Search

Scholarly accounts of the global rise of statistical credit scoring technologies have tended to portray these automated, digitised systems as supplanting human involvement in lending. This paper examines Chinese migrant factory workers' encounters with Ant Credit Pay, Alipay's novel consumer credit facility (which utilises the Zhima Credit scoring system). Drawing on ethnographic data, we document how workers come to understand Ant Credit Pay through the depersonalising and re-personalising processes they associate with it. Workers prefer its depersonalised mode of lending over borrowing from banks, friends, or family. However, they nonetheless also attempt to re-personalise Ant Credit Pay through propagating the belief that human-style logics underlie its scoring mechanisms. This becomes evidenced through workers' integration of the platform into their personal spending practices, alongside their portrayal of charismatic Alipay founder Jack Ma as the orchestrator of the platform's novel approach to lending. We argue that acknowledging Ant Credit Pay's consolidation of depersonalising and re-personalising qualities necessitates the productive analysis of digital credit as a human-machine assemblage. Furthermore, this financial object – and workers' engagement with it – is generative of a distinctive personhood that concretizes China's ongoing social transformation, while also carrying implications for understanding current global trends towards the digitisation of credit. [ABSTRACT FROM AUTHOR]

Nowadays, the effective credit scoring becomes a very crucial factor for gaining competitive advantages in credit market for both customers and corporations. In this paper, we propose a credit scoring method which combines the non-kernel fuzzy 2-norm quadratic surface SVM model, T-test feature weighting strategy and fuzzy within-class scatter together. It is worth pointing out that this new method not only saves computational time by avoiding choosing a kernel and corresponding parameters in the classical SVM models, but also addresses the "curse of dimensionality" issue and improves the robustness. Besides, we develop an efficient way to calculate the fuzzy membership of each training point by solving a linear programming problem. Finally, we conduct several numerical tests on two benchmark data sets of personal credit and one real-world data set of corporation credit. The numerical results strongly demonstrate that the proposed method outperforms eight state-of-the-art and commonly-used credit scoring methods in terms of accuracy and robustness. [ABSTRACT FROM AUTHOR]

This research aims to propose a framework for evaluating credit applications by assigning a binary score to the applicant. The score is targeted to determine whether the credit application is 'good' or 'bad' in small business purpose loans. Even tiny performance improvements in small businesses may yield a positive impact on the economy as they generate more than 60% of the value. The method presented in this paper hybridizes the Genetic Algorithm (GA) and the Support Vector Machine (SVM) in a bi-level feeding mechanism for increased prediction accuracy. The first level is to determine the parameters of SVM and the second is to find a feature set that increases classification accuracy. To test the proposed approach, we have investigated three different data sets; UCI Australian data set for preliminary works, Lending Club data set for large training and testing, and UCI German and Australian datasets for benchmarking against some other notable methods that use GA. Our computational results show that our proposed method using a feedback mechanism under the hybrid bi-level GA-SVM structure outperforms other classification algorithms in the literature, namely Decision Tree, Random Forests, Logistic Regression, SVM and Artificial Neural Networks, effectively improves the classification accuracy. [ABSTRACT FROM AUTHOR]

Financial institutions are exposed to credit risk due to issuance of consumer loans. Thus, developing reliable credit scoring systems is very crucial for them. Since, machine learning techniques have demonstrated their applicability and merit, they have been extensively used in credit scoring literature. Recent studies concentrating on hybrid models through merging various machine learning algorithms have revealed compelling results. There are two types of hybridization methods namely traditional and ensemble methods. This study combines both of them and comes up with a hybrid meta-learner model. The structure of the model is based on the traditional hybrid model of 'classification + clustering' in which the stacking ensemble method is employed in the classification part. Moreover, this paper compares several versions of the proposed hybrid model by using various combinations of classification and clustering algorithms. Hence, it helps us to identify which hybrid model can achieve the best performance for credit scoring purposes. Using four real-life credit datasets, the experimental results show that the model of (KNN-NN-SVMPSO)-(DL)-(DBSCAN) delivers the highest prediction accuracy and the lowest error rates. [ABSTRACT FROM AUTHOR]

