A Deep Neural Network (DNN) based classification model in application to loan default prediction
In this study, we applied a Deep Neural Networks (DNN) based classification model along with the conventional classification methods (Logistic Regression, Decision Tree, Naïve Bayes and Support Vector Machines) on a two distinct datasets containing characteristics of the loan clients in a medium-siz...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
General Association of Economists from Romania
2019-12-01
|
| Series: | Theoretical and Applied Economics |
| Subjects: | |
| Online Access: |
http://store.ectap.ro/articole/1421.pdf
|
| _version_ | 1818030299543502848 |
|---|---|
| author | Selçuk BAYRACI Orkun SUSUZ |
| author_facet | Selçuk BAYRACI Orkun SUSUZ |
| author_sort | Selçuk BAYRACI |
| collection | DOAJ |
| description | In this study, we applied a Deep Neural Networks (DNN) based classification model along
with the conventional classification methods (Logistic Regression, Decision Tree, Naïve Bayes and
Support Vector Machines) on a two distinct datasets containing characteristics of the loan clients
in a medium-sized Turkish commercial bank. Python programming language and libraries (Sklearn,
Tensorflow and Keras) have been used in data cleaning, data preparation, feature engineering and
model implementation processes. Our empirical findings document that the accuracy of the deep
learning classification model increases with the size of the dataset, implying that the deep learning
models might yield better results than regression-based models in more complex datasets. |
| first_indexed | 2024-12-10T05:33:23Z |
| format | Article |
| id | doaj.art-278dcf4faec04f29942d89f6c7f27200 |
| institution | Directory Open Access Journal |
| issn | 1841-8678 1844-0029 |
| language | English |
| last_indexed | 2024-12-10T05:33:23Z |
| publishDate | 2019-12-01 |
| publisher | General Association of Economists from Romania |
| record_format | Article |
| series | Theoretical and Applied Economics |
| spelling | doaj.art-278dcf4faec04f29942d89f6c7f272002022-12-22T02:00:28ZengGeneral Association of Economists from RomaniaTheoretical and Applied Economics1841-86781844-00292019-12-01XXVI4758418418678A Deep Neural Network (DNN) based classification model in application to loan default predictionSelçuk BAYRACI0Orkun SUSUZ1 R&D Center, C/S Information Technologies, Istanbul, Turkey R&D Center, C/S Information Technologies, Istanbul, Turkey In this study, we applied a Deep Neural Networks (DNN) based classification model along with the conventional classification methods (Logistic Regression, Decision Tree, Naïve Bayes and Support Vector Machines) on a two distinct datasets containing characteristics of the loan clients in a medium-sized Turkish commercial bank. Python programming language and libraries (Sklearn, Tensorflow and Keras) have been used in data cleaning, data preparation, feature engineering and model implementation processes. Our empirical findings document that the accuracy of the deep learning classification model increases with the size of the dataset, implying that the deep learning models might yield better results than regression-based models in more complex datasets. http://store.ectap.ro/articole/1421.pdf data analyticscredit scoringdeep learningrisk management |
| spellingShingle | Selçuk BAYRACI Orkun SUSUZ A Deep Neural Network (DNN) based classification model in application to loan default prediction Theoretical and Applied Economics data analytics credit scoring deep learning risk management |
| title | A Deep Neural Network (DNN) based classification model in application to loan default prediction |
| title_full | A Deep Neural Network (DNN) based classification model in application to loan default prediction |
| title_fullStr | A Deep Neural Network (DNN) based classification model in application to loan default prediction |
| title_full_unstemmed | A Deep Neural Network (DNN) based classification model in application to loan default prediction |
| title_short | A Deep Neural Network (DNN) based classification model in application to loan default prediction |
| title_sort | deep neural network dnn based classification model in application to loan default prediction |
| topic | data analytics credit scoring deep learning risk management |
| url |
http://store.ectap.ro/articole/1421.pdf
|
| work_keys_str_mv | AT selcukbayraci adeepneuralnetworkdnnbasedclassificationmodelinapplicationtoloandefaultprediction AT orkunsusuz adeepneuralnetworkdnnbasedclassificationmodelinapplicationtoloandefaultprediction AT selcukbayraci deepneuralnetworkdnnbasedclassificationmodelinapplicationtoloandefaultprediction AT orkunsusuz deepneuralnetworkdnnbasedclassificationmodelinapplicationtoloandefaultprediction |