Credit Scoring Research Articles

Sample selection bias in non-traditional lending: A copula-based approach for imbalanced data

Credit scoring models for non-traditional lending channels, such as peer-to-peer (P2P) lending platforms, are usually estimated only on the sample of accepted applicants. This may lead to biased estimates of the risk drivers. This issue can be addressed using a reject inference technique that includes the characteristics of rejected applicants in the model. Due to the low numbers of accepted applicants and default records, credit scoring models usually face a class imbalance problem. However, previous literature on sample selection models for credit scoring does not address the class imbalance issue. To fill this gap, we extend the Generalised Extreme Value (GEV) regression model for binary data to the sample selection framework. We consider the quantile function of the GEV distribution as a link function in both the selection and outcome equations. We use the copula function to model the dependence structure between the two equations for its flexibility. This proposal is called the Sample Selection Generalised Extreme Value (SSGEV) model and it is implemented in the R package BivGEV. We apply this model to a comprehensive dataset provided by Lending Club, and we show that parameter estimates obtained only on accepted P2P applicants are biased and coherently with the literature. The SSGEV model achieves a higher predictive accuracy than those obtained using univariate approaches or a sample selection probit model. Our proposal also provides more conservative estimates of the Value-at-Risk and the Expected Shortfall.

A novel profit-driven framework for model evaluation in credit scoring

Credit scoring is a prominent problem in machine learning (ML). ML classifiers used to assess creditworthiness need to be evaluated using appropriate metrics. Common metrics fall into two categories: cost-sensitive and traditional cost-insensitive. Traditional cost-insensitive metrics like accuracy and area under the curve (AUC) have several drawbacks. They can be difficult for managers to understand, potentially misleading in certain scenarios, and often overlook the business realities of credit scoring. Conversely, existing cost-sensitive metrics are imperfect, leading many studies to rely on classic AUC metrics. In this study, we introduce the expected profit ratio (EPR), a novel framework for evaluating classifiers in credit scoring. EPR does not require a base scenario and accurately calculates the profit. Its flexibility makes it suitable for all types of credit-scoring problems, and its simplicity aids in comprehension and explanation. By enabling accurate profit calculation, EPR helps managers, executives, and administrators make informed decisions and investments. This metric lays the foundation for more sophisticated and precise model evaluation and comparison in credit scoring. Additionally, it can be used as a performance measure, alongside fairness and other criteria needed to achieve trustworthy artificial intelligence (AI).

A Hybrid Extreme Gradient Boosting Model for Credit Risk Modelling in the Presence of Inflation

The recent developments in the credit and banking industry brought by technology has led to increased competition and the rise of risks and challenges. Credit scoring is one of the core items that keeps this industry competitive and profitable. The creation of credit score models to assess the ability of the loan applicant to repay his or her loan remains an active field of research. Practically, the existing models ignore the factor of inflation in determining the credit score of a loan applicant. Inflation affect the performance of the financing institution negatively because it makes some of the borrowers struggle to repay the loan and so leading to some bad debts that might end up being written off. By integrating the inflation factor to the Extreme gradient boosting algorithm led to improved accuracy of the model. In this paper, a new model that uses the inflation rate of a specific region or country in the regularization term of the extreme gradient boosting model has been developed. The evaluation of the model is by comparison with the other common models using ROC, Accuracy, precision and recall. The developed model emerge the second best in terms of performance but better than the standard extreme gradient boosting model.

A novel framework for enhancing transparency in credit scoring: Leveraging Shapley values for interpretable credit scorecards.

Credit scorecards are essential tools for banks to assess the creditworthiness of loan applicants. While advanced machine learning models like XGBoost and random forest often outperform traditional logistic regression in predictive accuracy, their lack of interpretability hinders their adoption in practice. This study bridges the gap between research and practice by developing a novel framework for constructing interpretable credit scorecards using Shapley values. We apply this framework to two credit datasets, discretizing numerical variables and utilizing one-hot encoding to facilitate model development. Shapley values are then employed to derive credit scores for each predictor variable group in XGBoost, random forest, LightGBM, and CatBoost models. Our results demonstrate that this approach yields credit scorecards with interpretability comparable to logistic regression while maintaining superior predictive accuracy. This framework offers a practical and effective solution for credit practitioners seeking to leverage the power of advanced models without sacrificing transparency and regulatory compliance.

