Credit Scoring Research Articles

Textual analysis and credit scoring: a new matrix factorization approach

Credit scoring models are important for financial institutions’ credit decisions. This study examined how variables are extracted from loan statements and whether textual variables can improve the accuracy of the default model. We used a combination of forward selection and non-negative matrix factorization to extract variables from loan statements. We also built a credit scoring model using both loan statement and numerical data. The results show that in the comparative analysis, the credit scoring model built using the optimal cut-off logistic regression model and the two types of data had the highest accuracy. Moreover, compared with the credit scoring model constructed using the deep learning method based on word vectors, the credit scoring model in this study had better interpretation. The regression analysis revealed that the variables from the loan statement have a significant effect on the default status.

Integrating traditional and non-traditional model risk frameworks in credit scoring

Background: An improved understanding of the reasoning behind model decisions can enhance the use of machine learning (ML) models in credit scoring. Although ML models are widely regarded as highly accurate, the use of these models in settings that require explanation of model decisions has been limited because of the lack of transparency. Especially in the banking sector, model risk frameworks frequently require a significant level of model interpretability.Aim: The aim of the article is to evaluate traditional model risk frameworks to determine their appropriateness when validating ML models in credit scoring and enhance the use of ML models in regulated environments by introducing a ML interpretability technique in model validation frameworks.Setting: The research considers model risk frameworks and regulatory guidelines from various international institutions.Method: The research is qualitative in nature and shows how through integrating traditional and non-traditional model risk frameworks, the practitioner can leverage trusted techniques and extend traditional frameworks to address key principles such as transparency.Results: The article proposes a model risk framework that utilises Shapley values to improve the explainability of ML models in credit scoring. Practical validation tests are proposed to enable transparency of model input variables in the validation process of ML models.Conclusion: Our results show that one can formulate a comprehensive validation process by integrating traditional and non-traditional frameworks.Contribution: This study contributes to existing model risk literature by proposing a new model validation framework that utilises Shapley values to explain ML model predictions in credit scoring.

The Manifestation and Implications of Bias in Artificial Intelligence on Global Society

Although artificial intelligence (AI) is becoming more and more prevalent, biases from data, algorithms, and feedback loops might still exist. Marginalized groups may be disproportionately affected by these biases, which may result in biased outcomes in areas such as facial recognition, credit scoring, and hiring. Reduced trust, sustained societal inequality, and stifled innovation are some of the effects. It is critical to support transparent development processes, diverse development teams, and ethical oversight in AI design in order to lessen these effects. If these issues are resolved, AI will become a more equitable instrument for advancing society.

Ethical Implications of AI in Financial Services: Bias, Transparency, and Accountability

This article examines the ethical implications of artificial intelligence (AI) in financial services, focusing on issues of bias, transparency, and accountability. As AI adoption in finance grows rapidly, with 85% of institutions now using AI, it brings both tremendous benefits and significant ethical challenges. The article explores how AI can perpetuate biases in lending and credit scoring, the "black box" problem of opaque AI decision-making, and the complexities of establishing accountability for autonomous AI systems. It analyzes strategies for mitigating these issues, including developing interpretable AI models, implementing robust governance structures, and creating industry-specific ethical guidelines. The discussion highlights the critical need for evolving regulatory frameworks and ethical standards to ensure responsible AI use while harnessing its potential to transform financial services.

The power of satellite imagery in credit scoring: a spatial analysis of rural loans

The power of satellite imagery in credit scoring: a spatial analysis of rural loans

HARVESTING INSIGHTS: THE ROLE OF ARTIFICIAL INTELLIGENCE IN TRANSFORMING AGRICULTURAL FINANCE

The intersection of artificial intelligence (AI) and agricultural finance has emerged as a transformative force in enhancing the efficiency and sustainability of farming practices. This review article explores the multifaceted applications of AI technologies in agricultural finance, focusing on credit scoring, risk assessment, and financial decision-making for farmers and agricultural businesses. We examine the integration of machine learning algorithms and big data analytics in providing tailored financial products, enabling precision agriculture, and improving access to credit in under banked communities. By synthesizing current literature and case studies, we identify key challenges and opportunities, such as the need for data security, transparency, and the democratization of AI tools in rural finance. Furthermore, we discuss the potential of AI to address climate change impacts on agriculture and its implications for financing sustainable practices. This article aims to provide stakeholders in the agricultural finance sector—policymakers, financial institutions, and technology developers—with a comprehensive understanding of how AI can drive innovation and improvement in financing agricultural activities, ultimately fostering a resilient and sustainable food system.