In this article, a problem of measurement of credit risk in bank is studied. The approach suggested to solve it uses a Bayesian networks. After the data-gathering characterizing of the customers requiring of the loans, this approach consists initially with the samples collected, then the setting in works about it of various network architectures and combinations of functions of activation and training and comparison between the results got and the results of the current methods used. To address this problem we will try to create a graph that will be used to develop our credit scoring using Bayesian networks as a method. After, we will bring out the variables that affect the credit worthiness of the beneficiaries of credit. Therefore this article will be divided so the first part is the theoretical side of the key variables that affect the rate of reimbursement and the second part a description of the variables, the research methodology and the main results. The findings of this paper serve to provide an effective decision support system for banks to detect and alleviate the rate of bad borrowers through the use of a Bayesian Network model. This paper contributes to the existing literature on customers' default payment and risk associated to allocating loans. [ABSTRACT FROM AUTHOR]

Risk prediction models in credit scoring have to fulfil regulatory requirements, one of which consists in the interpretability of the model. Unfortunately, many popular modern machine learning algorithms result in models that do not satisfy this business need, whereas the research activities in the field of explainable machine learning have strongly increased in recent years. Partial dependence plots denote one of the most popular methods for model-agnostic interpretation of a feature's effect on the model outcome, but in practice they are usually applied without answering the question of how much can actually be seen in such plots. For this purpose, in this paper a methodology is presented in order to analyse to what extent arbitrary machine learning models are explainable by partial dependence plots. The proposed framework provides both a visualisation, as well as a measure to quantify the explainability of a model on an understandable scale. A corrected version of the German credit data, one of the most popular data sets of this application domain, is used to demonstrate the proposed methodology. [ABSTRACT FROM AUTHOR]

For financial institutions, the ability to predict or forecast business failures is crucial, as incorrect decisions can have direct financial consequences. Bankruptcy prediction and credit scoring are the two major research problems in the accounting and finance domain. In the literature, a number of models have been developed to predict whether borrowers are in danger of bankruptcy and whether they should be considered a good or bad credit risk. Since the 1990s, machine-learning techniques, such as neural networks and decision trees, have been studied extensively as tools for bankruptcy prediction and credit score modeling. This paper reviews 130 related journal papers from the period between 1995 and 2010, focusing on the development of state-of-the-art machine-learning techniques, including hybrid and ensemble classifiers. Related studies are compared in terms of classifier design, datasets, baselines, and other experimental factors. This paper presents the current achievements and limitations associated with the development of bankruptcy-prediction and credit-scoring models employing machine learning. We also provide suggestions for future research. [ABSTRACT FROM PUBLISHER]

One of the basic stages of constructing credit-scoring models is the assessment of their quality understood as the ability to separate reliable and unreliable borrower population. This paper focuses on methods enabling the assessment of discrimination quality, and presents the results of researches on the basis of empirical data. Apart from establishing the measure of discrimination quality, this paper refers to the issue of the assessment of the stability of results obtained by setting a confidence interval for the quality measure of the scoring model. [ABSTRACT FROM AUTHOR]

Support Vector Machine, an optimization technique, is well known in the data mining community. In fact, many other optimization techniques have been effectively used in dealing with data separation and analysis. For the last 10 years, the author and his colleagues have proposed and extended a series of optimization-based classification models via Multiple Criteria Linear Programming (MCLP) and Multiple Criteria Quadratic Programming (MCQP). These methods are different from statistics, decision tree induction, and neural networks. The purpose of this paper is to review the basic concepts and frameworks of these methods and promote the research interests in the data mining community. According to the evolution of multiple criteria programming, the paper starts with the bases of MCLP. Then, it further discusses penalized MCLP, MCQP, Multiple Criteria Fuzzy Linear Programming (MCFLP), Multi-Class Multiple Criteria Programming (MCMCP), and the kernel-based Multiple Criteria Linear Program, as well as MCLP-based regression. This paper also outlines several applications of Multiple Criteria optimization-based data mining methods, such as Credit Card Risk Analysis, Classification of HIV-1 Mediated Neuronal Dendritic and Synaptic Damage, Network Intrusion Detection, Firm Bankruptcy Prediction, and VIP E-Mail Behavior Analysis. [ABSTRACT FROM AUTHOR]