A health-conformant reading of the GDPR's right not to be subject to automated decision-making.

As the use of Artificial Intelligence (AI) technologies in healthcare is expanding, patients in the European Union (EU) are increasingly subjected to automated medical decision-making. This development poses challenges to the protection of patients' rights. A specific patients' right not to be subject to automated medical decision-making is not considered part of the traditional portfolio of patients' rights. The EU AI Act also does not contain such a right. The General Data Protection Regulation (GDPR) does, however, provide for the right 'not to be subject to a decision based solely on automated processing' in Article 22. At the same time, this provision has been severely critiqued in legal scholarship because of its lack of practical effectiveness. However, in December 2023, the Court of Justice of the EU first provided an interpretation of this right in C-634/21 (SCHUFA)-although in the context of credit scoring. Against this background, this article provides a critical analysis of the application of Article 22 GDPR to the medical context. The objective is to evaluate whether Article 22 GDPR may provide patients with the right to refuse automated medical decision-making. It proposes a health-conformant reading to strengthen patients' rights in the EU.

Research on personal credit scoring model based on deep learning

The increasing integration of internet technology and the financial industry has led to the gradual replacement of traditional credit evaluation models with those based on deep learning, which have demonstrated excellent accuracy. This has become a prominent area of research. Nevertheless, the credit scoring model based on a deep neural network encounters significant challenges in terms of its applicability in the field of credit scoring, largely due to the opaque nature of its learning and decision-making processes. The application of deep learning to personal credit scoring has been shown to enhance the accuracy of the resulting scores by leveraging large amounts of data. The model employs a deep neural network (DNN) architecture that integrates multiple input features, including the user's transaction history, social behaviour and other relevant data. The model is trained using supervised learning, with a large amount of labelled data used to optimise its prediction performance. Experimental results demonstrate that the deep learning-based model exhibits a notable improvement in accuracy and robustness compared to traditional credit scoring models.

An enhanced consensus algorithm for blockchain

Consensus plays a crucial role in blockchain technology, with the delegated proof of stake (DPoS) consensus mechanism commonly utilized in both public and hybrid chains. However, the current DPoS mechanism faces challenges such as low node engagement in voting and potential security risks posed by malicious nodes. In response, we propose the DL-DPoS (deep link–delegated proof of stake) mechanism, which builds upon the DPoS framework. The DL-DPoS incorporates the LINK incentive mechanism to encourage inactive nodes to participate in voting and leader selection. Furthermore, a comprehensive credit scoring system based on wealth, performance, and stability is introduced to enhance the security of elected nodes. The verification process is optimized to involve all nodes except the leader node, and mechanisms are in place to handle malicious attacks by degrading or removing offending nodes and redistributing their responsibilities to the LINK group. Performance testing of the DL-DPoS mechanism, conducted through blockchain simulation tests using the GO language, shows a 23% increase in throughput compared to DPoS, with over 95% node participation and improved distribution of rights and equity. These results indicate the enhanced performance, security, and stability of the DL-DPoS consensus mechanism.

Promoting financial inclusion for SMEs: Leveraging AI and data analytics in the banking sector

Financial inclusion is crucial for the growth and sustainability of small and medium-sized enterprises (SMEs), which are significant contributors to economic development and job creation. However, traditional banking models often fall short in serving the unique needs of SMEs due to perceived high risks and insufficient credit history. Leveraging artificial intelligence (AI) and data analytics, the banking sector can transform its approach to financial inclusion, offering tailored financial products and services that cater specifically to SMEs. AI and data analytics enable banks to analyze vast amounts of data from diverse sources, including transactional histories, social media activity, and market trends. This holistic view of an SME's financial health and business potential allows for more accurate risk assessment and credit scoring. Machine learning algorithms can identify patterns and predict creditworthiness, enabling banks to extend credit to SMEs that may have been overlooked by traditional models. Additionally, AI-driven insights facilitate the development of customized financial products, such as flexible loan terms and dynamic interest rates, that align with the cash flow cycles and operational realities of SMEs. Automated processes and AI-powered chatbots enhance customer service, providing SMEs with timely support and financial advice, thereby improving their banking experience. Data analytics also play a critical role in fraud detection and prevention, ensuring the security of transactions and building trust among SME clients. By continuously monitoring and analyzing transaction data, banks can quickly identify and mitigate fraudulent activities, protecting SMEs from financial losses. Moreover, AI and data analytics support the creation of financial literacy programs tailored to the specific needs of SMEs, empowering business owners with the knowledge and tools to make informed financial decisions. This educational aspect is vital in fostering a sustainable financial ecosystem for SMEs. In conclusion, the integration of AI and data analytics in the banking sector holds significant promise for promoting financial inclusion among SMEs. By providing more accessible, customized, and secure financial services, banks can support the growth and success of SMEs, ultimately contributing to broader economic development and financial stability.

