TY - JOUR
T1 - Modeling credit scoring using neural network ensembles
AU - Tsai, Chih Fong
AU - Hung, Chihli
N1 - Publisher Copyright:
© Emerald Group Publishing Limited.
PY - 2014/7/29
Y1 - 2014/7/29
N2 - Purpose – Credit scoring is important for financial institutions in order to accurately predict the likelihood of business failure. Related studies have shown that machine learning techniques, such as neural networks, outperform many statistical approaches to solving this type of problem, and advanced machine learning techniques, such as classifier ensembles and hybrid classifiers, provide better prediction performance than single machine learning based classification techniques. However, it is not known which type of advanced classification technique performs better in terms of financial distress prediction. The paper aims to discuss these issues. Design/methodology/approach – This paper compares neural network ensembles and hybrid neural networks over three benchmarking credit scoring related data sets, which are Australian, German, and Japanese data sets. Findings – The experimental results show that hybrid neural networks and neural network ensembles outperform the single neural network. Although hybrid neural networks perform slightly better than neural network ensembles in terms of predication accuracy and errors with two of the data sets, there is no significant difference between the two types of prediction models. Originality/value – The originality of this paper is in comparing two types of advanced classification techniques, i.e. hybrid and ensemble learning techniques, in terms of financial distress prediction.
AB - Purpose – Credit scoring is important for financial institutions in order to accurately predict the likelihood of business failure. Related studies have shown that machine learning techniques, such as neural networks, outperform many statistical approaches to solving this type of problem, and advanced machine learning techniques, such as classifier ensembles and hybrid classifiers, provide better prediction performance than single machine learning based classification techniques. However, it is not known which type of advanced classification technique performs better in terms of financial distress prediction. The paper aims to discuss these issues. Design/methodology/approach – This paper compares neural network ensembles and hybrid neural networks over three benchmarking credit scoring related data sets, which are Australian, German, and Japanese data sets. Findings – The experimental results show that hybrid neural networks and neural network ensembles outperform the single neural network. Although hybrid neural networks perform slightly better than neural network ensembles in terms of predication accuracy and errors with two of the data sets, there is no significant difference between the two types of prediction models. Originality/value – The originality of this paper is in comparing two types of advanced classification techniques, i.e. hybrid and ensemble learning techniques, in terms of financial distress prediction.
KW - Bankruptcy prediction
KW - Classifier ensemble
KW - Credit scoring
KW - Hybrid classifier
KW - Machine learning
UR - http://www.scopus.com/inward/record.url?scp=84912050356&partnerID=8YFLogxK
U2 - 10.1108/K-01-2014-0016
DO - 10.1108/K-01-2014-0016
M3 - 期刊論文
AN - SCOPUS:84912050356
SN - 0368-492X
VL - 43
SP - 1114
EP - 1123
JO - Kybernetes
JF - Kybernetes
IS - 7
ER -