This paper encompasses three parts of validating risk models. The first part provides an understanding of the precision of the standard statistics used to validate risk models given varying sample sizes. The second part investigates jackknifing as a method to obtain a confidence interval for the Gini coefficient and K-S statistic for small sample sizes. The third and final part investigates the odds at various cutoff points as to its efficiency and appropriateness relative to the K-S statistic and Gini coefficient in model validation. There are many parts to understanding the risk associated with the extension of credit. This paper focuses on obtaining a better understanding of present methodology for validating existing risk models used for credit scoring, by investigating the three parts mentioned. The empirical investigation shows the precision of the Gini coefficient and K-S statistic is driven by the sample size of the smaller, either successes or failures. In addition, a simple adaption of the standard jackknifing formula is possible to use to get an understanding of the variability of the Gini coefficient and K-S statistic. Finally, the odds is not a reliable statistic to use without a considerably large sample of both successes and failures. [ABSTRACT FROM AUTHOR]

This paper proposes a novel model for establishing a credit evaluation system, including a system of indicators, indicator weights, and credit scores. A credit evaluation system whose evaluation results have significant discrimination is good. Based on this standard, we construct an objective programming model with the maximum discrimination of credit scores as the objective function. The main constraint condition is that the indicator weights sum to 1, and weight is a decision variable. After we delete indicators whose weight is 0, we design a system of indicators, and then obtain credit scores with the maximum discriminatory power. Our empirical study of China's 3,045 small businesses confirms that this model is both easy to use and reasonable. The empirical results show that, compared to logistic regression and CHAID decision trees, our model has greater accuracy based on F, AUC, and KS tests. [ABSTRACT FROM AUTHOR]

Credit scoring on class imbalance data, where the class of defaulters is insufficiently represented compared with the class of non-defaulters, is an important but challenging task. In this paper, we propose an imbalanced generative adversarial fusion network (IGAFN) to cope with the class imbalance credit scoring based on multi-source heterogeneous credit data. Concretely, we design a fusion module to integrate the heterogeneous credit data from multiple sources into a unified latent feature space. A generative adversarial network-based balance module is then designed to generate latent representations of new samples for the minority class of the imbalanced datasets. The performance of IGAFN is compared against multiple conventional machine learning and deep learning algorithms. Extensive experiments show that the proposed IGAFN exhibits significantly better performance than the compared methods on two real-life datasets. [ABSTRACT FROM AUTHOR]

In this paper, an experimental study was carried out to determine the influence of imbalanced datasets preprocessing in the performance of associative classifiers, in order to find the better computational solutions to the problem of credit scoring. To do this, six undersampling algorithms, six oversampling algorithms and four hybrid algorithms were evaluated in 13 imbalanced datasets referring to credit scoring. Then, the performance of four associative classifiers was analyzed. The experiments carried out allowed us to determine which sampling algorithms had the best results, as well as their impact on the associative classifiers evaluated. Accordingly, we determine that the Hybrid Associative Classifier with Translation, the Extended Gamma Associative Classifier and the Naïve Associative Classifier do not improve their performance by using sampling algorithms for credit data balancing. On the other hand, the Smallest Normalized Difference Associative Memory classifier was beneficiated by using oversampling and hybrid algorithms. [ABSTRACT FROM AUTHOR]

