Search results

With the rapid growth of the domestic lending industry, assessing whether the borrower of each loan is at risk of default is a pressing issue for financial institutions. Although there are some models that can handle such problems well, there are still some shortcomings in some aspects. The purpose of this paper is to improve the accuracy of credit assessment models.

In this paper, three different stages are used to improve the classification performance of LSTM, so that financial institutions can more accurately identify borrowers at risk of default. The first approach is to use the K-Means-SMOTE algorithm to eliminate the imbalance within the class. In the second step, ResNet is used for feature extraction, and then two-layer LSTM is used for learning to strengthen the ability of neural networks to mine and utilize deep information. Finally, the model performance is improved by using the IDWPSO algorithm for optimization when debugging the neural network.

On two unbalanced datasets (category ratios of 700:1 and 3:1 respectively), the multi-stage improved model was compared with ten other models using accuracy, precision, specificity, recall, G-measure, F-measure and the nonparametric Wilcoxon test. It was demonstrated that the multi-stage improved model showed a more significant advantage in evaluating the imbalanced credit dataset.

In this paper, the parameters of the ResNet-LSTM hybrid neural network, which can fully mine and utilize the deep information, are tuned by an innovative intelligent optimization algorithm to strengthen the classification performance of the model.

The credit of agricultural product quality and safety reflects the ability of the main actors involved in the supply chain to provide reliable agricultural products to consumers. To fundamentally solve the problem of agricultural product quality and safety, it is worth studying how to make the credit awareness and integrity self-discipline of the supply chain agriculture-related subjects strengthened and the role and value of credit supervision given full play. Starting from the application of blockchain in the agricultural product supply chain, this paper aims to investigate the main factors affecting the credit regulation of agricultural product quality.

Using the DEMATEL-ISM (decision-making trial and evaluation laboratory–interpretative structural modeling) method, we analyze the credit influencing factors of agricultural quality and safety empowered by blockchain technology, find the causal relationship between the crucial influencing factors and deeply explore the hierarchical transmission relationship between the influencing factors. Then, the path analysis in structural equation modeling is utilized to verify and measure the significance and effect value of the transmission relationship among the crucial influencing factors of credit regulation.

The results show that the quality and safety credit regulation of agricultural products is influenced by a combination of direct and deep influencing factors. Long-term stable cooperative relationship, Quality and safety credit evaluation, Supply chain risk control ability, Quality and safety testing, Constraints of the smart contract are the main influence path of blockchain embedded in agricultural product supply chain quality and safety credit supervision.

Credit supervision is an important means to improve the ability and level of social governance and standardize the market order. From the perspective of blockchain embedded in the agricultural supply chain, the regulatory body is transformed from the product body to the supply chain body. Take the credit supervision of supply chain subjects as the basis of agricultural product quality supervision. With the help of blockchain technology to improve the effectiveness of agricultural product quality and safety credit supervision, credit supervision is used to constrain and incentivize the behavior of agricultural subjects.

The purpose of the study is to examine the use of alternative information in bank lending to small and medium enterprises (SMEs). Understanding alternative information and its use in bank lending to SMEs is important because it has become a growing part of the future of SME finance. The results and findings of my study not only enrich the finance literature but, more importantly, also address the use of Fintech in the risk management of SME lending, a new and complex problem that is specific to both the information technology and finance field.

To answer the research question, the author used a case study approach that relies upon qualitative data and analysis. By iterating between the existing literature, theoretical pieces and empirical findings, the author explain and interpret in detail how the use of alternative information impacts loan outcomes and develop insights to guide future research.

The case is outlined in two time periods including the prepartnership period and the postpartnership period. It highlights the establishment of a partnership between LoanBank and FintechInc (pseudonym), aimed at SME-focused Fintech lending. The findings underscore how the partnership has enabled a mutually beneficial situation where LoanBank and FintechInc leverage each other’s strengths to provide efficient and effective lending services. The adoption of alternative information in the risk management Fintech (RMF) platform of FintechInc has transformed LoanBank’s lending processes, showcasing how technological innovations can enhance SME lending practices.

The study’s originality mainly lies in the three detailed insights regarding alternative information’s impact on SME lending: information, platform properties and financial inclusion. The information part demonstrates that RMF platforms expand the information used for lending decisions, shifting from traditional hard and soft data to incorporating various alternative information sources. The platform properties part suggests that location, openness and technology also play a pivotal role in shaping lending outcomes. Finally, the financial inclusion part proposes that the use of alternative information has the potential to improve financial inclusion and offer better credit terms to previously underserved borrowers.

