Predicting corporate financial sustainability using Novel Business Analytics

Kyoung Jae Kim, Kichun Lee, Hyunchul Ahn

Research output: Contribution to journalArticle

Abstract

Measuring and managing the financial sustainability of the borrowers is crucial to financial institutions for their risk management. As a result, building an effective corporate financial distress prediction model has been an important research topic for a long time. Recently, researchers are exerting themselves to improve the accuracy of financial distress prediction models by applying various business analytics approaches including statistical and artificial intelligence methods. Among them, support vector machines (SVMs) are becoming popular. SVMs require only small training samples and have little possibility of overfitting if model parameters are properly tuned. Nonetheless, SVMs generally show high prediction accuracy since it can deal with complex nonlinear patterns. Despite of these advantages, SVMs are often criticized because their architectural factors are determined by heuristics, such as the parameters of a kernel function and the subsets of appropriate features and instances. In this study, we propose globally optimized SVMs, denoted by GOSVM, a novel hybrid SVM model designed to optimize feature selection, instance selection, and kernel parameters altogether. This study introduces genetic algorithm (GA) in order to simultaneously optimize multiple heterogeneous design factors of SVMs. Our study applies the proposed model to the real-world case for predicting financial distress. Experiments show that the proposed model significantly improves the prediction accuracy of conventional SVMs.

Original languageEnglish
Article number64
JournalSustainability (Switzerland)
Volume11
Issue number1
DOIs
StatePublished - 2018 Dec 22

Fingerprint

Support vector machines
Sustainable development
sustainability
Industry
prediction
support vector machine
artificial intelligence
Risk management
Set theory
heuristics
risk management
genetic algorithm
Artificial intelligence
Feature extraction
Genetic algorithms
experiment
parameter
Experiments

Keywords

  • Feature selection
  • Financial distress prediction
  • Genetic algorithm
  • Instance selection
  • Support vector machines

Cite this

@article{cbf9d1b3ec9642338d412ab32e2a3031,
title = "Predicting corporate financial sustainability using Novel Business Analytics",
abstract = "Measuring and managing the financial sustainability of the borrowers is crucial to financial institutions for their risk management. As a result, building an effective corporate financial distress prediction model has been an important research topic for a long time. Recently, researchers are exerting themselves to improve the accuracy of financial distress prediction models by applying various business analytics approaches including statistical and artificial intelligence methods. Among them, support vector machines (SVMs) are becoming popular. SVMs require only small training samples and have little possibility of overfitting if model parameters are properly tuned. Nonetheless, SVMs generally show high prediction accuracy since it can deal with complex nonlinear patterns. Despite of these advantages, SVMs are often criticized because their architectural factors are determined by heuristics, such as the parameters of a kernel function and the subsets of appropriate features and instances. In this study, we propose globally optimized SVMs, denoted by GOSVM, a novel hybrid SVM model designed to optimize feature selection, instance selection, and kernel parameters altogether. This study introduces genetic algorithm (GA) in order to simultaneously optimize multiple heterogeneous design factors of SVMs. Our study applies the proposed model to the real-world case for predicting financial distress. Experiments show that the proposed model significantly improves the prediction accuracy of conventional SVMs.",
keywords = "Feature selection, Financial distress prediction, Genetic algorithm, Instance selection, Support vector machines",
author = "Kim, {Kyoung Jae} and Kichun Lee and Hyunchul Ahn",
year = "2018",
month = "12",
day = "22",
doi = "10.3390/su11010064",
language = "English",
volume = "11",
journal = "Sustainability (Switzerland)",
issn = "2071-1050",
number = "1",

}

Predicting corporate financial sustainability using Novel Business Analytics. / Kim, Kyoung Jae; Lee, Kichun; Ahn, Hyunchul.

In: Sustainability (Switzerland), Vol. 11, No. 1, 64, 22.12.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Predicting corporate financial sustainability using Novel Business Analytics

AU - Kim, Kyoung Jae

AU - Lee, Kichun

AU - Ahn, Hyunchul

PY - 2018/12/22

Y1 - 2018/12/22

N2 - Measuring and managing the financial sustainability of the borrowers is crucial to financial institutions for their risk management. As a result, building an effective corporate financial distress prediction model has been an important research topic for a long time. Recently, researchers are exerting themselves to improve the accuracy of financial distress prediction models by applying various business analytics approaches including statistical and artificial intelligence methods. Among them, support vector machines (SVMs) are becoming popular. SVMs require only small training samples and have little possibility of overfitting if model parameters are properly tuned. Nonetheless, SVMs generally show high prediction accuracy since it can deal with complex nonlinear patterns. Despite of these advantages, SVMs are often criticized because their architectural factors are determined by heuristics, such as the parameters of a kernel function and the subsets of appropriate features and instances. In this study, we propose globally optimized SVMs, denoted by GOSVM, a novel hybrid SVM model designed to optimize feature selection, instance selection, and kernel parameters altogether. This study introduces genetic algorithm (GA) in order to simultaneously optimize multiple heterogeneous design factors of SVMs. Our study applies the proposed model to the real-world case for predicting financial distress. Experiments show that the proposed model significantly improves the prediction accuracy of conventional SVMs.

AB - Measuring and managing the financial sustainability of the borrowers is crucial to financial institutions for their risk management. As a result, building an effective corporate financial distress prediction model has been an important research topic for a long time. Recently, researchers are exerting themselves to improve the accuracy of financial distress prediction models by applying various business analytics approaches including statistical and artificial intelligence methods. Among them, support vector machines (SVMs) are becoming popular. SVMs require only small training samples and have little possibility of overfitting if model parameters are properly tuned. Nonetheless, SVMs generally show high prediction accuracy since it can deal with complex nonlinear patterns. Despite of these advantages, SVMs are often criticized because their architectural factors are determined by heuristics, such as the parameters of a kernel function and the subsets of appropriate features and instances. In this study, we propose globally optimized SVMs, denoted by GOSVM, a novel hybrid SVM model designed to optimize feature selection, instance selection, and kernel parameters altogether. This study introduces genetic algorithm (GA) in order to simultaneously optimize multiple heterogeneous design factors of SVMs. Our study applies the proposed model to the real-world case for predicting financial distress. Experiments show that the proposed model significantly improves the prediction accuracy of conventional SVMs.

KW - Feature selection

KW - Financial distress prediction

KW - Genetic algorithm

KW - Instance selection

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=85059154081&partnerID=8YFLogxK

U2 - 10.3390/su11010064

DO - 10.3390/su11010064

M3 - Article

AN - SCOPUS:85059154081

VL - 11

JO - Sustainability (Switzerland)

JF - Sustainability (Switzerland)

SN - 2071-1050

IS - 1

M1 - 64

ER -