Training classification models on imbalanced data tends to result in bias towards the majority class. In this paper, we demonstrate how variable discretization and cost-sensitive logistic regression help mitigate this bias on an imbalanced credit scoring dataset, and further show the application of the variable discretization technique on the data from other domains, demonstrating its potential as a generic technique for classifying imbalanced data beyond credit socring. The performance measurements include ROC curves, Area under ROC Curve (AUC), Type I Error, Type II Error, accuracy, and F1 score. The results show that proper variable discretization and cost-sensitive logistic regression with the best class weights can reduce the model bias and/or variance. From the perspective of the algorithm, cost-sensitive logistic regression is beneficial for increasing the value of predictors even if they are not in their optimized forms while maintaining monotonicity. From the perspective of predictors, the variable discretization performs better than cost-sensitive logistic regression, provides more reasonable coefficient estimates for predictors which have nonlinear relationships against their empirical logit, and is robust to penalty weights on misclassifications of events and non-events determined by their apriori proportions. [ABSTRACT FROM AUTHOR]

Summary: Banks are continuously looking for novel ways to leverage their existing data assets. A major source of data that has not yet been used to the full extent is massive fine‐grained payment data on the bank's customers. In the paper, a design is proposed that builds predictive credit scoring models by using the fine‐grained payment data. Using a real life data set of 183 million transactions made by 2.6 million customers, we show that the scalable implementation that is put forward leads to a significant improvement in the receiver operating characteristic area under the curve, with only seconds of computation needed. When investigating the 1% riskiest customers, twice as many defaulters are detected when using the payment data. Such an improvement has a big effect on the overall working of the bank, from applicant scoring to minimum capital requirements. [ABSTRACT FROM AUTHOR]

Due to recent financial crises and regulatory concerns, financial intermediaries' credit risk assessment is an area of renewed interest in both the academic world and the business community. In this paper, we propose a new fuzzy support vector machine to discriminate good creditors from bad ones. Because in credit scoring areas we usually cannot label one customer as absolutely good who is sure to repay in time, or absolutely bad who will default certainly, our new fuzzy support vector machine treats every sample as both positive and negative classes, but with different memberships. By this way we expect the new fuzzy support vector machine to have more generalization ability, while preserving the merit of insensitive to outliers, as the fuzzy support vector machine (SVM) proposed in previous papers. We reformulate this kind of twos group classification problem into a quadratic programming problem. Empirical tests on three public datasets show that it can have better discriminatory power than the standard support vector machine and the fuzzy support vector machine if appropriate kernel and membership generation method are chosen. [ABSTRACT FROM AUTHOR]

Credit scoring is the term used to describe methods utilized for classifying applicants for credit into classes of risk. This paper evaluates two induction approaches, rough sets and decision trees, as techniques for classifying credit (business) applicants. Inductive learning methods, like rough sets and decision trees, have a better knowledge representational structure than neural networks or statistical procedures because they can be used to derive production rules. If decision trees have already been used for credit granting, the rough sets approach is rarely utilized in this domain. In this paper, we use production rules obtained on a sample of 1102 business loans in order to compare the classification abilities of the two techniques. We show that decision trees obtain better results with 87.5% of good classifications with a pruned tree, against 76.7% for rough sets. However, decision trees make more type–II errors than rough sets, but fewer type–I errors. [ABSTRACT FROM AUTHOR]

Scorecard is the main method used by financial institutions to quantitatively assess customer credit risk. The traditional scorecard mainly uses the logical regression (LR) for modeling, although it is good in interpretation and stability, it is not suitable for processing large-scale samples, and its accuracy is low. Meanwhile, with the further study in recent years, machine learning has gradually begun to be applied to high-dimensional large-scale sample modeling in the financial field. However, machine learning also has problems such as poor interpretability and weak generalization ability. This paper proposes to build an integrated model of machine learning and logical regression, and makes full use of the advantages of the two algorithms to develop a new scorecard model. The practice shows that the new scorecard model has good differentiation ability. [ABSTRACT FROM AUTHOR]