This study aims to develop a novel approach for predicting default risk in bancassurance, which plays a crucial role in the relationship between interest rates in banks and premium rates in insurance companies. The proposed method aims to improve default risk predictions and assist with client segmentation in the banking system.

This research introduces the group method of data handling (GMDH) technique and a diversified classifier ensemble based on GMDH (dce-GMDH) for predicting default risk. The data set comprises information from 30,000 credit card clients of a large bank in Taiwan, with the output variable being a dummy variable distinguishing between default risk (0) and non-default risk (1), whereas the input variables comprise 23 distinct features characterizing each customer.

The results of this study show promising outcomes, highlighting the usefulness of the proposed technique for bancassurance and client segmentation. Remarkably, the dce-GMDH model consistently outperforms the conventional GMDH model, demonstrating its superiority in predicting default risk based on various error criteria.

This study presents a unique approach to predicting default risk in bancassurance by using the GMDH and dce-GMDH neural network models. The proposed method offers a valuable contribution to the field by showcasing improved accuracy and enhanced applicability within the banking sector, offering valuable insights and potential avenues for further exploration.

This study aims to provide further insights into the connection between corporate social responsibility (CSR) and companies’ credit ratings, while also exploring the role of corporate governance as a moderating factor. The hypotheses for this relationship are rooted in both legitimacy and stakeholder theories.

Using a sample of French non-financial listed firms from 2007 to 2020, this paper uses the ordered probit model introduced by Greene (2000). The issue of endogeneity has also been addressed.

The study reveals that CSR practices positively impact companies’ credit ratings by enhancing solvency and financial performance. Specifically, firms that prioritize CSR, particularly in the social and environmental dimensions (such as community relations, diversity, employee relations, environmental performance and product characteristics), tend to have higher credit ratings and a reduced risk of default. This suggests that credit rating agencies likely incorporate CSR performance when assigning credit ratings. Furthermore, the quality of corporate governance acts as a moderator, strengthening the relationship between CSR and credit ratings. The findings remain robust even after accounting for key firm attributes and addressing potential endogeneity between CSR and credit ratings.

This research provides valuable guidance for policymakers, corporate managers, investors and other stakeholders, as it offers insights into the influence of CSR activities on risk premiums and financing costs. For financial institutions, expanding credit decisions to encompass non-financial factors such as CSR can result in more accurate predictions of firm credit quality compared to relying solely on financial indicators.

To the best of the authors’ knowledge, this study stands out as the first to systematically examine the relationship between CSR and credit ratings within the French context. Moreover, it distinguishes itself by investigating the moderating influence of corporate governance on this relationship, setting it apart from prior research.

The crux of this paper is to unveil efficient features and practical tools that can predict credit default.

Annual data of non-financial listed companies were taken from 2000 to 2020, along with 71 financial ratios. The dataset was bifurcated into three panels with three default assumptions. Logistic regression (LR) and k-nearest neighbor (KNN) binary classification algorithms were used to estimate credit default in this research.

The study’s findings revealed that features used in Model 3 (Case 3) were the efficient and best features comparatively. Results also showcased that KNN exposed higher accuracy than LR, which proves the supremacy of KNN on LR.

Using only two classifiers limits this research for a comprehensive comparison of results; this research was based on only financial data, which exhibits a sizeable room for including non-financial parameters in default estimation. Both limitations may be a direction for future research in this domain.

This study introduces efficient features and tools for credit default prediction using financial data, demonstrating KNN’s superior accuracy over LR and suggesting future research directions.

Many waste-to-energy (WTE) plants are constructed and operated using the public-private partnership (PPP) mode in China. However, risk events of PPP WTE incineration projects sometimes occur. This study aims to clarify the relationship of risks in China's PPP WTE incineration projects and identify the key risks accordingly and risk transmission paths.

A risk list of PPP WTE incineration projects was obtained based on literature analysis. Moreover, a hybrid approach combining fuzzy sets, decision-making trial and evaluation laboratory (DEMATEL) and interpretive structural modeling (ISM) was developed to analyze the causality of risks, explore critical risks and reveal the risk transmission paths. The quantitative analysis process was implemented in MATLAB.

The results show that government decision-making risk, government credit risk, government supervision behavior risk, legal and policy risk, revenue and cost risk and management capacity risk are the critical risks of PPP WTE incineration projects in China. These critical risks are at different levels in the risk hierarchy and often trigger other risks.