A comprehensive analysis of LSTM techniques for predicting financial market

The “Financial Engineering” has revolutionized the financial industry by integrating mathematics, finance, economics, statistics, and computational tools to solve complex problems like risk management and portfolio optimization. This interdisciplinary approach has given rise to “AI in Finance”, merging the quantitative techniques of financial engineering with AI’s data-driven capabilities. In this survey, we explore concrete examples of their real-world impact. One such example involves a leading investment firm using machine learning algorithms to analyze market sentiments for informed trading decisions, resulting in significant returns. Additionally, AI-driven credit scoring models are expanding financial access by accurately assessing creditworthiness, especially for underserved populations. Natural language processing algorithms are also employed to parse financial news and social media data, providing investors with timely insights to navigate volatile markets effectively. These advancements highlight the transformative potential of financial engineering and AI in finance. By optimizing investment strategies and mitigating risks, they drive innovation and resilience in today’s dynamic financial landscape. From algorithmic trading to credit risk assessment and market sentiment analysis, the fusion of these disciplines is reshaping traditional paradigms and shaping the future of finance.

A Fast Survival Support Vector Regression Approach to Large Scale Credit Scoring via Safe Screening.

Survival models have found wider and wider applications in credit scoring recently due to their ability to estimate the dynamics of risk over time. In this research, we propose a Buckley-James safe sample screening support vector regression (BJS4VR) algorithm to model large-scale survival data by combing the Buckley-James transformation and support vector regression. Different from previous support vector regression survival models, censored samples here are imputed using a censoring unbiased Buckley-James estimator. Safe sample screening is then applied to discard samples that guaranteed to be non-active at the final optimal solution from the original data to improve efficiency. Experimental results on the large-scale real lending club loan data have shown that the proposed BJS4VR model outperforms existing popular survival models such as RSFM, CoxRidge and CoxBoost in terms of both prediction accuracy and time efficiency. Important variables highly correlated with credit risk are also identified with the proposed method.

A comprehensive study of coefficient signs in weighted logistic regression

In this paper, we explore the coefficient signs in weighted logistic regression, a variation of logistic regression that includes positive weights and is commonly used for handling uneven data sets and reject inference in credit scoring. Initially, we examine simple weighted logistic regression. Assuming full rank and overlap, we demonstrate that the slope's sign matches the sign of the difference in weighted averages of the independent variable across two groups, 1 and 0. We extend this analysis to multiple weighted logistic regression by employing two vectors: one representing the slopes and the other the differences in weighted averages of the independent variables across the groups. We establish that if one vector is zero, the other must also be zero. Additionally, we prove that if the slope vector isn't zero, the angle between these vectors will be acute. Our theoretical results can serve as a preliminary step prior to feature selection, which is important in logistic regression. Our numerical analysis further illustrates how our theoretical results can be applied to the well-known German Credit Data for reject inference. Additionally, we provide a detailed explanation of feature selection in our analysis.

Leveraging Artificial Intelligence and Machine Learning for Digital Transformation in the Banking Sector

Over the years, technology has revolutionized our world. It has changed our lives from barter system to currency system, and now it has upgraded to Artificial Intelligence powered system. It has also changed the way we think, the way we communicate, the way we bank and transact. The technology is getting better and smarter day-by-day leading human life become easier, faster, and convenient. In this digitalized era, like all other industrial sectors, it has become imperative for banking sectors to embrace digital transformation and to adopt new technologies like artificial intelligence and machine learning. Banks that fail to make the leap to digital transformation will risk being overtaken by competition and deserted by their customers.This paper provides a detailed review about Artificial Intelligence and Machine learning in banking, covering key areas such as customer services, fraud detection, personalised banking services, credit scoring, operational efficiency, and sophisticated product development.

