Micro Credit Risk Metrics: A Comprehensive Review

Çelik, Şaban

doi:10.1002/isaf.1344

Cited by 11 publications

(7 citation statements)

References 124 publications

(77 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As a result, banking organizations make use of various strategies to manage credit risks. Moreover, credit risk analysis has become an important tool for financial risk management (Celik, 2013). The increase in defaulter's rate in the credit risk dataset which is not found to be reliable provides motivation to undertake the current study (Chen et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

Biogeography based optimization for mining rules to assess credit risk

Giri

Dehuri

et al. 2021

Intell Sys Acc Fin Mgmt

View full text Add to dashboard Cite

Financial institutions, by and large, rely on the use of machine learning techniques to improve the classic credit risk assessment model for reduction of costs, delivery of faster decisions, guaranteed credit collections, and risk mitigations. As such, several data mining and machine learning approaches have been developed for computation of credit scores over the last few decades. Moreover, the existing rule-based classification algorithms tend to generate a number of rules with a large number of conditions in the antecedent part. However, these algorithms fail to demonstrate high predictive accuracy while balancing coverage and simplicity. Thus, it becomes quite a challenging task for the researchers to generate an optimal rule set with high predictive accuracy. In this paper, we present an effective rule based classification technique for the prediction of credit risk using a novel Biogeography Based Optimization (BBO) method. The novel BBO in the context of rule mining is named as locally and globally tuned biogeography based rule-miner (LGBBO-RuleMiner). This is applied for discovering optimal rule set with high predictive accuracy from the dataset containing both the categorical and continuous attributes. The performance of the proposed algorithm is compared against a variety of rule-miners such as OneR (1R), PART, JRip, Decision Table, Conjunctive Rule, J48, and Random Tree, along with some meta-heuristic based rule mining techniques by considering two credit risk datasets obtained from University of California, Irvine (UCI) repository. It is found from the comparative study that the proposed rule miner in ten independent runs of tenfold cross validation outperforms all of the aforesaid algorithms in terms of predictive accuracy, coverage, and simplicity.

show abstract

Section: Introductionmentioning

confidence: 99%

Biogeography based optimization for mining rules to assess credit risk

Giri

Dehuri

et al. 2021

Intell Sys Acc Fin Mgmt

View full text Add to dashboard Cite

show abstract

“…Although formal modeling of credit risk first came to prominence in the 1960s, the importance of evaluating firm creditability dates back to the earliest days of market trading (Caouette et al, 1998). Although inspection of academic literature indicates that quantitative and qualitative research in the field of credit risk modeling tended to diverge in the late 1960s, the basic purpose of both strands of inquiry has remained the same, that is, evaluating firm credit worthiness and default probability (Çelik, 2013). What has changed, however, in recent years is the recognition of credit risk modeling as a critical element in financial institutions' risk management processes (Lopez & Saidenberg, 2000).…”

Section: Introductionmentioning

confidence: 99%

Firm dynamics and bankruptcy processes: A new theoretical model

Çelik

Aktan

Burton

2021

Journal of Forecasting

Self Cite

View full text Add to dashboard Cite

This paper introduces a theoretical model that relates firm dynamics to bankruptcy processes on both univariate and multivariate bases. The distinctiveness of the study lies in the estimation of default using a framework where firm dynamics are linked to the bankruptcy process itself. The structure builds on theoretical relations among the constructs viewed from a perspective sufficiently wide to demonstrate value addition and dilution. The univariate‐based estimation results indicate that the variables determined via the model successfully differentiate distressed firms from non‐distressed and other firms, although the evidence from the multivariate analysis facilitate a 90%+ correct distressed/non‐distressed classification rate for both 1‐ and 2‐year periods. The findings provide a road map for selecting the most appropriate default prediction variables and identifying the role of each in the prediction process. The prediction accuracy of the model does not depend solely upon statistical techniques but also reflects each variable's theoretical underpinning. The model is shown to be useful for firm rating in general and credit approval decisions in particular.

show abstract

“…The purpose of the current work is to study the effectiveness of various ensemble learning and classification systems in the context of financial data classification; especially in corporate bankruptcy prediction and credit scoring which have previously received a large attention (Abdou & Poiton, ; Çelik, ; Davalos, Leng, Feroz, & Cao, ; Figini, Savona, & Vezzoli, ; Lahmiri, ; Lahmiri, ; Lahmiri & Bekiros, ; Lahmiri & Gagnon, ; Mendes, Cardoso, Mário, Martinez, & Ferreira, ; Peat & Jones, ; Pendharkar, ; Quek, Zhou, & Lee, ; Savona & Vezzoli, ; Sun, ; Trinkle & Baldwin, ).…”

Section: Introductionmentioning

confidence: 99%

Performance assessment of ensemble learning systems in financial data classification

Lahmiri

Bekiros

Giakoumelou

et al. 2020

Intell Sys Acc Fin Mgmt

View full text Add to dashboard Cite

Summary Financial data classification plays an important role in investment and banking industry with the purpose to control default risk, improve cash and select the best customers. Ensemble learning and classification systems are becoming gradually more applied to classify financial data where outputs from different classification systems are combined. The objective of this research is to assess the relative performance of existing state‐of‐the‐art ensemble learning and classification systems with applications to corporate bankruptcy prediction and credit scoring. The considered ensemble systems include AdaBoost, LogitBoost, RUSBoost, subspace, and bagging ensemble system. The experimental results from three datasets: one is composed of quantitative attributes, one encompasses qualitative data, and another one combines both quantitative and qualitative attributes. By using ten‐fold cross‐validation method, the experimental results show that AdaBoost is effective in terms of low classification error, limited complexity, and short time processing of the data. In addition, the experimental results show that ensemble classification systems outperform existing models that were recently validated on the same databases. Therefore, ensemble classification system can be employed to increase the reliability and consistency of financial data classification task.

show abstract

Micro Credit Risk Metrics: A Comprehensive Review

Cited by 11 publications

References 124 publications

Biogeography based optimization for mining rules to assess credit risk

Biogeography based optimization for mining rules to assess credit risk

Firm dynamics and bankruptcy processes: A new theoretical model

Performance assessment of ensemble learning systems in financial data classification

Contact Info

Product

Resources

About