Default Risk Prediction Based on Support Vector Machine and Logit Support Vector Machine
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25410%2F23%3A39920854" target="_blank" >RIV/00216275:25410/23:39920854 - isvavai.cz</a>
Result on the web
<a href="https://link.springer.com/chapter/10.1007/978-3-031-18552-6_6" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-18552-6_6</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-18552-6_6" target="_blank" >10.1007/978-3-031-18552-6_6</a>
Alternative languages
Result language
angličtina
Original language name
Default Risk Prediction Based on Support Vector Machine and Logit Support Vector Machine
Original language description
This chapter aims to predict the credit customer default risk. We propose a machine learning algorithm such as Support Vector Machine and a hybrid default risk prediction model such as Logistic Regression and Support Vector Machine being known as LogitSVM (LSVM) to access the credit default risk. We apply three real-world credit databases to validate the probability and value of the proposed risk appraisal hybrid approaches. This chapter uses Type-I Error, Type-II Error, and Root Mean Squared Error (RMSE) to evaluate the performance of the algorithms. Empirical findings show that hybrid model experimentation (LogitSVM) maximizes overall accuracy and minimizes RMSE, Type-I error, and Type-II error. This study is useful for stakeholders to develop a wide variety of approaches to predict risk of default of the credit customer.
Czech name
—
Czech description
—
Classification
Type
C - Chapter in a specialist book
CEP classification
—
OECD FORD branch
50206 - Finance
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Book/collection name
Novel financial applications of machine learning and deep learning : algorithms, product modeling, and applications
ISBN
978-3-031-18551-9
Number of pages of the result
14
Pages from-to
93-106
Number of pages of the book
231
Publisher name
Springer Nature Switzerland AG
Place of publication
Cham
UT code for WoS chapter
—