Machine Learning and Artificial Intelligence Method for FinTech Credit Scoring and Risk Management

The ever-changing landscape of financial technology has undergone significant changes owing to advancements in machine learning, artificial intelligence, blockchains, and digitalization. These changes have had a profound impact on the provision of financial services, specifically, credit scoring and lending. This study examines the intersection of financial technology, artificial intelligence, machine learning, blockchain, and digitalization in the context of credit services with a focus on credit scoring and lending. This study addressed three main research questions: The research followed a comprehensive methodology, considering factors such as population, intervention, comparison, outcomes, and setting to ensure that collected data aligns with research objectives. The research questions were structured using the PICOS framework, and the PRISMA model was used for the systematic review and study selection. The publications analysed covered a wide range of datasets and methodologies.

Using Grocery Data for Credit Decisions

Many consumers across the world struggle to gain access to credit because of their lack of credit scores. This paper explores the potential of a new alternative data source, grocery transaction data, for evaluating consumers’ creditworthiness. Our analysis takes advantage of a unique, individual-level match of credit card data and supermarket loyalty card data. By developing credit scoring algorithms that either exclude or include grocery data, we illustrate both the incremental value of grocery data for credit decisions and its boundary conditions. We demonstrate that signals from grocery data can improve credit approval decisions, particularly for individuals who lack traditional credit scores. Furthermore, as a consumer establishes a relationship with lenders and builds a credit history, the marginal value of incorporating grocery data diminishes. These findings highlight the potential of grocery data in informing credit decisions and, consequently, in enabling financial institutions to extend credit to consumers who lack traditional credit scores. This paper was accepted by David Simchi-Levi, marketing. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2022.02364 .

XGBoost-B-GHM: An Ensemble Model with Feature Selection and GHM Loss Function Optimization for Credit Scoring

Credit evaluation has always been an important part of the financial field. The existing credit evaluation methods have difficulty in solving the problems of redundant data features and imbalanced samples. In response to the above issues, an ensemble model combining an advanced feature selection algorithm and an optimized loss function is proposed, which can be applied in the field of credit evaluation and improve the risk management ability of financial institutions. Firstly, the Boruta algorithm is embedded for feature selection, which can effectively reduce the data dimension and noise and improve the model’s capacity for generalization by automatically identifying and screening out features that are highly correlated with target variables. Then, the GHM loss function is incorporated into the XGBoost model to tackle the issue of skewed sample distribution, which is common in classification, and further improve the classification and prediction performance of the model. The comparative experiments on four large datasets demonstrate that the proposed method is superior to the existing mainstream methods and can effectively extract features and handle the problem of imbalanced samples.

Credit Risk Assessment Using a Combined Approach of Supervised and Unsupervised Learning

In the financial industry, credit scoring is a crucial tool for assessing credit risk. The study aims to enhance the accuracy and reliability of credit scoring by combining supervised and unsupervised learning methods. We propose an integrated model that combines Kohonen's Self-Organizing Maps (SOM) with the Random Forest algorithm to provide a more comprehensive analysis of credit card user data. Key features for model training were identified through feature selection and extraction. Experimental results show that the integrated model improved the AUC from 0.82 to 0.89, increased user satisfaction from a score of 3.8 to 4.35, and boosted usage rates by 12.5%. Additionally, the integrated model significantly enhanced the discrimination and prediction accuracy of user credit risk. These findings indicate that the combination of unsupervised learning with Kohonen's Self-Organizing Maps and supervised learning with Random Forest can effectively improve the accuracy of credit scoring, providing financial institutions with a more reliable tool for credit risk assessment.