Conventional credit scoring models evaluated by predictive accuracy or profitability typically serve the financial institutions and can hardly reflect their contribution on financial stability. To remedy this, we develop a novel regulatory scoring framework to quantify and compare the corresponding regulatory capital charge errors of credit scoring models. As an application of RegTech, the proposed framework considers the characteristic of example-dependence and costsensitivity in credit scoring, which is expected to enhance the ability of risk absorption of financial institutions and thus benefit the regulators. Validated on two real-world credit datasets, empirical results reveal that credit scoring models with good predictive accuracy or profitability do not necessarily provide low capital charge requirement error, which further highlights the importance of regulatory scoring framework. The family of gradient boosting decision tree (GBDT) provides significantly better average performance than industry benchmarks and deep multilayer perceptron network, especially when financial stability is the primary focus. To further examine the robustness of the proposed regulatory scoring, sampling techniques, cut-off value modification, and probability calibration are employed within the framework and the main conclusions hold in most cases. Furthermore, the analysis on the interpretability via TreeSHAP algorithm alleviates the concerns on transparency of GBDT-based models, and confirms the important roles of loan characteristics, borrowers' solvency and creditworthiness as powerful predictors in credit scoring. Finally, the managerial implications for both financial institutions and regulators are discussed. [ABSTRACT FROM AUTHOR]

This paper compares the predictive power of credit scoring models based on machine learning techniques with that of traditional loss and default models. Using proprietary transaction-level data from a leading fintech company in China, we test the performance of different models to predict losses and defaults both in normal times and when the economy is subject to a shock. In particular, we analyse the case of an (exogenous) change in regulation policy on shadow banking in China that caused credit conditions to deteriorate. We find that the model based on machine learning and non-traditional data is better able to predict losses and defaults than traditional models in the presence of a negative shock to the aggregate credit supply. This result reflects a higher capacity of non-traditional data to capture relevant borrower characteristics and of machine learning techniques to better mine the non-linear relationship between variables in a period of stress. • We compare the predictive power of machine learning and traditional credit models. • We analyse data from a Chinese fintech firm during normal and stress periods. • Machine learning models outperform other models, especially during negative shocks. • This shows their ability to detect non-linear patterns in stressful times. [ABSTRACT FROM AUTHOR]

This article examines how racial capitalism intersects with platform capitalism through the rise of rental platforms and corporate landlords in the post-apartheid housing market. Combining 18 months of fieldwork in Cape Town with the spatial analysis of sales and longitudinal census data, I demonstrate how rental platforms enabled the consolidation of the private rental sector and the emergence of corporate landlords through the classification of tenants centered upon credit scoring. To automate tenant screening solutions, rental platforms leveraged and extended the information dragnet knitted by credit bureaus. This dragnet of unprecedented depth and volume is built upon the infrastructures and devices that enabled the for-profit, racial classification of people, housing and neighborhoods during colonialism and apartheid, notably ID numbers. In the context of racialized indebtedness and housing inequalities engineered by racial property regimes, the use of platforms to sort the "good" from the "bad" tenant and manage rental portfolios shifts mechanisms of segregation and reproduces racialized patterns of capital accumulation across the post-apartheid city. The article argues that rental platforms extend the extractive logic of racial capitalism through two joint rentier mechanisms: the transformation of rental housing into a new asset class; the extraction and assetization of rental data. [ABSTRACT FROM AUTHOR]

