Search Results (673)

Counterparty risk, which combines market and credit risks, gained prominence after the 2008 financial crisis due to its complexity and systemic implications. Traditional management methods, such as netting and collateralization, have become computationally demanding under frameworks like the Fundamental Review of the Trading Book (FRTB). This paper explores the combined application of Gaussian process regression (GPR) and Bayesian quadrature (BQ) to enhance the efficiency and accuracy of counterparty risk metrics, particularly credit valuation adjustment (CVA). This approach balances excellent precision with significant computational performance gains. Focusing on fixed-income derivatives portfolios, such as interest rate swaps and swaptions, within the One-Factor Linear Gaussian Markov (LGM-1F) model framework, we highlight three key contributions. First, we approximate swaption prices using Bachelier’s formula, showing that forward-starting swap rates can be modeled as Gaussian dynamics, enabling efficient CVA computations. Second, we demonstrate the practical relevance of an analytical approximation for the CVA of an interest rate swap portfolio. Finally, the combined use of Gaussian processes and Bayesian quadrature underscores a powerful synergy between precision and computational efficiency, making it a valuable tool for credit risk management. Full article

The Solvency II regulatory framework requires European insurance companies to guarantee their solvability and stability by retaining enough Own Funds to cover future unexpected losses at a given confidence level. A Standard Formula approach is provided to estimate the capital requirement needed. Still, Solvency II allows internal methodologies to quantify the capital absorption arising from specific risk types or even to replace the Standard Formula with a full internal model. This work proposes a new internal model approach to measure the Catastrophe Recession Risk. The Recession Risk implies a mandatory capital absorption component for the insurance companies operating in the credit and suretyship business. The proposed model is based on the CreditRisk⁺ model and designed to behave countercyclically, aligning with the original intent of the European supervisory authority when first introducing this risk into the Solvency II risks’ taxonomy. Additionally, the model is applied to define an index for monitoring future recession crises based on the time series of past default rates. Full article

The key strategic point for facilitating domestic circulation is to enhance and expand household consumption. Based on a survey of 1080 farming households in Hunan, Hubei, and Jilin Provinces, this study examines the impact of digital finance use on the scale and structural upgrading of household consumption among farmers. The findings indicate that digital finance use effectively expands the scale of household consumption and promotes structural upgrades. The results remain robust through various endogenous and robust methods. Heterogeneity analysis reveals that the benefits of digital finance use are greater for middle- to high-income groups and those with lower education levels, indicating the presence of a digital divide effect. Furthermore, the construction of village communities, skill training, improvements in village logistics services, and the availability of medical clinic facilities can enhance the consumption-promoting effects of digital finance use. Mechanism analysis shows that digital finance primarily operates through alleviating credit constraints, enhancing risk prevention, and improving financial returns to influence the scale and structural upgrading of household consumption. This study provides policy insights for rural revitalization and unlocking the consumption potential of rural residents. Full article

The proposal of the energy-consuming right (ECR) market may lead to generation companies (GenCos) facing the risk of being overcharged due to the inaccurate calculation of carbon emission reduction, since it claims the same credit as the carbon market does. To estimate the carbon emission reduction accurately for the GenCos that participate in electricity, carbon, and ECR markets simultaneously, this paper proposes a market framework where a flexible exchange mechanism between the ECR and carbon markets is specially considered. To investigate the influence of the allocation and exchange of ECR and carbon credits on the behavior of GenCos that participate in multi-type markets, a bi-level model based on the leader–follower game theory is proposed. In the upper level of the proposed model, a decision problem for maximizing the profit of GenCos is developed, which is especially constrained to the primary allocation of ECR and carbon credits. While the multi-type market clearing model and an exchange mechanism between the ECR and carbon credits are proposed in the lower level of the model. The bi-level problem is converted into the mathematical program with equilibrium constraints (MPECs) through the Karush–Kuhn–Tucker (KKT) condition to solve. The results illustrate that the interaction between the ECR market and the carbon market can improve the energy efficiency and reduce the carbon emissions of GenCos. Full article