LG-GNN: Local and Global Information-aware Graph Neural Network for default detection

Default detection, a crucial aspect of individual credit scoring, has attracted considerable attention in research. Previous approaches typically focus on classifying applicants using only explicit attributes, overlooking the importance of latent relations among them. Concurrently, graph-based techniques have emerged as promising tools for credit scoring. However, existing graph-based methods often need to be more accurate in aggregating information from limited neighbors, which can lead to misclassification when the target node has differently labeled neighbors. Motivated by these challenges, we propose a Local and Global Information-aware Graph Neural Network (LG-GNN) approach for default detection. By leveraging the loan applicant relation graph, LG-GNN dynamically learns the representation of the target node from both local and global perspectives. Furthermore, it adaptively fuses the information from these perspectives and employs contrastive learning to enhance feature variations. Extensive experiments demonstrate the superiority of LG-GNN over mainstream methods across several widely used default detection datasets. Specifically, LG-GNN achieves an average relative performance improvement of 47.9% compared to baselines. Moreover, compared to the most competitive default detection methods, LG-GNN exhibits an average performance improvement of 11.9%. Our code is publicly available at https://github.com/BERA-wx/LG-GNN.

Assessing the implementation and effectiveness of China’s social credit system of the construction industry: a case study of Nanjing

Construction contractor evaluation is the first step in ensuring the successful completion of a project. Nowadays, the Chinese government has developed a social credit system (SCS) and proposed contractors’ credit scores as an additional factor to facilitate bidding decisions. Using Nanjing as a case study, this article investigates the status quo of construction contractors’ credit scoring. It evaluates how credit scores have impacted the public procurement of construction projects. This article utilizes data-driven approaches and conducts different statistical analyses based on the bidding results of 15,094 public projects and the credit scores of over 6,000 registered construction companies from 2014 to 2021. The results show that (1) around half the companies had no credit-changing activities; (2) credit scores are important when companies are bidding for medium, large, and extra-large projects; (3) large companies are more likely to have better credit ratings; and (4) credit scores have a significant impact on revenue generation. This article provides a basis for understanding the status quo and effectiveness of the SCS implementation in the Chinese construction industry and evaluating its impact on the public procurement of construction projects, which are often concerns of researchers, policymakers, and industry practitioners.

Application of business intelligence under deep neural network in credit scoring of bank users

This paper aims to improve the level of social credit system and the accuracy and efficiency of bank users’ credit scoring by using business intelligence technology based on deep neural network (DNN). Firstly, based on the theory of personal credit evaluation factors, a comprehensive credit evaluation factor system is constructed, taking into account social and economic background, consumption habits, behavior patterns and other factors. Meanwhile, back propagation neural network (BPNN) theory is introduced as the core method of modeling to cope with the nonlinear relationship in the credit scoring task and the demand of large-scale data processing. Secondly, by analyzing the operation process of BPNN in detail, the specific application in credit scoring model is emphasized. Finally, on the basis of theory and operation, this paper implements a credit scoring model for bank users based on BPNN theory. The experimental results show that the model realized in this paper can automatically discover the key attributes and internal rules in the sampled data, and adjust the weight and threshold of the network by modifying the parameters and network structure to meet the expected requirements. The accuracy of the credit score of the predicted sample data reaches 99.5%, and the prediction error is very small, which has a good prediction effect. This paper provides a feasible solution for business intelligence and DNN in the field of credit scoring, and also provides strong empirical support for improving the level of social credit system.

Who gets the money? A qualitative analysis of fintech lending and credit scoring through the adoption of AI and alternative data

Credit scoring plays an important role in determining the accessibility of credit in the financial sector. This in turn has a significant impact on how economic opportunities are distributed. Our study examines the use of AI and alternative data in fintech lending through the lens of Information Asymmetry Theory. By employing a qualitative research design using the Gioia method, we extract, analyze, and synthesize insights from a diverse group of 26 experts in fintech lending, artificial intelligence, machine learning, data science, and academia. Our results reveal several important findings: the enhancement of predictive proficiency and risk management, the decrease in default rates, the extension of credit access by including previously ‘unbanked populations’, the introduction of real-time creditworthiness assessment and new business models for entrepreneurs, the enhancement of credit market efficiencies and positive effects on the stability of financial markets. In addition, our study highlights the necessity for rigorous and critical ethical considerations of important challenges such as the question of consent, algorithmic transparency, data quality, data misuse, representativeness, traceability, responsibility, bias and discrimination. The reasonable goal of a more fair, resilient, sustainable and accessible credit system will require a joint effort to balance leveraging technological innovations with respecting peoples' right to privacy.