The evaluation of consumer loans using support vector machines

Li, Sheng-Tun; Shiue, Weissor; Huang, Meng-Huah

doi:10.1016/j.eswa.2005.07.041

Cited by 115 publications

(51 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ecological modeling [30], evaluation of consumer loans [31], studying credit rating systems [32], bank performance prediction [33], bankruptcy predictions [34], financial forecasting [35,36]. Some such applications in the construction engineering and management domains include slope reliability analysis [37], studying settlement of shallow foundations [38], supply chain demand forecasting [39], model induction [40], document classification for information systems [41] information integration and situation assessment [42] and conceptual cost estimates in construction projects [43].…”

Section: Introductionmentioning

confidence: 99%

A support vector machine model for contractor prequalification

Lam

Palaneeswaran

2009

Automation in Construction

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

A support vector machine model for contractor prequalification

Lam

Palaneeswaran

2009

Automation in Construction

View full text Add to dashboard Cite

“…The use of artificial intelligence techniques, imported from statistical learning theory, such as classification trees (Breiman et al, 1984) and neural networks (Desai et al, 1996;Malhotra & Malhotra, 2002) has become increasingly common in credit scoring systems. Statistical learning methods have received great attention in the past decade in finance-related research, for credit scoring and bankruptcy prediction (Li et al, 2006), bankruptcy classification (Lensberg et al, 2006), stress analysis (Gestel et al, 2006) and application for financing decisions and return (West et al, 2005;Xia et al, 2000). In addition, regression techniques (Lee & Chen, 2005) and clustering techniques (Wei et al, 2014) have also been adapted for the credit scoring problem.…”

Section: Bibliographic Reviewmentioning

confidence: 99%

Application of bayesian additive regression trees in the development of credit scoring models in Brazil

Filho

Artes

2018

Prod.

View full text Add to dashboard Cite

Paper aims: This paper presents a comparison of the performances of the Bayesian additive regression trees (BART), Random Forest (RF) and the logistic regression model (LRM) for the development of credit scoring models. Originality:It is not usual the use of BART methodology for the analysis of credit scoring data. The database was provided by Serasa-Experian with information regarding direct retail consumer credit operations. The use of credit bureau variables is not usual in academic papers.Research method: Several models were adjusted and their performances were compared by using regular methods. Main findings:The analysis confirms the superiority of the BART model over the LRM for the analyzed data. RF was superior to LRM only for the balanced sample. The best-adjusted BART model was superior to RF. Implications for theory and practice:The paper suggests that the use of BART or RF may bring better results for credit scoring modelling. KeywordsCredit. Machine learning. Logistic regression. BART. Random Forest.

show abstract

“…Machine learning techniques, which are developed in computer science literature, refer to a set of algorithms specifically designed to tackle computationally intensive pattern-recognition problems in extremely large datasets (Li et al, 2006;Bellotti and Crook, 2009;Khandani et al, 2010).…”

Section: Mutual Guarantee Institutionsmentioning

confidence: 99%

Operational drivers affecting credit risk of mutual guarantee institutions

Gai

Ielasi

2014

The Journal of Risk Finance

View full text Add to dashboard Cite

Purpose -The purpose of this paper is to investigate the drivers influencing the risk of default on mutual guaranteed loans. The authors aim to verify whether default is influenced by the specific business policies of mutual guarantee institutions (MGIs) and to recommend guidelines for directing their operating management. Design/methodology/approach -The authors analyse the guaranteed portfolios of 19 Italian MGIs and investigate the determinants of the defaulted positions at the end of June 2011. The sample consists of 167,777 guaranteed loans, of which 11,349 are in default. Using regression models, we identify the variables related to the business model of MGIs that are significantly associated with default on their positions. Findings -The defaulted positions of MGIs are significantly correlated with the type of issued guarantees. This condition should be considered in defining product and price policies. Practical implications -The authors identify some critical issues in the risk-taking processes of MGIs. The tested hypothesis highlights the opportunities for the optimisation of guaranteed loan portfolios, which is necessary for reducing the profitability/liquidity pressures of these financial institutions and enhancing their efficiency as instruments for mitigating the effects of credit rationing and promoting the revitalisation of small-and medium-sized enterprises. Originality/value -The results are based on an original and reserved dataset, which is not available in public financial statements or public statistics, but is collected directly from the MGIs that are part of the study.

show abstract

The evaluation of consumer loans using support vector machines

Cited by 115 publications

References 45 publications

A support vector machine model for contractor prequalification

A support vector machine model for contractor prequalification

Application of bayesian additive regression trees in the development of credit scoring models in Brazil

Operational drivers affecting credit risk of mutual guarantee institutions

Contact Info

Product

Resources

About