Electromagnetic anomalies before earthquakes exhibit significant short-term characteristics. In this study, we first employed the non-negative matrix factorization (NMF) method to extract anomalies in the electric field, magnetic field, and electron density within the ionosphere. Then, to obtain earthquake-related anomalies, we propose a random matrix theory (RMT) anomaly distinction approach, which involves comparing the eigenvalue distribution of the ionospheric anomaly’s correlation matrix with that of a random matrix to remove earthquake-unrelated anomalies. Temporally, we observed that the pre-earthquake anomalies displayed sigmoidal growth between −65 and −25 days, followed by power-law growth from −20 days until the seismic event. Spatially, the anomalies exhibited a concentration pattern, migrating from the periphery of the study region toward the epicenter. Finally, the ionospheric anomalies were compared with multi-layer anomalies before the Madoi earthquake. We found three distinct phases, in the early phase, anomaly propagation through the lithosphere, atmosphere, and ionosphere followed an asynchronous chain process. In contrast, in the middle phase, anomalies appeared synchronously across the multi-layer. In the impending earthquake phase, the anomalies were directly coupled from the lithosphere to the ionosphere, which we hypothesize to be a new mechanism related to the dramatic decrease in Earth's resistivity.
The location and number of earthquake-induced trapped people (ETP) in ruined buildings are critical for postearthquake search and rescue (PESR) operations. Current earthquake-induced personnel entrapment risk (EPER) assessments suffer from low spatiotemporal resolution, limiting their application in PESRs. Taking three subdistricts of Tianjin as the study area, an EPER assessment framework with high spatiotemporal resolution was proposed, with the building damage predicted through nonlinear time-history analysis. The personnel entrapment rate (PER) and number of ETP are subsequently calculated via series analysis of census data spatialization, the personnel evacuation rate and self- and mutual-rescue rate estimation at the building level. The results show that the framework effectively characterizes spatial heterogeneity and temporal dynamic changes in EPER, with the PER on workdays ranging from 0.17% to 0.38% and 0.22% to 0.38% on nonworkdays. Diurnal patterns revealed higher PER during the nighttime than during the daytime and elevated risk on nonworkdays. Compared with traditional methods, this framework improved the prediction accuracy of EPER by 12.9% to 47.9% across time periods. Considering the uncertainties of the input parameters, the average relative errors of the ETP are between −36.2% and 27.5% across time periods. With high spatiotemporal resolution and enhanced identification efficiency for priority targets, the framework can provide substantial technical support for PESR operations.
This paper presents a meta-learning framework for credit risk assessment of Italian Small and Medium Enterprises (SMEs) that explicitly addresses the temporal misalignment of credit scoring models. The approach aligns financial statement reference dates with evaluation dates, mitigating bias arising from publication delays and asynchronous data sources. It is based on a two-step temporal decomposition that at first estimates annual probabilities of default (PDs) anchored to balance-sheet reference dates (December 31st) through a static model. Then it models the monthly evolution of PDs using higher-frequency behavioral data. Finally, we employ stacking-based architecture to aggregate multiple scoring systems, each capturing complementary aspects of default risk, into a unified predictive model. In this way, first level model outputs are treated as learned representations that encode non-linear relationships in financial and behavioral indicators, allowing integration of new expert-based features without retraining base models. This design provides a coherent and interpretable solution to challenges typical of low-default environments, including heterogeneous default definitions and reporting delays. Empirical validation shows that the framework effectively captures credit risk evolution over time, improving temporal consistency and predictive stability relative to standard ensemble methods.
Nur Alamsyah, Budiman Budiman, Titan Parama Yoga
et al.
The increase in forest fires poses a significant risk due to its impact on underground dryness, which can cause long-term environmental damage and challenge fire suppression efforts. This research aims to develop a prediction model for underground drought levels in the context of forest fires using machine learning techniques. The methodology used in this research follows the CRISP-DM (Cross-Industry Standard Process for Data Mining) framework, which includes the stages of business understanding, data understanding, data preparation, modeling, evaluation, and deployment. This study analyzes a forest fire dataset, applies encoder labels to transform categorical variables, and uses linear regression and random forest models to predict underground drought levels. The goal is to create a predictive model that can help inform wildfire risk management strategies by anticipating underground drought levels. The results showed that the random forest model achieved higher prediction accuracy than the linear regression, with an R-squared value of 0.97. This suggests that the random forest model is a more robust tool for predicting underground drought levels, providing valuable insights for forest fire management. This research contributes to the understanding of underground drought levels, aiding the development of effective wildfire risk management strategies.
