Search

Abstract Commercial banks are required to explain the credit evaluation results to their customers. Therefore, banks attempt to improve the performance of their credit scoring models while ensuring the interpretability of the results. However, there is a tradeoff between the logistic regression model and machine learning-based techniques regarding interpretability and model performance because machine learning-based models are a black box. To deal with the tradeoff, in this study, we present a two-stage logistic regression method based on the Bayesian approach. In the first stage, we generate the derivative variables by linearly combining the original features with their explanatory powers based on the Bayesian inference. The second stage involves developing a credit scoring model through logistic regression using these derivative variables. Through this process, the explanatory power of a large number of original features can be utilized for default prediction, and the use of logistic regression maintains the model's interpretability. In the empirical analysis, the independent sample t-test reveals that our proposed approach significantly improves the model’s performance compared to that based on the conventional single-stage approach, i.e., the baseline model. The Kolmogorov–Smirnov statistics show a 3.42 percentage points (%p) increase, and the area under the receiver operating characteristic shows a 2.61%p increase. Given that our two-stage modeling approach has the advantages of interpretability and enhanced performance of the credit scoring model, our proposed method is essential for those in charge of banking who must explain credit evaluation results and find ways to improve the performance of credit scoring models.

Small and Medium Enterprises (SMEs) have played a significant role in the development of any economy. However, easy access to finance from financial institutions is a prime challenge for them. Similarly, financial institutions also face difficulties while selecting the potential SMEs for granting credit. The SMEs are often seen as unorganized in terms of financial data as compared to large corporate sectors. The credit risk assessment based on unorganized financial data is a challenge for financial institutions. Most of the existing models used regression to predict the possibility of default of SMEs. However, the regression model may not perform well with limited data points and missing data. The problem can be solved by using a multi criteria decision‐making (MCDM) model. Credit scoring, especially addressing the SMEs, has been infrequently reported in the archived literature. To fill the gaps of literature, the present study proposes a credit scoring model applying the hybrid analytic hierarchy process‐technique for order of preference by similarity to ideal solution (AHP‐TOPSIS) technique. The study has been carried out in three stages. In the first stage, credit rating criteria and sub‐criteria have been identified from the literature review and taking opinions from experts. In the second stage, weights of criteria and sub‐criteria have been calculated using AHP. Finally, in the third stage, weights calculated by AHP have been used in TOPSIS to determine the credit score. The effectiveness of the proposed model has been illustrated through a case study. Further, the results of the proposed model are compared with the commercially available ratings. The proposed model may be a low‐cost alternative for financial institutions for credit scoring of SMEs. Further, the model has the advantage of customization as per the needs of the financial institutions. The suggested model can help the managers to identify the potential SMEs for granting credit. [ABSTRACT FROM AUTHOR]

Commercial banks are required to explain the credit evaluation results to their customers. Therefore, banks attempt to improve the performance of their credit scoring models while ensuring the interpretability of the results. However, there is a tradeoff between the logistic regression model and machine learning-based techniques regarding interpretability and model performance because machine learning-based models are a black box. To deal with the tradeoff, in this study, we present a two-stage logistic regression method based on the Bayesian approach. In the first stage, we generate the derivative variables by linearly combining the original features with their explanatory powers based on the Bayesian inference. The second stage involves developing a credit scoring model through logistic regression using these derivative variables. Through this process, the explanatory power of a large number of original features can be utilized for default prediction, and the use of logistic regression maintains the model's interpretability. In the empirical analysis, the independent sample t-test reveals that our proposed approach significantly improves the model's performance compared to that based on the conventional single-stage approach, i.e., the baseline model. The Kolmogorov–Smirnov statistics show a 3.42 percentage points (%p) increase, and the area under the receiver operating characteristic shows a 2.61%p increase. Given that our two-stage modeling approach has the advantages of interpretability and enhanced performance of the credit scoring model, our proposed method is essential for those in charge of banking who must explain credit evaluation results and find ways to improve the performance of credit scoring models. [ABSTRACT FROM AUTHOR]