Climate risk refers to the risks associated with climate change and has already started to impact various sectors of the economy. In this work, we focus on the impact of physical risk on the probability of default for a firm in the agribusiness sector. The probability of default is estimated based on the Merton model, where the firm defaults when its asset value falls below the threshold defined by its liabilities. We study the relationship between the stock value of the firm and global surface temperature anomalies, observing that an increase in temperature negatively affects the stock value and, consequently, the asset value of the firm. A decrease in the asset value of the firm translates into an increase in its probability of default. We also propose a model to assess the exposure of the firm to transition risk. Full article

Over-indebtedness is an increasingly serious issue among young people in China. Using Atlas.ti, this study analyzes textual data from the online community “Debtors Avengers” on Douban.com, applying a combined framework of life cycle and credit liberalization hypotheses. The findings reveal that youth indebtedness is not solely driven by irrational consumer behavior but is closely linked to economic activities during specific life stages. Structurally, it reflects sociofinancial digitization and normalized credit use. Factors such as life circumstances, financial literacy, labor market instability, and public safety risks contribute to a “debt spiral”. Addressing these challenges requires the refinement of financial policies, enhanced education, and intervention in financial aggression. Full article

Despite the MFI insurgency, agricultural financing remains critically low, even though microcredit is widely accepted as both a substitute and compliment to formal credit. Zimbabwe is an agro-based economy and very little is known about the determinants of microcredit demand and microcredit size in smallholder resettled sugarcane farmers. Research is concentrated in short-term agriculture activities. Thus, this study aims to fill the unattended gap in lagged returns agriculture activities such as sugarcane production which takes at least a year to mature, hence, the greater need for agriculture financing alternatives such as microfinance. The study examined the determinants of both microcredit demand and loan size (magnitude of microcredit participation) by smallholder resettled A2 sugarcane farmers in Chiredzi. Primary data from 370 smallholder resettled sugarcane farmers (214 borrower participants and 156 non-borrower participants) were used. Probit and Tobit regression models were used for data analysis in STATA. Operational costs, interest rate, grace period, and land size significantly affect both the demand for microcredit and microcredit size, while education, household farming assets, extension services, and payback period significantly affect microfinance demand, and risk attitude/perception additionally determine microcredit size. Special microfinance schemes best suitable for the agriculture sector and crop/plant-specific agriculture financing schemes, currency, and macroeconomic stability are the major policy recommendations. Full article

This study addresses a significant gap in the literature by comparing the effectiveness of traditional statistical methods with artificial intelligence (AI) techniques in predicting bankruptcy among small and medium-sized enterprises (SMEs). Traditional bankruptcy prediction models often fail to account for the unique characteristics of SMEs, such as their vulnerability due to lean structures and reliance on short-term credit. This research utilizes a comprehensive database of 7104 Belgian SMEs to evaluate these models. Belgium was selected due to its unique regulatory and economic environment, which presents specific challenges and opportunities for bankruptcy prediction in SMEs. Our findings reveal that AI techniques significantly outperform traditional statistical methods in predicting bankruptcy, demonstrating superior predictive accuracy. Furthermore, our analysis highlights that a firm’s position within the Global Value Chain (GVC) impacts prediction accuracy. Specifically, firms operating upstream in the production process show lower prediction performance, suggesting that bankruptcy risk may propagate upward along the value chain. This effect was measured by analyzing the firm’s GVC position as a variable in the prediction models, with upstream firms exhibiting greater vulnerability to the financial distress of downstream partners. These insights are valuable for practitioners, emphasizing the need to consider specific performance factors based on the firm’s position within the GVC when assessing bankruptcy risk. By integrating both AI techniques and GVC positioning into bankruptcy prediction models, this study provides a more nuanced understanding of bankruptcy risks for SMEs and offers practical guidance for managing and mitigating these risks. Full article

The increasing population and emerging business opportunities have led to a rise in consumer spending. Consequently, global credit card companies, including banks and financial institutions, face the challenge of managing the associated credit risks. It is crucial for these institutions to accurately classify credit card customers as “good” or “bad” to minimize capital loss. This research investigates the approaches for predicting the default status of credit card customer via the application of various machine-learning models, including neural networks, logistic regression, AdaBoost, XGBoost, and LightGBM. Performance metrics such as accuracy, precision, recall, F1 score, ROC, and MCC for all these models are employed to compare the efficiency of the algorithms. The results indicate that XGBoost outperforms other models, achieving an accuracy of 99.4%. The outcomes from this study suggest that effective credit risk analysis would aid in informed lending decisions, and the application of machine-learning and deep-learning algorithms has significantly improved predictive accuracy in this domain. Full article