Information technology, Management information systems
Ching-Hsi Tseng, Yu-Heng Hsieh, Wei-Qi Chen
et al.
Abstract As labor dispatch becomes increasingly widespread, enterprises face serious challenges such as résumé fraud, low background verification efficien-cy, and heightened data breach risks—especially under growing regulatory pressures. Existing solutions, such as centralized HR systems and third-party verification platforms, may improve efficiency to some extent, but still suffer from issues including a lack of transparency, susceptibility to data tampering, and cumbersome verification procedures. These limitations highlight a signifi-cant research gap in balancing efficiency, privacy, and trust. This study aims to develop a secure, automated, and regulation-compliant labor dispatch management system that enhances the credibility, efficiency, and privacy protection in résumé verification. To address these issues, we propose a blockchain-based labor dispatch system that integrates smart contracts for automated credential validation and incorporates Self-Sovereign Identity (SSI) to reinforce data ownership and control. Leveraging the immutability and decentralization of blockchain, the system ensures secure contract storage and auditability, while an access control mechanism effectively mitigates unauthorized data access risks. Our research involves the development of a prototype system, evaluated based on key performance indicators such as transaction processing time, verification latency, data integrity, and security. The contributions of this study include: (1) Credential certification of personal data ensures the authenticity of résumés, improving recruitment efficiency; (2) Secure contract storage on the blockchain satisfies both business confidentiality and legal compliance requirements; (3) A robust access control mechanism effectively safeguards sensitive personal data, reducing the risk of unauthorized access and data breaches; (4) The construction and performance evaluation of a blockchain-based labor dispatch system prototype addressing key operational metrics. Compared to existing technologies, the proposed model demonstrates signifi-cant advantages in trustworthiness, efficiency, and data protection and shows strong potential for practical deployment in highly regulated industry environ-ments.
In the increasingly complex and dynamic financial landscape, managing operational risks poses a crucial challenge for financial institutions. Evolving regulations, the rise of cyber threats, and growing stakeholder expectations make a rigorous and systematic approach to quantifying and managing these risks essential. In this context, Basel 4 focuses on a more robust framework for operational risk management, introducing a standardized approach for calculating operational risk capital. This framework aims to encourage greater 'risk sensitivity' in risk assessment and requires an increase in the capital that banks must hold to address losses arising from operational events, such as internal errors, fraud, or natural disasters. Basel IV will have significant implications for financial institutions. The greater capital requirements imposed by the introduction of the new regulations will push banks to revise their processes and strategies in order to contain the higher capital absorptions.
Sandra Coello Suarez, V. Sanchez Padilla, Ronald Ponguillo-Intriago
et al.
Parameter monitoring and control systems are crucial in the industry as they enable automation processes that improve productivity and resource optimization. These improvements also help to manage environmental factors and the complex interactions between multiple inputs and outputs required for production management. This paper proposes an automation system for broiler management based on a simulation scenario that involves sensor networks and embedded systems. The aim is to create a transmission network for monitoring and controlling broiler temperature and feeding using the Internet of Things (IoT), complemented by a dashboard and a cloud-based service database to track improvements in broiler management. We look forward this work will serve as a guide for stakeholders and entrepreneurs in the animal production industry, fostering sustainable development through simple and cost-effective automation solutions. The goal is for them to scale and integrate these recommendations into their existing operations, leading to more efficient decision-making at the management level.
