Search Results (246)

Static Priority-based Multiple Access (SPMA) is an emerging and promising wireless MAC protocol which is widely used in Unmanned Aerial Vehicle (UAV) networks. UAV (Unmanned Aerial Vehicle) networks, also known as drone networks, refer to a system of interconnected UAVs that communicate and collaborate to perform tasks autonomously or semi-autonomously. These networks leverage wireless communication technologies to share data, coordinate movements, and optimize mission execution. In SPMA, traffic arriving at the UAV network node can be divided into multiple priorities according to the information timeliness, and the packets of each priority are stored in the corresponding queues with different thresholds to transmit packet, thus guaranteeing the high success rate and low latency for the highest-priority traffic. Unfortunately, the multi-priority queue scheduling of SPMA deprives the packet transmitting opportunity of low-priority traffic, which results in unfair conditions among different-priority traffic. To address this problem, in this paper we propose the method of Adaptive Credit-Based Shaper with Reinforcement Learning (abbreviated as ACBS-RL) to balance the performance of all-priority traffic. In ACBS-RL, the Credit-Based Shaper (CBS) is introduced to SPMA to provide relatively fair packet transmission opportunity among multiple traffic queues by limiting the transmission rate. Due to the dynamic situations of the wireless environment, the Q-learning-based reinforcement learning method is leveraged to adaptively adjust the parameters of CBS (i.e., idleslope and sendslope) to achieve better performance among all priority queues. The extensive simulation results show that compared with traditional SPMA protocol, the proposed ACBS-RL can increase UAV network throughput while guaranteeing Quality of Service (QoS) requirements of all priority traffic. Full article

This study addresses the challenges of data imbalance and missing values in credit card transaction datasets by employing mode-based imputation and various machine learning models. We analyzed two distinct datasets: one consisting of European cardholders and the other from American Express, applying multiple machine learning algorithms, including Artificial Neural Networks, Convolutional Neural Networks, and Gradient Boosted Decision Trees, as well as others. Notably, the Gradient Boosted Decision Tree demonstrated superior predictive performance, with accuracy increasing by 4.53%, reaching 96.92% on the European cardholders dataset. Mode imputation significantly improved data quality, enabling stable and reliable analysis of merged datasets with up to 50% missing values. Hypothesis testing confirmed that the performance of the merged dataset was statistically significant compared to the original datasets. This study highlights the importance of robust data handling techniques in developing effective fraud detection systems, setting the stage for future research on combining different datasets and improving predictive accuracy in the financial sector. Full article

Globally, forest leisure and recreation (FLR) activities are widely recognized not only for their environmental and social benefits but also for their economic contributions. To better understand these economic contributions, it is vital to examine how the regional economic levels of customers vary when consuming FLR. This study aimed to empirically examine whether the regional economic level of residents (i.e., gross regional domestic product; GRDP) is classifiable using FLR expenditure data, and to interpret which variables contribute to its classification. We acquired anonymized credit card transaction data on residents of two regions with different GRDP levels. The data were preprocessed by identifying FLR-related industries and extracting key spending features for classification analysis. Five classification models (e.g., deep neural network (DNN), random forest, extreme gradient boosting, support vector machine, and logistic regression) were applied. Among the models, the DNN model presented the best performance (overall accuracy = 0.73; area under the curve (AUC) = 0.82). SHAP analysis showed that the “FLR industry” variable was most influential in differentiating GRDP levels across all the models. These findings demonstrate that FLR consumption patterns may vary and are interpretable by economic levels, providing an empirical framework for designing regional economic policies. Full article

This study investigates the relationship between sovereign credit rating transitions and domestic equity market performance, focusing on Greece from 2004 to 2024. Although credit ratings are central to sovereign risk assessment, their immediate influence on financial markets remains contested. This research adopts a multi-method analytical framework combining algebraic combinatorics and time-series econometrics. The methodology incorporates the construction of a directed credit rating transition graph, the partially ordered set representation of rating hierarchies, rolling-window correlation analysis, Granger causality testing, event study evaluation, and the formulation of a reward matrix with optimal rating path optimization. Empirical results indicate that credit rating announcements in Greece exert only modest short-term effects on the Athens Stock Exchange General Index, implying that markets often anticipate these changes. In contrast, sequential downgrade trajectories elicit more pronounced and persistent market responses. The reward matrix and path optimization approach reveal structured investor behavior that is sensitive to the cumulative pattern of rating changes. These findings offer a more nuanced interpretation of how sovereign credit risk is processed and priced in transparent and fiscally disciplined environments. By bridging network-based algebraic structures and economic data science, the study contributes a novel methodology for understanding systemic financial signals within sovereign credit systems. Full article