Currently, there is a lack of exploration on the interaction between the risks of PPP WTE incineration projects. This study fills this gap by examining the key risks and risk transfer pathways of PPP WTE incineration projects from the perspective of risk interactions. The findings can help the public and private sectors to systematically understand the risks in PPP WTE incineration projects, thus enabling them to identify the risks that need to be focused on when making decisions and to optimize risk prevention strategies. The proposed hybrid approach can offer methodological ideas for risk analysis of other types of PPP projects.

Under the background of low consumer financial knowledge and accumulated credit card liabilities, this study investigates the relationship between financial knowledge and responsible credit card behavior using data from the 2019 China Household Finance Survey (CHFS). From the perspective of consumer economic well-being, this study defines accruing credit card debt to buy houses and cars when loans with lower interest rates are available as irresponsible credit card behavior.

This study uses probit regressions to examine the association between financial knowledge and responsible credit card behavior because the dependent variable is a dummy variable. To alleviate endogeneity problems, this study uses instrument variables and Heckman’s two-step estimation. Furthermore, to explore the potential mediators in this process, this study follows the stepwise regression method. Finally, this study introduces interaction terms to examine whether this association differs in different groups.

The results indicate that financial knowledge is conducive to increasing the probability of responsible credit card behavior. Mediating analyses reveal that the roles of financial knowledge occur by increasing the degree of concern for financial and economic information and the propensity to plan. Moderating analyses show that the effects of financial knowledge on responsible credit card behavior are stronger among risk-averse consumers and in regions with favorable digital access.

This study measures responsible credit card behavior from the perspective of the consumer’s well-being, which enriches practical implications for consumer finance. Furthermore, this study explores the potential mediators influencing the process of financial knowledge that affects responsible credit card behavior and identifies moderators to conduct heterogeneous analyses, which helps comprehensively understand the nexus between financial knowledge and credit card behavior. By achieving these contributions, this study helps to curb the adverse effects of irresponsible credit card behavior on consumers’ well-being and the economic system and helps policymakers promote financial knowledge to fully prevent irresponsible credit card behavior.

This study aims to examine the impact of intellectual capital (IC) on default risk in Indian companies listed on the National Stock Exchange.

This study applies panel data regression analysis to derive a relationship between IC and default risk for the sample period 2013–2022. The value-added intellectual coefficient (VAIC) of Pulic (2000) has been applied to measure IC performance, and default risk is estimated using the revised Z-score model of Altman (2000).

The results revealed a positive association between Z-score and VAIC. It implies that a higher value of VAIC improves financial stability and leads to a lower likelihood of default. The findings further suggest that new default forecasting models can be experimented with IC indicators for better default prediction.

The findings can have implications for investors and banks. This paper provides evidence of IC performance in improving the financial solvency of firms. Investors and financial institutions should invest their resources in a healthy firm that effectively manages and invests in their IC. It will eventually award investors and creditors high returns through efficient value-creation processes.

This study provides evidence of IC performance in improving the financial solvency of Indian high-defaulting firms, which lacks sufficient evidence in this domain of research. Numerous studies exist examining the relationship between firm performance and IC value, but this area is inadequately focused and underresearched. This study, therefore, fills the research gap from an Indian perspective.

The authors originally explore the factors for blockchain technology (BCT) adoption in agricultural supply chains (ASCs) to enhance circularity and understand the dependencies, hierarchical structure and causalities between these factors.

Based on an extant literature review and expert opinion, the present study identified ten enablers for adopting BCT to leverage the circular economy (CE) practices in the ASCs. Then, using an integrated interpretive structural modeling and decision-making trial and evaluation laboratory (ISM-DEMATEL) approach, hierarchical and cause–effect relationships are established.

It was observed that traceability is the most prominent enabler from the CE perspective in ASCs. However, traceability, being a net effect enabler, will be realized through the achievement of other cause enablers, such as seamless connectivity and information flow and decentralized and distributed ledger technology. The authors also propose a 12 Rs framework for enhancing circularity in ASC operations.

The paper identifies enablers to BCT adoption that will enhance circularity in ASC operations. The ISM hierarchical model is based on the driving and dependence powers of the enablers, and DEMATEL aids in identifying causal relationships among the enablers.

The study's findings and proposed 12 Rs framework may help the practitioners and policymakers devise effective BCT implementation strategies in ASCs, thereby empowering sustainability and circularity.

This study enriches the literature by identifying and modeling enablers for BCT adoption in ASCs. The study also proposes a new 12 Rs framework to help enhance ASC circularity.