Purpose - Personal bankruptcy is on the rise in Malaysia. The Insolvency Department of Malaysia reported that personal bankruptcy has increased since 2007, and the total accumulated personal bankruptcy cases stood at 131,282 in 2014. This is indeed an alarming issue because the increasing number of personal bankruptcy cases will have a negative impact on the Malaysian economy, as well as on the society. From the aspect of individual's personal economy, bankruptcy minimizes their chances of securing a job. Apart from that, their account will be frozen, lost control on their assets and properties and not allowed to start any business nor be a part of any company's management. Bankrupts also will be denied from any loan application, restricted from travelling overseas and cannot act as a guarantor. This paper aims to investigate this problem by developing the personal bankruptcy prediction model using the decision tree technique. Design/methodology/approach - In this paper, bankrupt is defined as terminated members who failed to settle their loans. The sample comprised of 24,546 cases with 17 per cent settled cases and 83 per cent terminated cases. The data included a dependent variable, i.e. bankruptcy status (Y = 1(bankrupt), Y = 0 (non-bankrupt)) and 12 predictors. SAS Enterprise Miner 14.1 software was used to develop the decision tree model. Findings - Upon completion, this study succeeds to come out with the profiles of bankrupts, reliable personal bankruptcy scoring model and significant variables of personal bankruptcy. Practical implications - This decision tree model is possible for patent and income generation. Financial institutions are able to use this model for potential borrowers to predict their tendency toward personal bankruptcy. Originality/value - This decision tree model is able to facilitate and assist financial institutions in evaluating and assessing their potential borrower. It helps to identify potential defaulting borrowers. It also can assist financial institutions in implementing the right strategies to avoid defaulting borrowers. [ABSTRACT FROM AUTHOR]

In view of class-imbalance in real credit scoring business of credit industry, this paper firstly determined the main evaluation indicators of credit scoring based on a comprehensive analysis of the influence factors’ Fisher ratio value. Then, it chose the SMOTE based on support degree( SDSMOTE) oversampling algorithm to synthesize new samples, SVM played as the base predictor and Boosting algorithm as the framework, this paper proposed a credit scoring prediction model which associated class-imbalance with Fisher-SDSMOTE-ESBoostSVM theory. Besides, it introduced the elimination strategy to delete the synthetic sample which was not classified accurately, after that synthesized the new positive class sample again and modified the sample weight. Finally, it selected the German credit dataset in the UCI database as the experimental dataset, and Fmeasure value and G-mean value as evaluation standard, comparing and analyzing the prediction result of Fisher-SDSMOTEESBoostSVM model and others ensemble learning algorithm. Experimental results show that the application of FisherSDSMOTE-ESBoostSVM algorithm to customer credit score prediction is feasible and applicable, and show a high level of accuracy, which proved that the algorithm has a certain practical application value. [ABSTRACT FROM AUTHOR]

Credit scoring focuses on the development of empirical models to support the financial decision‐making processes of financial institutions and credit industries. It makes use of applicants' historical data and statistical or machine learning techniques to assess the risk associated with an applicant. However, the historical data may consist of redundant and noisy features that affect the performance of credit scoring models. The main focus of this paper is to develop a hybrid model, combining feature selection and a multilayer ensemble classifier framework, to improve the predictive performance of credit scoring. The proposed hybrid credit scoring model is modeled in three phases. The initial phase constitutes preprocessing and assigns ranks and weights to classifiers. In the next phase, the ensemble feature selection approach is applied to the preprocessed dataset. Finally, in the last phase, the dataset with the selected features is used in a multilayer ensemble classifier framework. In addition, a classifier placement algorithm based on the Choquet integral value is designed, as the classifier placement affects the predictive performance of the ensemble framework. The proposed hybrid credit scoring model is validated on real‐world credit scoring datasets, namely, Australian, Japanese, German‐categorical, and German‐numerical datasets. [ABSTRACT FROM AUTHOR]