This paper examines the impact of carbon capture and storage (CCS) deployment on national carbon intensity (CI) across 43 countries from 2010 to 2020. Using a dynamic common correlated effects (DCCE) log–log panel, we estimate the elasticity of CI with respect to sectoral CCS facility counts within four income-group panels and the full sample. In the high-income panel, CCS in direct air capture, cement, iron and steel, power and heat, and natural gas processing sectors produces statistically significant CI declines of 0.15%, 0.13%, 0.095%, 0.092%, and 0.087% per 1% increase in facilities, respectively (all p < 0.05). Upper-middle-income countries exhibit strong CI reductions in direct air capture (–0.22%) and cement (–0.21%) but mixed results in other sectors. Lower-middle- and low-income panels show attenuated or positive elasticities—reflecting early-stage CCS adoption and infrastructure barriers. Robustness checks confirm these patterns both before and after the 2015 Paris Agreement and between emerging and developed economy panels. Spatial analysis reveals that the United States and United Kingdom achieved 30–40% CI reductions over the decade, whereas China, India, and Indonesia realized only 10–20% declines (relative to a 2010 baseline), highlighting regional deployment gaps. Drawing on these detailed income-group insights, we propose tailored policy pathways: in high-income settings, expand tax credits and public–private infrastructure partnerships; in upper-middle-income regions, utilize blended finance and technology-transfer programs; and in lower-income contexts, establish pilot CCS hubs with international support and shared storage networks. We further recommend measures to manage CCS’s energy and water penalties, implement rigorous monitoring to mitigate leakage risks, and design risk-sharing contracts to address economic uncertainties. Full article

As an emerging e-commerce model, live streaming e-commerce integrates instant interaction, content marketing, and online sales to bring consumers a new shopping experience. However, there are many risks in the process of live e-commerce transactions. Identifying key risk factors and implementing targeted control measures are crucial for promoting the sustainable and healthy development of live streaming e-commerce. This paper firstly constructs a business model of live streaming e-commerce transactions according to the transaction scenario and summarizes 24 risk factors from the three dimensions of live streaming e-commerce platforms, merchants, and anchors based on relevant national standards and other relevant literature. Secondly, the Delphi method is employed to modify and optimize the initial risk factors. On this basis, the social network model of risk factors is constructed to determine the influence relationship among risk factors. By calculating the degree centrality, factor types are segmented, and key risk factors as well as influence paths are identified. Finally, corresponding countermeasures and suggestions are proposed. The results indicate that Credit Evaluation System Perfection, Service Evaluation System Perfection, Qualification Audit Mechanism Perfection, Dispute Complaint Handling Channels Perfection, Risk Identification Mechanism Perfection, Platform Qualification, Merchant Qualification, and Merchant Credit are the critical risk factors affecting live streaming e-commerce transactions. Full article

In recent years, numerous regions worldwide have experienced devastating natural disasters, leading to significant structural damage to buildings and loss of human lives. The reconstruction process highlights the need for a reliable method to document and track the maintenance history of buildings. This paper introduces a novel approach for managing and monitoring restoring interventions using a secure and transparent digital framework. We will also present an application aimed at improving building structures with respect to earthquake resistance. The proposed system, referred as the “Building Ledger Dossier”, leverages a Digital Twin approach applied to blockchain to establish an immutable record of all structural interventions. The framework models buildings using OpenSees, while all maintenance, repair activities, and documents are registered as Non-Fungible Tokens on a blockchain network, ensuring timestamping, transparency, and accountability. A Decentralized Autonomous Organization oversees identity management and work validation, enhancing security and efficiency in building restoration efforts. This approach provides a scalable and globally applicable solution for improving both ante-disaster monitoring and post-disaster reconstruction, ensuring a comprehensive, verifiable history of structural interventions and fostering trust among stakeholders. The proposed method is also applicable to other types of processes that require the aforementioned properties for document monitoring, such as the life-cycle management of tax credits and operations in the financial or banking sectors. Full article