Abstract Small- and medium-sized enterprises (SMEs) have a crucial influence on the economic development of every nation, but access to formal finance remains a barrier. Similarly, financial institutions encounter challenges in the assessment of SMEs’ creditworthiness for the provision of financing. Financial institutions employ credit scoring models to identify potential borrowers and to determine loan pricing and collateral requirements. SMEs are perceived as unorganized in terms of financial data management compared to large corporations, making the assessment of credit risk based on inadequate financial data a cause for financial institutions’ concern. The majority of existing models are data-driven and have faced criticism for failing to meet their assumptions. To address the issue of limited financial record keeping, this study developed and validated a system to predict SMEs’ credit risk by introducing a multicriteria credit scoring model. The model was constructed using a hybrid best–worst method (BWM) and the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). Initially, the BWM determines the weight criteria, and TOPSIS is applied to score SMEs. A real-life case study was examined to demonstrate the effectiveness of the proposed model, and a sensitivity analysis varying the weight of the criteria was performed to assess robustness against unpredictable financial situations. The findings indicated that SMEs’ credit history, cash liquidity, and repayment period are the most crucial factors in lending, followed by return on capital, financial flexibility, and integrity. The proposed credit scoring model outperformed the existing commercial model in terms of its accuracy in predicting defaults. This model could assist financial institutions, providing a simple means for identifying potential SMEs to grant credit, and advance further research using alternative approaches.

Credit scoring models have been widely used in traditional financial institutions for many years. Using these models in P2P Lending have limitations. First, the credit data of P2P usually contains dense numerical features and sparse categorical features. Second, the existing credit scoring models are generally cannot be updated online. The loan transaction of P2P lending is very frequent and the new data leads data distribution to change. A credit scoring model without considering data update causes a serious deviation or even failure in subsequent credit assessment. In this paper, we propose a new online integrated credit scoring model (OICSM) for P2P Lending. OICSM integrates gradient boosting decision tree and neural network to make the credit scoring model can handle two types of features more effectively and update online. Offline and online experiments based on real and representative credit datasets are conducted to verify the effectiveness and superiority of the proposed model. Experimental results demonstrate that OICSM can significantly improve performance due to its advantage in deep learning over two features, and it can further correct model deterioration due to its online dynamic update capability.

Small- and medium-sized enterprises (SMEs) have a crucial influence on the economic development of every nation, but access to formal finance remains a barrier. Similarly, financial institutions encounter challenges in the assessment of SMEs' creditworthiness for the provision of financing. Financial institutions employ credit scoring models to identify potential borrowers and to determine loan pricing and collateral requirements. SMEs are perceived as unorganized in terms of financial data management compared to large corporations, making the assessment of credit risk based on inadequate financial data a cause for financial institutions' concern. The majority of existing models are data-driven and have faced criticism for failing to meet their assumptions. To address the issue of limited financial record keeping, this study developed and validated a system to predict SMEs' credit risk by introducing a multicriteria credit scoring model. The model was constructed using a hybrid best–worst method (BWM) and the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). Initially, the BWM determines the weight criteria, and TOPSIS is applied to score SMEs. A real-life case study was examined to demonstrate the effectiveness of the proposed model, and a sensitivity analysis varying the weight of the criteria was performed to assess robustness against unpredictable financial situations. The findings indicated that SMEs' credit history, cash liquidity, and repayment period are the most crucial factors in lending, followed by return on capital, financial flexibility, and integrity. The proposed credit scoring model outperformed the existing commercial model in terms of its accuracy in predicting defaults. This model could assist financial institutions, providing a simple means for identifying potential SMEs to grant credit, and advance further research using alternative approaches. [ABSTRACT FROM AUTHOR]

Credit scoring model (CSM) is a risk management tool that assesses the credit worthiness of a customer borrower by estimating her probability of default based on historical data. Traditionally CSM is built by logit model or decision tree algorithm in financial companies, and in recent studies CSM has been integrated with machine learning algorithms such as random forest and gradient boosting to process a number of complex attributes of customer borrowers. On the other hand, CSM has been facing a critical challenge ‐ the domain adaptation of customer borrowers. For domain adaptation problem, transfer learning techniques are generally utilized, however, it is quite difficult to execute precise predictions for unknown domain datasets in CSM because the distributions of labels could be different depending on the characteristics of domains. Therefore, there is no appropriate transfer learning method to solve domain adaptation problem in credit scoring. In this paper we propose a comprehensive transfer learning framework using Bayesian network to extract useful knowledge based on probability distributions to predict probability of default of customer borrowers more precisely than existing machine learning and transfer learning methods. Experimental results showed the proposed method performed over the existing machine learning and transfer learning methods for accuracy of predictions. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