Finance Modeling Approach Using Machine Learning

The integration of machine learning (ML) into financial modeling represents a transformative shift in the finance sector, enhancing analytical capabilities and decision-making processes. This article explores the fundamental concepts of financial modeling and machine learning, illustrating how ML methodologies—both supervised and unsupervised—improve traditional financial models by enabling the analysis of extensive datasets to uncover intricate patterns. By leveraging historical data, ML enhances predictive accuracy in various applications, including risk assessment, algorithmic trading, credit scoring, and fraud detection. The article highlights significant advancements in predictive analytics through techniques such as regression analysis and time series forecasting, which allow financial analysts to navigate market uncertainties more effectively. Moreover, the automation of data processing and feature engineering through ML leads to increased operational efficiency, reducing human error and enhancing real-time decision-making capabilities. However, challenges such as data quality issues, model interpretability, and ethical considerations regarding algorithmic bias necessitate careful management to ensure responsible implementation. The article emphasizes the importance of transparency in ML models to foster trust among stakeholders while meeting regulatory requirements. Future research directions are proposed, focusing on the integration of explainable AI with blockchain technology and the implications of big data analytics on ML models. By addressing these emerging challenges and opportunities, finance professionals can leverage advanced analytical tools to drive innovation and enhance strategic initiatives in an increasingly complex financial landscape. Ultimately, this article underscores the pivotal role of machine learning in reshaping financial modeling practices and its potential to redefine the future of finance.

A submodular optimization approach to trustworthy loan approval automation

AbstractIn the field of finance, the underwriting process is an essential step in evaluating every loan application. During this stage, the borrowers' creditworthiness and ability to repay the loan are assessed to ultimately decide whether to approve the loan application. One of the core components of underwriting is credit scoring, in which the probability of default is estimated. As such, there has been significant progress in enhancing the predictive accuracy of credit scoring models through the use of machine learning, but there still exists a need to ultimately construct an approval rule that takes into consideration additional criteria beyond the score itself. This construction process is traditionally done manually to ensure that the approval rule remains interpretable to humans. In this paper, we outline an automated system for optimizing a rule‐based system for approving loan applications, which has been deployed at Hyundai Capital Services (HCS). The main challenge lays in creating a high‐quality rule base that is simultaneously simple enough to be interpretable by risk analysts as well as customers, since the approval decision should be easily understandable. We addressed this challenge through principled submodular optimization. The deployment of our system has led to a 14% annual growth in the volume of loan services at HCS, while maintaining the target bad rate, and has resulted in the approval of customers who might have otherwise been rejected.

Juxtaposing Gender Differentials in Credit Assessment of Farmers in Nigeria: A Hybridized Credit-Scoring Approach

Using data from 360 smallholder farmers in Southeast Nigeria, the study creates the architecture for a new farmer's hybrid credit rating system used in classifying farmers who applied for microfinance loans based on their creditworthiness. We discovered new evidence that the hybridized credit scoring algorithm demonstrated unprecedented concordance in assessing the financial viability of farmers along gender lines. The discriminant analysis, in particular, closely aligned with the credit score model, with 34.4% and 46.7% of male and female farmers grouped as creditworthy, reflecting the model's estimates of 33.3% and 45.5%, indicating gaps of 12.3% and 12.2%, respectively, to the advantage of the female farmers. Our findings further suggest that annual income, marital status, and farm size strongly influence the separation between creditworthy and non-creditworthy farmers. While age, loan term, and a history of defaults had a negative impact on discrimination, in light of the findings, we recommend a collaboration between authorities, financial institutions, and extension workers in offering tailored trainings to both male and female farmers, assisting them in meeting up-to-date credit prerequisites, adopting modified farming techniques, and improving their general preparedness to be accepted for loans in this changing credit evaluation landscape so as to bridge the disparity and promote financial inclusion for farmers irrespective of gender affiliations.