To increase the quality of loans provision and reduce the risk involved in this process, several credit scoring models have been developed and utilized to improve the process of assessing credit worthiness. Credit scoring is an evaluation of the risk connected with lending to clients (consumers) or an organization. The Gustafson-Kessel (GK) algorithm has become one of the most valuable tools for credit scoring. However, this algorithm demonstrates a relatively poor capability to identify a subset of features from a large dataset. Most methods that use the GK algorithm require a predefined number of clusters. This paper presents a new GK-based modified binary particle swarm optimization (MBPSO) approach to increase the classification accuracy of the GK algorithm. The proposed MBPSO consists of three parts. First, the figure of particles is utilized to determine the optimal number of clusters automatically and overcome the drawback of the GK algorithm that requires a predefined number of clusters. A subset of features is identified because the same dataset may contain influencing features or a high level of noise. The two procedures are then combined in the same optimization method to increase the classification accuracy of the GK algorithm. Second, the updating function uses velocity and position to update the next position for every particle in the swarm. Third, a kernel fuzzy clustering method (KFCM) is used as the fitness function because this function can analyze high- dimensional data. These modifications are utilized as preprocessing steps before the classification of credit data is performed. Internal measures of clustering are conducted on Australian, German, and Taiwan standard datasets that contain 690, 1,000, and 30,000 instances, respectively, with several feature properties. Results show that the GK algorithm is good at separating the data into clusters. Furthermore, the fuzzy Rand validity measures of the three credit datasets derived by using the proposed method of combining the GK algorithm with a MBPSO are greater than the values of the two other compared methods. This finding means that fuzzy partitioning (classification) is robust therefore, the risk associated with loans provision can be reduced when the proposed method is used. [ABSTRACT FROM AUTHOR]

Abstract Credit scoring models have offered benefits to lenders and borrowers for many years. However, in practice these models are normally built on a sample of accepted applicants and fail to consider the remaining rejected applicants. This may cause a sample bias which is an important statistical issue, especially in the online lending situation where a large proportion of requests are rejected. Reject inference is a method for inferring how rejected applicants would have behaved if they had been granted and incorporating this information in rebuilding a more accurate credit scoring system. Due to the good performances of SVM models in this area, this paper proposes a new approach based on the state-of-the-art kernel-free fuzzy quadratic surface SVM model. It is worth pointing out that our method not only performs very well in classification as some latest works, but also handles some big issues in the classical SVM models, such as searching proper kernel functions and solving complex models. Besides, this paper is the first one to eliminate the bad effect of outliers in credit scoring. Moreover, we use two real-world loan data sets to compare our method with some benchmark methods. Particularly, one of the data set is very valuable for the study of reject inference, because the outcomes of rejected applicants are partially known. Finally, the numerical results strongly demonstrate the superiority of the proposed method in applicability, accuracy and efficiency. Highlights • Kernel-free FQSSVM is used in the approach to reject inference. • The approach eliminates the bad effect of outliers in credit scoring. • The approach can handle large-sized problem efficiently. • The approach achieves the best accuracy in prediction. • The real-world data contains valuable information about rejected applicants. [ABSTRACT FROM AUTHOR]

The objective of quantitative credit scoring is to develop accurate models of classification. Most attention has been devoted to deliver new classifiers based on variables commonly used in the economic literature. Several interdisciplinary studies have found that personality traits are related to financial behaviour; therefore, psychological traits could be used to lower credit risk in scoring models. In our paper, we considered financial histories and psychological traits of customers of an Italian bank. We compared the performance of kernel-based classifiers with those of standard ones. We found very promising results in terms of misclassification error reduction when personality attitudes are included in models, with both linear and non-linear discriminants. We also measured the contribution of each variable to risk prediction in order to assess importance of each predictor. [ABSTRACT FROM AUTHOR]

Trade finance plays a significant role in the global trade of merchandise, which witnessed a sharp fall in late 2008 and early 2009. Firms across the world experienced restricted access to bank credit in the wake of the financial crisis, and this had a considerable impact on the operation and growth of their businesses. The financial crisis led to a contagion on trade finance and product sellers' payment terms. Furthermore, corporate trade credit is a potential alternative to institutional financing that serves as an important source of finance. Corporate trade finance represents an important part of short-term financing for firms, especially during financial crises. This paper evaluates the impact of the increased use of corporate trade finance in two unique portfolios of production firms during the financial crisis. All have an active treasury organization. The analysis demonstrates the impact of the financial crisis on corporate trade credit demographically. Furthermore, it uses financial performance and working capital data of other German stock-listed production firms. It analyses how developments or changes in working capital impact a firm's sales growth, EBIT interest, tangible net and EBITDA margin, and total asset worth. [ABSTRACT FROM AUTHOR]