To manage credit risk, commercial banks use various scoring methodologies to evaluate the financial performance of client firms. In this study, a parametric model (Logistic regression) and a nonparametric model (Classification and regression tree) were used in order to create credit scoring models. These models were designed using 13 financial ratios as independent variables. The data were collected from 282 companies and then were compared in term of accuracy rate. The two models specified the important variables which affect the classification and credit risk. The obtained results revealed that the accuracy rates of nonparametric methods were competitive with the parametric methods.

Loan default is a serious problem in banking industries. Banking systems have strong processes in place for identification of customers with poor credit risk scores; however, most of the credit scoring models need to be constantly updated with newer variables and statistical techniques for improved accuracy. While totally eliminating default is almost impossible, loan risk teams, however, minimize the rate of default, thereby protecting banks from the adverse effects of loan default. Credit scoring models have used logistic regression and linear discriminant analysis for identification of potential defaulters. Newer and contemporary machine learning techniques have the ability to outperform classic old age techniques. This article aims to conduct empirical analysis on publically available bank loan dataset to study banking loan default using decision tree as the base learner and comparing it with ensemble tree learning techniques such as bagging, boosting, and random forests. The results of the empirical analysis suggest that the gradient boosting model outperforms the base decision tree learner, indicating that ensemble model works better than individual models. The study recommends that the risk team should adopt newer contemporary techniques to achieve better accuracy resulting in effective loan recovery strategies. [ABSTRACT FROM AUTHOR]

Credit scoring model is one of common tools for commercial banks to manage credit risks. In this paper, we use a public dataset from UCI machine learning repository and construct credit scoring models based on Group Lasso Logistic Regression, where the tuning parameters λ are selected by the Akaike Information Criterion(AIC), Bayesian Information Criterion(BIC) and Cross Validation prediction errors respectively. The experimental results show that the Group Lasso method is better than backward elimination in both interpretability and prediction accuracy. [ABSTRACT FROM AUTHOR]

Various types of government credit guarantee programs exist for small- and medium-sized enterprises (SMEs). The SMEs guaranteed by these programs can resolve their financial difficulties by obtaining loans from banks or being included in a pool for the issuance of primary collateralized bond obligations. However, the loan default rate for these supported firms is high owing to their moral hazard, which can be associated with unethical behavior in the accounting process. Since the stakeholders of credit guarantee programs initiated by the government include not only lenders and borrowers, but also taxpayers, the default risk of moral hazard must be minimized. Thus, an additional evaluation step is required to deal with accounting ethics, which has not thus far been considered in the literature. In this study, we propose an accounting ethics-based credit scoring model as a complementary approach, which can be used to select suitable borrowers. The proposed model is expected to reduce the default rate resulting from the moral hazard associated with unethical accounting behaviors in the supported firms. [ABSTRACT FROM AUTHOR]

This study provides a model of banks' personal loan interest-rate markups by analyzing their expected profit maximization. Employing 804 personal loan cases from one Taiwanese bank, our empirical findings show that this model is able to identify the personal loan interest cut-off rates for each risk segment for bank profit maximization in order to determine personal loan interest-rate markups in a more accurate and rational manner. The interest-rate markups identified by this model can serve as a reference for banks' projections regarding optimal interest-rate markups for personal loans. [ABSTRACT FROM AUTHOR]

Inadequate credit risk management is likely to lead a credit institution' bankruptcy. There are many techniques of this risk management some of which aimed at early warning models of depreciation loan portfolio (Credit Risk +, CreditPortfolio View, KMV etc.), while, the other part is to monitor the credit risk to the borrowers. The study undertaken proposed a credit scoring model, applied to legal entities, designed to identify their insolvency risk. The model was built based on the results obtained by 35 commercial companies (belonging to industry and production) listed on the Bucharest Stock Exchange, for a period of 3 years, between 2012-2014. Of these companies, 8 are in the default condition, meaning 23% of the sample size considered. The selected indicators express the debt repayment capacity, the profitability and the liquidity of the analyzed entities. The most relevant indicator used into the model was appreciated to be banking debt recovery term. The tests applied have demonstrated the model' validity (graininess principle, the power of discrimination). [ABSTRACT FROM AUTHOR]