The surge in credit fraud incidents poses a critical threat to financial systems, driving the need for robust and adaptive fraud detection solutions. While various predictive models have been developed, existing approaches often struggle with two persistent challenges: extreme class imbalance and delays in detecting fraudulent activity. In this study, we propose an unsupervised Adversarial Autoencoder (AAE) framework designed to tackle these challenges simultaneously. The results highlight the potential of our approach as a scalable, interpretable, and adaptive solution for real-world credit fraud detection systems. Full article

In Latin America, over 50% of the population has relied on loans from family members or friends, reflecting the importance of trust-based networks in response to financial exclusion. This study examines how distrust in the formal financial system influences the use of informal borrowing. Using data from 17 countries for the years 2014, 2017, and 2021, and applying a fixed-effects logistic regression model by country and time, we confirm that rising distrust significantly increases the likelihood of turning to loans from personal networks. This relationship intensifies in times of crisis. Beyond this, we find that macroeconomic variables such as GDP per capita and unemployment also significantly affect informal borrowing behavior. This research contributes to the literature by integrating institutional, economic, and social variables, highlighting the role of interpersonal trust as a form of social capital. It also advances the field of personal finance by revealing an everyday strategy of financial resilience. Finally, this study offers relevant implications for public policy, advocating for a more realistic and context-sensitive approach to financial inclusion, especially in regions where credit constraints in the formal sector have pushed households to seek more accessible and flexible alternatives. Full article

Past and current advances in artificial intelligence (AI) have resulted in a significant impact on business and accounting. Over time, AI has slowly transformed from the 1950s to today, from rule-based systems, also known as expert systems, to the deep learning architectures and sophisticated neural networks of modern generative AI. Early AI accounting applications of expert systems included a GAAP-based expert system to assess the appropriate accounting treatment for business combinations and an expert system to determine the proper type of audit report to issue. Recent accounting expert systems have been developed for document analysis, fraud detection, evaluating credit risk, and corporate default forecasting. The purpose of this study is to examine key events in the history of AI, current applications, and potential future effects pertaining to management accounting and society overall. In addition, the relationship of AI with economic and social factors will be evaluated. The study’s findings will be of interest to management accountants, businesspersons, academic researchers, and others who are concerned with artificial intelligence and its impact on management accounting and society overall. Full article

Accurate corporate credit ratings are essential for financial risk assessment; yet, traditional methodologies relying on manual evaluation and basic statistical models often fall short in dynamic economic conditions. This study investigated the potential of machine-learning (ML) algorithms as a more precise and adaptable alternative for credit rating predictions. Using a seven-year dataset from S&P Capital IQ Pro, corporate credit ratings across 20 countries were analyzed, leveraging 51 financial and business risk variables. The study evaluated multiple ML models, including Logistic Regression, Support Vector Machines, Decision Trees, Random Forest, Gradient Boosting (GB), and Neural Networks, using rigorous data pre-processing, feature selection, and validation techniques. Results indicate that Artificial Neural Networks (ANN) and GB consistently outperform traditional models, particularly in capturing non-linear relationships and complex interactions among predictive factors. This study advances financial risk management by demonstrating the efficacy of ML-driven credit rating systems, offering a more accurate, efficient, and scalable solution. Additionally, it provides practical insights for financial institutions aiming to enhance their risk assessment frameworks. Future research should explore alternative data sources, real-time analytics, and model explainability to facilitate regulatory adoption. Full article