The lack of high-quality public cyber incident data limits empirical research and predictive modeling for cyber risk assessment. This challenge persists due to the reluctance of companies to disclose incidents that could damage their reputation or investor confidence. Therefore, from an actuarial perspective, potential resolutions conclude two aspects: the enhancement of existing cyber incident datasets and the implementation of advanced modeling techniques to optimize the use of the available data. A review of existing data-driven methods highlights a significant lack of entity-specific organizational features in publicly available datasets. To address this gap, we propose a novel InsurTech framework that enriches cyber incident data with entity-specific attributes. We develop various machine learning (ML) models: a multilabel classification model to predict the occurrence of cyber incident types (e.g., Privacy Violation, Data Breach, Fraud and Extortion, IT Error, and Others) and a multioutput regression model to estimate their annual frequencies. While classifier and regressor chains are implemented to explore dependencies among cyber incident types as well, no significant correlations are observed in our datasets. Besides, we apply multiple interpretable ML techniques to identify and cross-validate potential risk factors developed by InsurTech across ML models. We find that InsurTech empowered features enhance prediction occurrence and frequency estimation robustness compared to only using conventional risk factors. The framework generates transparent, entity-specific cyber risk profiles, supporting customized underwriting and proactive cyber risk mitigation. It provides insurers and organizations with data-driven insights to support decision-making and compliance planning.
Jan Dhaene, Atibhav Chaudhry, Ka Chun Cheung
et al.
This paper studies the mathematical problem of allocating payouts (compensations) in an endowment contingency fund using a risk-sharing rule that satisfies full allocation. Besides the participants, an administrator manages the fund by collecting ex-ante contributions to establish the fund and distributing ex-post payouts to members. Two types of administrators are considered. An 'active' administrator both invests in the fund and receives the payout of the fund when no participant receives a payout. A 'passive' administrator performs only administrative tasks and neither invests in nor receives a payout from the fund. We analyze the actuarial fairness of both compensation-based risk-sharing schemes and provide general conditions under which fairness is achieved. The results extend earlier work by Denuit and Robert (2025) and Dhaene and Milevsky (2024), who focused on payouts based on Bernoulli distributions, by allowing for general non-negative loss distributions.
Areej Alhogail, Mona Alshahrani, Alanoud Alsheddi
et al.
The transportation industry has been recognized as one of the industries that can benefit from investment in blockchain-based systems and services that enable distributed data management and improve the effectiveness and efficiency of the transportation sector. However, the literature needs a guiding framework for integrating blockchain in issuing and preserving public transportation transactions in a technical environment that is secure, efficient, and transparent. This study proposes a blockchain-based transportation wallet (BTW) framework that facilitates the main digital transactions across diverse public transportation services. BTW embodies leveraging blockchain technology, which provides a decentralized and immutable ledger that records and verifies transactions, ensuring trust and reducing the risk of fraud. The framework has been validated by developing a blockchain-based public transportation smart wallet named “RideChain”. This serves as a single decentralized point for making public transportation transactions and payments, as well as identity authorizations and management. RideChain enhances passengers’ and service providers’ experience through a secure and authentic platform for offering several reliable public transportation transactions efficiently. In this study, we implemented a smart contract to establish a protocol between passengers and journey services. The testing methodologies used in this study comprise unit testing, integration testing, performance testing, and user acceptance testing. The findings suggest that BTW has been successfully verified to demonstrate its capability for secure transactions, authenticity of monetary transactions, automated smart contracts, decentralized identity authentication, and effortless payments.
We introduce the concept of set risk measures (SRMs), which are real-valued maps defined on the space of all non-empty, closed, and bounded sets of almost surely bounded random variables. Traditional risk measures typically operate on random variables, but SRMs extend this framework to sets of random variables. We establish an axiomatic scheme for SRMs, similar to classical risk measures but adapted for set operations. The main technical contribution is an axiomatic dual representation of convex SRMs by using regular, $τ$-additive (for nets) measures on the unit ball of the dual space of essentially bounded random variables. We explore worst-case SRMs, which evaluate risk as the supremum of individual risks within a set, and provide a collection of examples illustrating the applicability of our framework to systemic risk, optimization, and decision-making under uncertainty.