Credit scoring is a cornerstone of financial risk management, enabling financial institutions to assess the likelihood of loan default. However, widely recognized contemporary credit risk metrics, like FICO (Fair Isaac Corporation) or Vantage scores, remain proprietary and inaccessible to the public. This study aims to devise an alternative credit scoring metric that mirrors the FICO score, using an extensive dataset from Lending Club. The challenge lies in the limited available insights into both the precise analytical formula and the comprehensive suite of credit-specific attributes integral to the FICO score’s calculation. Our proposed metric leverages basic information provided by potential borrowers, eliminating the need for extensive historical credit data. We aim to articulate this credit risk metric in a closed analytical form with variable complexity. To achieve this, we employ a symbolic regression method anchored in genetic programming (GP). Here, the Occam’s razor principle guides evolutionary bias toward simpler, more interpretable models. To ascertain our method’s efficacy, we juxtapose the approximation capabilities of GP-based symbolic regression with established machine learning regression models, such as Gaussian Support Vector Machines (GSVMs), Multilayer Perceptrons (MLPs), Regression Trees, and Radial Basis Function Networks (RBFNs). Our experiments indicate that GP-based symbolic regression offers accuracy comparable to these benchmark methodologies. Moreover, the resultant analytical model offers invaluable insights into credit risk evaluation mechanisms, enabling stakeholders to make informed credit risk assessments. This study contributes to the growing demand for transparent machine learning models by demonstrating the value of interpretable, data-driven credit scoring models. Full article

Climate change exacerbates flood hazards, resulting in risks to real estate values that should be considered by long-term investors. Flood risk presents two major financial risks: market risk and credit risk. Market risk refers to potential property value loss, and credit risk increases the likelihood of mortgage defaults. However, methods and comprehensive data for quantifying global real estate flood risks are lacking. To address this problem, this paper proposes two flood risk assessment frameworks: the local-oriented approach (LOA) and global-oriented approach (GOA). Two hazard and three vulnerability assessment methods are also introduced to support these frameworks. The LOA vulnerability estimates of regions with complete records are required to support the GOA. Taiwan was selected as an example for the LOA assessment, and the results were used to estimate vulnerability overseas in GOA assessments. The results of case studies for buildings located in four cities in different countries were compared. The proposed framework enables investors and asset owners to globally quantify climate risks in real estate, even when the available data are incomplete. Users can choose the most appropriate approach on the basis of the available data and their tolerance for uncertainty. Full article

Predicting credit default risk is important to financial institutions, as accurately predicting the likelihood of a borrower defaulting on their loans will help to reduce financial losses, thereby maintaining profitability and stability. Although machine learning models have been used in assessing large applications with complex attributes for these predictions, there is still a need to identify the most effective techniques for the model development process, including the technique to address the issue of data imbalance. In this research, we conducted a comparative analysis of random forest, decision tree, SVMs (Support Vector Machines), XGBoost (Extreme Gradient Boosting), ADABoost (Adaptive Boosting) and the multi-layered perceptron, to predict credit defaults using loan data from LendingClub. Additionally, XGBoost was used as a framework for testing and evaluating various techniques. Moreover, we applied this XGBoost framework to handle the issue of class imbalance observed, by testing various resampling methods such as Random Over-Sampling (ROS), the Synthetic Minority Over-Sampling Technique (SMOTE), Adaptive Synthetic Sampling (ADASYN), Random Under-Sampling (RUS), and hybrid approaches like the SMOTE with Tomek Links and the SMOTE with Edited Nearest Neighbours (SMOTE + ENNs). The results showed that balanced datasets significantly outperformed the imbalanced dataset, with the SMOTE + ENNs delivering the best overall performance, achieving an accuracy of 90.49%, a precision of 94.61% and a recall of 92.02%. Furthermore, ensemble methods such as voting and stacking were employed to enhance performance further. Our proposed model achieved an accuracy of 93.7%, a precision of 95.6% and a recall of 95.5%, which shows the potential of ensemble methods in improving credit default predictions and can provide lending platforms with the tool to reduce default rates and financial losses. In conclusion, the findings from this study have broader implications for financial institutions, offering a robust approach to risk assessment beyond the LendingClub dataset. Full article