Currently, a fundamental role in firm activity lies in financial performance, given that competition for each market segment has become increasingly tight and mechanisms of globalization exclude the weakest ones. So the chance to survive in this competition increases considerably for those firms who quickly find and reduce their vulnerabilities and furthermore implement performance management tools that facilitate discovery, explanation and solutioning difficulties. Research presented in this paper continues the investigations that were carried out in the domain of firm financial performance, seeking to highlight the importance of financial knowledge within all sectors. Present reasearch aims to evaluate financial performance within Romanian tourism sector, given specific of this sector. Evaluation of financial performance of this sector is based on a proposed credit scoring model. [ABSTRACT FROM AUTHOR]

This study extends the Foreclosed House credit scoring system with further five Speculator characteristics, i.e. ｢ debt ratio ｣, ｢ whether the loan's residence and tender object is in different locations ｣ ,｢ the borrower of last three months by other banks because of the number of new mortgage query totaled more than three times ｣ , ｢ the borrower to apply for loans has more than one loan credit ｣ and ｢ the borrower to apply for loans had paid off the mortgages totaled more than three times within three years ｣ , in the logistic regression model to build a dichotomous prediction credit scoring model which can be adopted by financial institutes to prevent default risk of Foreclosed House mortgage loan and improve the quality of risky asset. The empirical results indicate that the overall accurate predict rate of the model with five Speculator characteristics (80.5%) is higher than the model without five Speculator characteristics (91.0%) indicating that characteristics of speculator has the most ability to predict default rate. [ABSTRACT FROM AUTHOR]

One of the most commonly used methods for assessing the credit rating of counterparties is a credit scoring model or credit scoring. Economic pressures, resulting in increased demand for loans, along with increasing the competition in the market of enterprises and the development of computational techniques and technologies leads to the development of statistical credit scoring model, and in order to expedite the process for making decisions related to credit approval. Credit scoring is used to increase the precision in the approval of loans to creditworthy customers, which can result in increased profits or rejection of those customers who are not creditworthy. [ABSTRACT FROM AUTHOR]

Recent finance and debt crises have made credit risk management one of the most important issues in financial research. Reliable credit scoring models are crucial for financial agencies to evaluate credit applications and have been widely studied in the field of machine learning and statistics. In this paper, a novel feature-weighted support vector machine (SVM) credit scoring model is presented for credit risk assessment, in which an F-score is adopted for feature importance ranking. Considering the mutual interaction among modeling features, random forest is further introduced for relative feature importance measurement. These two feature-weighted versions of SVM are tested against the traditional SVM on two real-world datasets and the research results reveal the validity of the proposed method. [ABSTRACT FROM AUTHOR]

This study extends the traditional credit scoring system with further four factors, i.e. 「debt ratio」,「real-estate speculator」,「batch processing mortgage loan」and「size of the house」in the logistic regression model to build a dichotomous prediction model which can be adopted by financial institutes to prevent default risk of residential mortgage loan and improve the quality of risky asset. The empirical results indicate that the overall accurate predict rate of this new model is 89.3%, which is significantly higher than the traditional model (77.5%). Among the four factors, the factor of「real-estate speculator」has the highest odds ratio (24.49) indicating that factor of speculator has the most ability to predict default rate. [ABSTRACT FROM AUTHOR]

This paper describes the utility of Principal Component Analysis (PCA) in the banking domain, more exactly in the consumer lending problem. PCA is a powerful tool for analyzing data of high dimension. When an applicant requests a loan for personal needs, a credit officer collects data from him and makes a scoring. The factors analyzed can be significant as well as insignificant. The principal component analysis can help in this case to extract those factors, which produce a better credit scoring model. The data set used for the analysis is provided by a public database containing credit data from a German bank. The results emphasize the utility of PCA in the banking sector to reduce the dimension of data, without much loss of information. [ABSTRACT FROM AUTHOR]

