц – потенциальных заемщиков банка – с целью снижения уровня кредитного риска. Выполнено оценивание параметров logit-модели методом максимального правдоподобия с использованием пакета Statistica. Предложены процедуры оценивания качества модели |
| Description: | Credit activity determines the effectiveness of the functioning of the bank, as a significant part of the bank’s income comes from lending operations. This lending is always associated with risk. NPLs could lead to the bankruptcy of the bank and this may lead to the bankruptcy of its related companies. Therefore, the problem of effective management of credit risk is a necessary part of the strategy and tactics to survival and growth for every commercial bank. The purpose of this work - show usage of advanced mathematical methods and IT-technologies to assess the creditworthiness of individuals - potential borrowers. This article proves the necessity of building a model with a binary dependent variable to estimate and predict creditworthiness for potential borrowers - in order to reduce the level of credit risk. Research was performed in accordance to the materials of the retail lending of a bank and on this basis was built logistic model diagnostics creditworthiness of a potential client. In this model the dependent variable is a binary variable reflecting the status of the client. The dependent variable will be zero if the loan was problematic, and the value of 1, otherwise. The value that ranges from 0 to 1 would indicate the probability of loan default or other problems with returning the debt. Parameter estimation was made with help of logit-model’s that uses maximum likelihood method. In this research was used “Statistica” - software package for data analysis, data management, statistics, data mining, and data visualization procedures. Also proposed the procedures of estimating the quality of the model. With this model, is possible to determine the percentage of trustworthy borrowers and the percentage of unscrupulous borrowers. |
| URI: | http://ea.donntu.edu.ua/handle/123456789/26468 |
| Appears in Collections: | Наукові статті кафедри фінансів та банківської справи |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| статья.pdf | 668,67 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.