Credit risk is a crucial component of daily financial services operations; it measures the likelihood that a borrower will default on a loan, incurring an economic loss. By analysing historical data for assessment of the creditworthiness of a borrower, lenders can reduce credit risk. Data are vital at the core of the credit decision-making processes. Decision-making depends heavily on accurate, complete data, and failure to harness high-quality data would impact credit lenders when assessing the loan applicants’ risk profiles. In this paper, an empirical comparison of the robustness of seven machine learning algorithms to credit risk, namely support vector machines (SVMs), naïve base, decision trees (DT), random forest (RF), gradient boosting (GB), K-nearest neighbour (K-NN), and logistic regression (LR), is carried out using the Lending Club credit data from Kaggle. This task uses seven performance measures, including the F1 Score (recall, accuracy, and precision), ROC-AUC, and HL and MCC metrics. Then, the harnessing of generative adversarial networks (GANs) simulation to enhance the robustness of the single machine learning classifiers for predicting credit risk is proposed. The results show that when GANs imputation is incorporated, the decision tree is the best-performing classifier with an accuracy rate of 93.01%, followed by random forest (92.92%), gradient boosting (92.33%), support vector machine (90.83%), logistic regression (90.76%), and naïve Bayes (89.29%), respectively. The classifier is the worst-performing method with a k-NN (88.68%) accuracy rate. Subsequently, when GANs are optimised, the accuracy rate of the naïve Bayes classifier improves significantly to (90%) accuracy rate. Additionally, the average error rate for these classifiers is over 9%, which implies that the estimates are not far from the actual values. In summary, most individual classifiers are more robust to missing data when GANs are used as an imputation technique. The differences in performance of all seven machine learning algorithms are significant at the 95% level. Full article

BigTech credit has enhanced financial inclusion, but it also poses concerns with its boundaries. This article uses theoretical frameworks and numerical simulations to examine the risks and inclusiveness of technology-empowered credit services for “long-tail” clients. This research discovered that the discrepancy between the commercial boundaries of BigTech credit and the technical limitations of risk management poses a risk in BigTech credit. The expanding boundaries of BigTech’s credit business may mitigate the representativeness of the data, resulting in a systematic deviation of unclear characteristics from the training sample data, which reduces the risk-control model’s ability to identify long-tail customers and raises the risk of credit defaults. Further computer simulations validate these results and demonstrate that competition among various companies would expedite the market’s transition over the boundary in case of a capital shortage. Finally, this article proposes setting up a joint-stock social unified credit technology company with data assets as an investment to facilitate the healthy and orderly development of financial technology institutions. Full article

Access to finance is essential for fostering financial inclusion, improving household economic well-being, and stimulating economic growth. However, if not prudently managed, it can become a double-edged sword, increasing the risk of over-indebtedness, particularly among low-income households. This paper investigates the borrowing behavior of rural households in Egypt, exploring whether it is motivated by the optimization of intertemporal consumption or reflects deeper financial vulnerabilities. The study enhances our understanding of rural households’ financial behavior in Egypt and contributes to the literature by introducing perceived general self-efficacy as a key behavioral factor. The paper employs a quantitative methodology using a probit analysis of the Egypt Labor Market Panel Survey to explore the factors affecting the demand for formal loans, informal borrowing, and Rotating Saving and Credit Associations (RoSCAs). The results show that informal credit plays a dominant role in meeting rural households’ financial needs. A significant positive relationship between formal and informal credit suggests they are complementary. Elderly, married, less educated, and poorer individuals are more likely to seek both forms of credit, with employment stability being a key differentiator. Self-efficacy also has a significant positive effect. No significant regional differences are observed, except in the case of informal borrowing, with rural households in Upper Egypt showing less reliance, suggesting that social image may influence financial behavior in this region. The results suggest that demand for credit is driven by economic and financial vulnerability of rural households. The paper highlights key policy implications. First, to enhance participation in formal credit market, credit policies should offer more affordable, tailored credit relevant to starting a business rather than financing consumption, part of which is conspicuous. Second, the low self-efficacy among the rural poor suggests a need for policies that combine credit access with financial literacy and debt management support to prevent over-indebtedness. Full article