As traditional credit evaluation methods generally only use accepted sample modeling, the rejected data is omitted, which means the model's prediction of new customers is biased. However, reject inference can be used to solve this credit evaluation sample selection bias. This paper proposes a new reject inference method based on joint distribution adaptation (JDA) and cost-sensitive semi-supervised support vector machines (CS4VM). First, this method uses both accepted (labeled) samples and rejected (unlabeled) samples modeling, which overcomes the deviations in traditional credit evaluation methods. Second, as the accepted sample and the rejected sample distributions are different, this method reduces the distribution differences between the accepted and rejected sample sets, which ensures that the sample data conforms to the basic assumptions in the semi-supervised model, and improves the performance of the classification model. Third, this method reduces the overall cost in the actual credit business by considering both the traditional misclassification costs when mining the default samples and the different decision weights for the accepted and rejected samples. Finally, an empirical study verifies the excellent predictive performance of the proposed method and effectively reduces the total credit costs. [ABSTRACT FROM AUTHOR]

Credit scoring is a useful tool for assessing the capability of customers repayments. The purpose of this paper is to compare the predictive abilities of six credit scoring models: Linear Discriminant Analysis (LDA), Random Forests (RF), Logistic Regression (LR), Decision Trees (DT), Support Vector Machines (SVM) and Deep Neural Network (DNN). To compare these models, an empirical study was conducted using a sample of 688 observations and twelve variables. The performance of this model was analyzed using three measures: Accuracy rate, F1 score, and Area Under Curve (AUC). In summary, machine learning techniques exhibited greater accuracy in predicting loan defaults compared to other traditional statistical models.

Credit scoring is a crucial problem in both finance and banking. In this paper, we tackle credit scoring as a classification problem where three local search-based methods are studied for feature selection. The feature selection is an interesting technique that can be launched before the data classification task. It permits to keep only the relevant variables and eliminate the redundant ones which enhances the classification accuracy. We study the local search method (LS), the stochastic local search method (SLS) and the variable neighborhood search method (VNS) for feature selection. Then, we combine these methods with the support vector machine (SVM) classifier to find the best described model from a dataset with the correct class variable. The proposed methods (LS+SVM, SLS+SVM and VNS+SVM) are evaluated on both German and Australian credit datasets and compared with some well-known classifiers. The numerical results are promising and show a good performance in favor of our methods. [ABSTRACT FROM AUTHOR]

Copyright of Research Papers of the Wroclaw University of Economics / Prace Naukowe Uniwersytetu Ekonomicznego we Wroclawiu is the property of Uniwersytet Ekonomiczny we Wroclawiu and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the financial crisis happened in 2007, massive credit risks are exposed to the banking sectors. So credit scoring has attracted more and more attention. Bank owns a lot of customer data. By using those data, credit scoring model can judge the applicants’ credit risk accurately. But those data are often high dimensional, and have some irrelevant features. Those irrelevant features will affect classifiers accuracy. Therefore, feature selection is an important topic. This paper proposes a two-phase hybrid approach based on filter approach and multiple population genetic algorithm-HMPGA. In phase 1, it introduces the idea of wrapper approach into three filter approaches to acquire some important prior information for initial populations setting of MPGA. In phase 2, it takes advantage of MPGA’s characteristics of global optimization and quick convergence to find optimal feature subset. This paper uses two real credit scoring datasets of UCI databases to compare HMPGA, MPGA and GA. It verifies that the accuracies of feature subsets acquired from HMPGA, MPGA and GA are superior to three filter approaches. Meanwhile, nonparametric Wilcoxon signed rank test is held to confirm that HMPGA is better than MPGA and GA. HMPGA not only can be applied to feature selection of credit scoring, but also can be applied to more fields of data mining. [ABSTRACT FROM AUTHOR]