Algorithm Comparison for Data Mining Classification: Assessing Bank Customer Credit Scoring Default Risk

Algorithm Comparison for Data Mining Classification: Assessing Bank Customer Credit Scoring Default Risk

Character Counts: Psychometric-Based Credit Scoring for Underbanked Consumers

Psychometric-based credit scores measure important personality traits that are characteristic of good borrowers’ behaviors. While such data can potentially improve credit models for underbanked consumers, the utility of psychometric data in consumer lending is still largely understudied. The present study contributes to the literature in this respect, as it is one of the first studies to evaluate the efficacy of psychometric-based credit scores for predicting future loan defaults among underbanked consumers. The results from two culturally diverse samples of loan applicants (Sub-Saharan Africa, n = 1113; Western Europe, n = 1033) found that psychometric scores correlated significantly with future loan defaults (Gini = 0.28–0.31) and were incrementally valid above and beyond the banks’ own credit scorecards. These results highlight the theoretical basis for personality in financial behaviors, as well as the practical utility that psychometric scores can have for credit decisioning in general and the facilitation of financial inclusion for underbanked consumer groups in particular.

Incorporating Digital Footprints into Credit-Scoring Models through Model Averaging

Digital footprints provide crucial insights into individuals’ behaviors and preferences. Their role in credit scoring is becoming increasingly significant. Therefore, it is crucial to combine digital footprint data with traditional data for personal credit scoring. This paper proposes a novel credit-scoring model. First, lasso-logistic regression is used to select key variables that significantly impact the prediction results. Then, digital footprint variables are categorized based on business understanding, and candidate models are constructed from various combinations of these groups. Finally, the optimal weight is selected by minimizing the Kullback–Leibler loss. Subsequently, the final prediction model is constructed. Empirical analysis validates the advantages and feasibility of the proposed method in variable selection, coefficient estimation, and predictive accuracy. Furthermore, the model-averaging method provides the weights for each candidate model, providing managerial implications to identify beneficial variable combinations for credit scoring.

A hybrid metaheuristic optimised ensemble classifier with self organizing map clustering for credit scoring

A hybrid metaheuristic optimised ensemble classifier with self organizing map clustering for credit scoring

Clinical Reasoning Skills Among Second-Phase Medical Students in West Bengal, India: An Exploratory Study.

Introduction Proper application of clinical reasoning skills is essential to reduce diagnostic and management errors. Explicit inclusion of training and assessment of clinical reasoning skills is the demand of time. The study intended to measure the clinical reasoning skills of second-phase undergraduate students in a medical college inWest Bengal, India, and its distribution across several individual variables. Methods The clinical reasoning skills of 105 undergraduate medical students were assessed in a cross-sectional exploratory study using key feature questions (KFQs) with the partial credit scoring system. Six case vignettes aligned to the core competencies in the subject of pharmacology, pathology, and microbiology were designed and validated by the subject material experts for this purpose. The responses of the participants were collected through Google Forms (Google, Mountain View, CA) after obtaining written informed consent. The scores obtained in all KFQs were added and expressed in percentage of the maximum attainable score. Results The mean (±SD) clinical reasoning score of the participants was 42.5 (±12.6). Only 29.6% of respondents scored ≥ 50. Students with higher subjective economic status (p-value = 0.01) and perceived autonomy (p-value < 0.001) were more likely to have higher clinical reasoning scores. The marks obtained in previous summative examinations were significantly correlated with clinical reasoning scores. Conclusion Average score < 50.0 and inability to score ≥ 50.0 by more than two-thirds of the participants reflected the deficit in the clinical reasoning skills of second-phase MBBSstudents. The association of clinical reasoning skills with economic status, autonomy, and previous academic performances needs further exploration.

Comparing logistic regression and neural networks for predicting skewed credit score: a LIME-based explainability approach

Over the past years, machine learning emerged as a powerful tool for credit scoring, producing high-quality results compared to traditional statistical methods. However, literature shows that statistical methods are still being used because they still perform and can be interpretable compared to neural network models, considered to be black boxes. This study compares the predictive power of logistic regression and multilayer perceptron algorithms on two credit-risk datasets by applying the Local Interpretable Model-Agnostic Explanations (LIME) explainability technique. Our results show that multilayer perceptron outperforms logistic regression in terms of balanced accuracy, Matthews Correlation Coefficient, and F1 score. Based on our findings from LIME, building models on imbalanced datasets results in biased predictions towards the majority class. Model developers in the field of finance could consider explanation methods such as LIME to extend the use of deep learning models to help them make well-informed decisions.

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.