The existing financial payment system has inherent credit card fraud problems that must be solved with strong and effective solutions. In this research, a combined deep learning model that incorporates a convolutional neural network (CNN), long-short-term memory (LSTM), and fully connected output layer is proposed to enhance the accuracy of fraud detection, particularly in addressing the class imbalance problem. A CNN is used for spatial features, LSTM for sequential information, and a fully connected output layer for final decision-making. Furthermore, SMOTE is used to balance the data and hyperparameter tuning is utilized to achieve the best model performance. In the case of hyperparameter tuning, the detection rate is greatly enhanced. High accuracy metrics are obtained by the proposed CNN-LSTM (CLST) model, with a recall of 83%, precision of 70%, F1-score of 76% for fraudulent transactions, and ROC-AUC of 0.9733. The proposed model’s performance is enhanced by hyperparameter optimization to a recall of 99%, precision of 83%, F1-score of 91% for fraudulent cases, and ROC-AUC of 0.9995, representing almost perfect fraud detection along with a low false negative rate. These results demonstrate that optimization of hyperparameters and layers is an effective way to enhance the performance of hybrid deep learning models for financial fraud detection. While prior studies have investigated hybrid structures, this study is distinguished by its introduction of an optimized of CNN and LSTM integration within a unified layer architecture. Full article

Accurate credit scoring models are essential for financial risk management, yet conventional approaches often fail to address the complexities of high-dimensional, heterogeneous credit data, particularly in capturing nonlinear relationships and hierarchical dependencies, ultimately compromising predictive performance. To overcome these limitations, this paper introduces the level-wise feature-guided cascading ensemble (LFGCE) model, a novel framework that integrates hierarchical feature selection with cascading ensemble learning to systematically uncover latent feature hierarchies. The LFGCE framework leverages symmetry principles in its cascading architecture, where each ensemble layer maintains structural symmetry in processing its assigned feature subset while asymmetrically contributing to the final prediction through hierarchical information fusion. The LFGCE model operates through two synergistic mechanisms: (1) a hierarchical feature selection strategy that quantifies feature importance and partitions the feature space into progressively predictive subsets, thereby reducing dimensionality while preserving discriminative information, and (2) a cascading ensemble architecture where each layer specializes in learning risk patterns from its assigned feature subset, while iteratively incorporating outputs from preceding layers to enable cross-level information fusion. This dual process of hierarchical feature refinement and layered ensemble learning allows the LFGCE to extract deep, robust representations of credit risk. Empirical validation on four public credit datasets (Australian Credit, German Credit, Japan Credit, and Taiwan Credit) demonstrates that the LFGCE achieves an average AUC improvement of 0.23% over XGBoost (Python 3.13) and 0.63% over deep neural networks, confirming its superior predictive accuracy. Full article

This study presents a bibliometric analysis, using spatial approach, of 943 articles from 2003 to March 2025 showing the growing importance of CDSs in the literature and their role in credit risk management. The Web of Science’s Core Collection database was used for bibliometric mapping. The bibliographic data were grouped and analyzed using VOSviewer to create network visualization maps that included country-wise, document-wise, and source-wise citations analysis, bibliographic coupling, and the co-occurrence of keywords. Subsequently, significant terms were identified through the analyses where risk assessment, risk management, and credit derivatives were found to be the most used keywords. Further, USA turns out to be the country where the most research was published on CDSs with maximum citations, highlighting the growing popularity of this research topic in this region. In addition, bibliographic coupling appears to capture information from 13 clusters formed during the analysis on bibliographically linked documents with their link strength. The bibliometric analysis of the CDS literature illustrates the intellectual framework of research on this topic, traces the progression of the research topic over time, and identifies the areas where this research field might develop in the future. Full article

As China’s voluntary greenhouse gas emission reduction mechanism undergoes institutional revitalization, the accurate valuation of carbon assets such as China Certified Emission Reductions (CCERs) becomes increasingly critical for effective climate finance and sustainability-oriented investment. This study proposes an integrated value assessment model for CCERs that combines Long Short-Term Memory (LSTM) neural network-based carbon price forecasting with both the discounted net cash flow method and the Black–Scholes option pricing framework. Applying this model to a wind power project, the study found that the practical value of CCERs, derived from verified emission reductions, significantly exceeds their market option value, underscoring the economic and environmental viability of such projects. By distinguishing between the realized and potential values of carbon credits, this research offers a comprehensive tool for carbon asset valuation that supports corporate carbon management and policy development. The framework contributes to the growing literature on sustainable finance by aligning carbon asset pricing with long-term climate goals and enhancing transparency in carbon markets. Full article