Tezislər / Theses



Yüklə 17,55 Mb.
Pdf görüntüsü
səhifə114/493
tarix02.10.2023
ölçüsü17,55 Mb.
#151572
1   ...   110   111   112   113   114   115   116   117   ...   493
BHOS Tezisler 2022 17x24sm

THE 3
rd
 INTERNATIONAL SCIENTIFIC CONFERENCES OF STUDENTS AND YOUNG RESEARCHERS 
dedicated to the 99
th
anniversary of the National Leader of Azerbaijan Heydar Aliyev
124
Figure 1.
Volatility Prediction - SVR
Figure 2. 
Volatility Prediction – Neural Network 
Credit risk is the risk that arises when a borrower is not able to honor 
their debt. In other words, when a borrower defaults, they fail to pay back 
their debt, which causes losses for financial institutions. The two most active 
research topics for credit risk management are bankruptcy/default prediction 
and credit scoring [3]. Credit scoring generally refers to the risk classification 
of retail borrowers (which includes personal loans or mortgages) whereas 
bankruptcy prediction generally refers to the prediction of bankruptcy of an 
institutional borrower (for example, a small business). The group of 


THE 3
rd
 INTERNATIONAL SCIENTIFIC CONFERENCES OF STUDENTS AND YOUNG RESEARCHERS 
dedicated to the 99
th
anniversary of the National Leader of Azerbaijan Heydar Aliyev
125
classifiers used for credit risk evaluation can be categorised into two families: 
Supervised Learning Methods: Two mostly used single classifiers for this 
task are Support Vector Machines (SVM), Random Forest and Neural 
Networks. Unsupervised Learning Methods: Clustering methods can also be 
used to identify the risk of bankruptcy or credit default. These methods can 
help to identify groups of loan applicants/ enterprises with similar 
characteristics. A cluster-based dynamic scoring model can achieve better 
scoring accuracy by implementing different classifiers for different clusters. 
In this paper, core machine learning models, namely SVC, random forest, 
and NNs with deep learning were employed, and the performance of all 
models was compared. (ROC is a probability curve and AUC represents the 
degree or measure of separability. It tells how much the model is capable of 
distinguishing between classes.)
The ROC AUC score of SVC 
for 
first cluster
0.5000 
The ROC AUC score of RF 
for 
first cluster
0.5906 
The ROC AUC score of NN 
for 
first cluster
0.6155 

Yüklə 17,55 Mb.

Dostları ilə paylaş:
1   ...   110   111   112   113   114   115   116   117   ...   493




Verilənlər bazası müəlliflik hüququ ilə müdafiə olunur ©azkurs.org 2024
rəhbərliyinə müraciət

gir | qeydiyyatdan keç
    Ana səhifə


yükləyin