Jul 2026· Advances in Economics, Management and Political Sciences· 0 citations
TL;DR
The paper shows that ensemble learning models have superior predictive power and argues that behavioral data complement traditional datasets for underbanked populations, such as "credit invisibles," and makes a strong case for XAI being essential for model transparency, combating bias, and meeting regulatory requirements.
Abstract
Credit risk management (CRM) is a fundamental pillar of financial systems, attracting attention from practitioners and researchers. Traditional credit assessment methods have limitations in today's complex, fast-changing financial environment. Advances in machine learning (ML) and behavioral data analytics offer new possibilities for improving CRM through better models and performance. This paper provides a systematic review of ML applications in credit default prediction and early warning systems, critically synthesizing recent literature. It discusses three major dimensions: the evolution of ensemble learning algorithms, the use and issues of behavioral data in feature engineering, and advances in model explainability (XAI). The paper shows that ensemble learning models have superior predictive power and argues that behavioral data complement traditional datasets for underbanked populations, such as "credit invisibles." It makes a strong case for XAI being essential for model transparency, combating bias, and meeting regulatory requirements. The review also addresses class imbalance, data privacy, and ethical issues, with mitigation strategies. The review offers theoretical guidance and practical implications for financial institutions to improve risk control and build reliable early warning systems, outlining directions for future research.
Credit risk assessment forms a cornerstone of banking risk management and the stability of the wider financial system. Over the past decade, the rapid development of machine learning (ML) techniques has substantially enhanced traditional credit risk assessment methodologies. ML has now emerged as a core technological pillar for the banking sector, strengthening risk identification capabilities, optimising credit decision-making, and advancing financial inclusion. Conventional credit scoring models, dominated by logistic regression (LR) and scorecard approaches, offer inherent strengths in interpretability and regulatory compliance. However, constrained by their linear assumptions, these methods struggle to capture complex non-linear relationships within credit data and deliver insufficient predictive accuracy for the “credit-invisible” population lacking formal credit histories. This paper presents a systematic literature review (SLR) of ML applications in credit risk assessment (CRA), covering publications from January 2016 to May 2026. A total of 894 papers were retrieved from five digital libraries, and following a rigorous multi-stage screening process, 129 studies were selected for final inclusion. Our analysis reveals that tree-based ensemble models and deep learning (DL) architectures predominate in contemporary research in this field. Meanwhile, post hoc explanation methods and machine learning operations (MLOps) are gaining significant traction as solutions to address fairness, transparency, and system maintenance challenges in real-world production environments. We synthesise prevailing methodologies into a unified end-to-end credit risk modelling framework spanning data preprocessing, feature engineering, model training, evaluation, and operational deployment. Through a critical assessment of the advantages, limitations, and inherent trade-offs of existing approaches, this SLR not only identifies current research gaps and future directions for the academic community, but also provides practical guidance for the banking sector to build compliant, fair, and efficient intelligent risk assessment systems.
Bolun Zhang, Jun Luo, Ruobing Wu et al.· Journal of Risk and Financia...· 0 citations
Credit risk assessment underpins lending decisions, pricing strategies, portfolio management, and regulatory capital allocation within modern financial systems. Logistic regression has historically served as the dominant modeling framework in credit scoring due to its probabilistic coherence and interpretability. In recent years, advances in machine learning—particularly tree-based ensemble methods such as Random Forest and Gradient Boosting—have demonstrated strong predictive performance and often outperform traditional approaches in discrimination metrics such as the area under the ROC curve (AUC). However, the adoption of machine learning in credit risk modeling remains debated due to concerns regarding probability calibration, temporal robustness, interpretability, and regulatory governance. This paper provides a comprehensive comparison of traditional statistical models and tree-based machine learning approaches in credit risk assessment. Rather than focusing exclusively on discriminatory performance, the analysis adopts a multidimensional evaluation framework incorporating calibration quality and temporal stability. Drawing on foundational theory and recent empirical evidence, the paper argues that model adequacy in credit risk is inherently context dependent. A three-pillar framework—discrimination, calibration, and temporal robustness—is proposed to guide academic research and practical model deployment. The findings suggest that superior ranking performance does not necessarily imply superior decision quality and that effective credit risk modeling requires balancing predictive flexibility with probabilistic reliability and governance stability.