Abstract: Credit scoring model development became a very important issue as the credit industry has many competitions and bad debt problems. Therefore, most credit scoring models have been widely studied in the areas of statistics to improve the accuracy of credit scoring models during the past few years. In order to solve the classification and decrease the Type I error of credit scoring model, this paper presents a reassigning credit scoring model (RCSM) involving two stages. The classification stage is constructing an ANN-based credit scoring model, which classifies applicants with accepted (good) or rejected (bad) credits. The reassign stage is trying to reduce the Type I error by reassigning the rejected good credit applicants to the conditional accepted class by using the CBR-based classification technique. To demonstrate the effectiveness of proposed model, RCSM is performed on a credit card dataset obtained from UCI repository. As the results indicated, the proposed model not only proved more accurate credit scoring than other four common used approaches, but also contributes to increase business revenue by decreasing the Type I and Type II error of scoring system. [Copyright &y& Elsevier]

The credit scoring model is one of the most important decision-making tools for the sustainability of banking systems. This study is the first to examine whether it can be improved by using system log data that are stoed extensively for system operation. We used the log data recorded by the mobile application system of KakaoBank, a leading internet bank used by more than 14 million people in Korea. After generating candidate variables from KakaoBank's log data, we created a credit scoring model by utilizing variables with high information values and logistic regression, the most common method for developing credit scoring models in financial institutions. To prove our hypothesis on the improvement of credit scoring model performance, we performed an independent sample t-test using the simulation results of repeated model development and performance measurement based on randomly sampled data. Consequently, the discrimination power of the proposed model using logistic regression (neural network) compared to the credit bureau-based model significantly improved by 1.84 (2.22) percentage points based on the Kolmogorov–Smirnov statistics. The results of this study suggest that a bank can utilize the accumulated log data inside the bank to improve decision-making systems, including credit scoring, at a low cost. [ABSTRACT FROM AUTHOR]

As credit card usage has expanded rapidly worldwide, credit scoring has become a very important task for banks, which can benefit from reducing possible risks of default. Credit scoring models help decision makers to decide whether to issue a credit card to a new applicant on the basis of both financial and nonfinancial criteria. The scope of the current study is to develop a dynamic scoring model that (a) estimates the credit performance of an applicant using generalised linear models and (b) accommodates the changes of a borrower's characteristics after the issuance of the credit card and forecasts the time of default using survival analysis.Journal of Financial Services Marketing (2008) 13, 17–27. doi:10.1057/fsm.2008.2 [ABSTRACT FROM AUTHOR]

Abstract: Credit scoring models have been widely studied in the areas of statistics, machine learning, and artificial intelligence (AI). Many novel approaches such as artificial neural networks (ANNs), rough sets, or decision trees have been proposed to increase the accuracy of credit scoring models. Since an improvement in accuracy of a fraction of a percent might translate into significant savings, a more sophisticated model should be proposed for significantly improving the accuracy of the credit scoring models. In this paper, two-stage genetic programming (2SGP) is proposed to deal with the credit scoring problem by incorporating the advantages of the IF–THEN rules and the discriminant function. On the basis of the numerical results, we can conclude that 2SGP can provide the better accuracy than other models. [Copyright &y& Elsevier]

Abstract: Unrepresentative data samples are likely to reduce the utility of data classifiers in practical application. This study presents a hybrid mining approach in the design of an effective credit scoring model, based on clustering and neural network techniques. We used clustering techniques to preprocess the input samples with the objective of indicating unrepresentative samples into isolated and inconsistent clusters, and used neural networks to construct the credit scoring model. The clustering stage involved a class-wise classification process. A self-organizing map clustering algorithm was used to automatically determine the number of clusters and the starting points of each cluster. Then, the K-means clustering algorithm was used to generate clusters of samples belonging to new classes and eliminate the unrepresentative samples from each class. In the neural network stage, samples with new class labels were used in the design of the credit scoring model. The proposed method demonstrates by two real world credit data sets that the hybrid mining approach can be used to build effective credit scoring models. [Copyright &y& Elsevier]