The integration of machine learning into accounting has advanced predictive analytics, yet the optimal fusion of structured financial data (“hard data”) and textual sentiment (“soft data”) remains ambiguous. This study addresses this gap by examining whether appending lowdimensional text features to strong predictive models enhances accuracy.
Using an XGBoost model trained on financial ratios from 10-K reports, we compare its performance against a naive hybrid model incorporating Loughran-McDonald (2011) dictionary-based sentiment features from the Management Discussion & Analysis (MD&A) section.
Empirical results reveal a “Signal Dilution Effect”: the hybrid model statistically underperforms the pure structured-data model. SHAP value analysis confirms that while structured ratios dominate predictive contributions, naive text concatenation introduces noise that degrades the performance of advanced non-linear classifiers.
This research contributes to accounting analytics by cautioning against indiscriminate feature stacking and advocating for separated processing strategies in financial prediction systems.
Maysoon Khoja· Journal of Administrative an...· 0 citations
Financial risk assessment is essential in handling uncertainties and complexities in modern financial systems. Traditional statistical models often struggle with nonlinear relationships and dynamic market conditions. This paper explores the application of data science techniques—such as machine learning, deep learning, and big data analytics—in evaluating various financial risks, including credit, market, operational, and systemic risks. The proposed framework integrates data preprocessing, feature engineering, predictive modeling, and explainability to enhance decision-making and regulatory compliance. Experimental insights show that models like random forests, gradient boosting, SVMs, and neural networks provide better predictive accuracy and early warning capabilities compared to traditional methods. However, challenges related to data quality, interpretability, and ethical concerns remain. Overall, data science is identified as a transformative approach to financial risk assessment when supported by proper governance and validation practices.
Daniel Rodríguez· International Journal of App...· 0 citations
Credit scoring is vital in modern banking for loan decisions, risk management, and financial inclusion. Traditional models rely on limited, static financial data and struggle to adapt to changing conditions. This paper proposes an AI-based credit scoring approach that uses machine learning, deep learning, and hybrid models to improve accuracy and scalability. The framework integrates financial data with alternative data such as transaction behavior, digital footprints, and repayment patterns. Techniques like decision trees, random forests, SVMs, gradient boosting, and neural networks are analyzed and compared with traditional methods. It also emphasizes explainable AI (XAI) to ensure transparency, fairness, and regulatory compliance. Results show that AI models outperform conventional approaches in accuracy and risk prediction. The study highlights the importance of interpretability, bias reduction, and strong governance, concluding that AI-driven credit scoring enhances smart banking, customer experience, and financial inclusion.
L. O'Connor· International Journal of Art...· 0 citations
Machine learning is widely used to improve predictive accuracy in complex domains like credit scoring, but many models (e.g., deep neural networks) remain opaque. This lack of interpretability is problematic in regulated domains (banking, finance) where transparency is required. Rule-based learning methods, such as Learning Classifier Systems (LCS), offer a trade-off between accuracy and explainability. We introduce a novel Ranked Attribute Selection with Midpoint Filtering (RASF) framework that extends LCS (EXTRACS) to enhance feature selection and rule validation for credit approval. RASF first ranks features by mutual information, then employs rank-guided randomized selection to diversify rule conditions, and finally filters new rules by midpoint-based Euclidean distance to the current instance. We evaluate RASF-enhanced LCS on public loan approval datasets, comparing against a baseline LCS and logistic regression. Results show that RASF improves predictive accuracy by about 3.6 – 4.64% over the base LCS, while producing an inherently interpretable rule set. By bridging accuracy and transparency, RASF-LCS supports explainable AI in credit scoring.
M. Ahamed, Abubakar Siddique, Trung Nguyen et al.· Proceedings of the Genetic a...· 0 citations