With the development of the financial industry, credit default prediction, as an important task in financial risk management, has received increasing attention. Traditional credit default prediction methods mostly rely on machine learning models, such as decision trees and random forests, but these methods have certain limitations in processing complex data and capturing potential risk patterns. To this end, this paper proposes a deep learning model based on the combination of convolutional neural networks (CNN) and Transformer for credit user default prediction. The model combines the advantages of CNN in local feature extraction with the ability of Transformer in global dependency modeling, effectively improving the accuracy and robustness of credit default prediction. Through experiments on public credit default datasets, the results show that the CNN+Transformer model outperforms traditional machine learning models, such as random forests and XGBoost, in multiple evaluation indicators such as accuracy, AUC, and KS value, demonstrating its powerful ability in complex financial data modeling. Further experimental analysis shows that appropriate optimizer selection and learning rate adjustment play a vital role in improving model performance. In addition, the ablation experiment of the model verifies the advantages of the combination of CNN and Transformer and proves the complementarity of the two in credit default prediction. This study provides a new idea for credit default prediction and provides strong support for risk assessment and intelligent decision-making in the financial field. Future research can further improve the prediction effect and generalization ability by introducing more unstructured data and improving the model architecture.
Risk measures for random vectors have been considered in multi-asset markets with transaction costs and financial networks in the literature. While the theory of set-valued risk measures provide an axiomatic framework for assigning to a random vector its set of all capital requirements or allocation vectors, the actual decision-making process requires an additional rule to select from this set. In this paper, we define vector-valued risk measures by an analogous list of axioms and show that, in the convex and lower semicontinuous case, such functionals always ignore the dependence structures of the input random vectors. We also show that set-valued risk measures do not have this issue as long as they do not reduce to a vector-valued functional. Finally, we demonstrate that our results also generalize to the conditional setting. These results imply that convex vector-valued risk measures are not suitable for defining capital allocation rules for a wide range of financial applications including systemic risk measures.
Big data is at the heart of the insurance industry through the uses it provides, where the year 2022 is considered the beginning of the “digital revolution” when humans were able to store more digital information in technological tools than ever before. Research results have shown the impact relationship between big data and various industries, including the insurance industry. Big data has improved all aspects of the insurance process, from pricing and underwriting to claims management and customer service to ultimately more effective risk management. Based on practical and theoretical practices in this framework, the question arises whether big data has brought about development in the insurance industry. Therefore, the purpose of this study was to gain a better understanding of the impact of big data on all aspects of the insurance industry. The research findings showed that the quantity and quality of data collected and used by insurance companies directly impact the services produced and developed. Big data enables insurers to identify patterns, trends and behaviors, allowing them to develop customized products and services. Also, by collecting and utilizing quality big data, insurance companies can provide more efficient and effective services, improving customer satisfaction and increasing profitability. Although big data is a lucrative opportunity for the insurance industry, it is also a threat as companies that need the means to access big data, technologies and skills will see their competitiveness drop significantly in the future. On the other hand, intermediary platforms, particularly GAFTA (Google, Apple, Facebook, Twitter, Amazon) that control the entire data value chain, can seek a large percentage of profits by providing the value chain to insurers, or the purchase of these platforms for vulnerable insurance companies, allowing them to dominate the insurance market.
Nadia Niknami, Avinash Srinivasan, Ken St. Germain
et al.
The rise of the Internet of Things (IoT) has opened up exciting possibilities for new applications. One such novel application is the modernization of maritime communications. Effective maritime communication is vital for ensuring the safety of crew members, vessels, and cargo. The maritime industry is responsible for the transportation of a significant portion of global trade, and as such, the efficient and secure transfer of information is essential to maintain the flow of goods and services. With the increasing complexity of maritime operations, technological advancements such as unmanned aerial vehicles (UAVs), autonomous underwater vehicles (AUVs), and the Internet of Ships (IoS) have been introduced to enhance communication and operational efficiency. However, these technologies also bring new challenges in terms of security and network management. Compromised IT systems, with escalated privileges, can potentially enable easy and ready access to operational technology (OT) systems and networks with the same privileges, with an increased risk of zero-day attacks. In this paper, we first provide a review of the current state and modalities of maritime communications. We then review the current adoption of software-defined radios (SDRs) and software-defined networks (SDNs) in the maritime industry and evaluate their impact as maritime IoT enablers. Finally, as a key contribution of this paper, we propose a unified SDN–SDR-driven cross-layer communications framework that leverages the existing SATCOM communications infrastructure, for improved and resilient maritime communications in highly dynamic and resource-constrained environments.
Shipping is a highly volatile, cyclical, and capital-intensive industry defined by extreme highs and lows. This makes information regarding volatility in this market material and relevant for decisions related to portfolio diversification, forecasting, and hedging in the maritime industry. Understanding how volatility is disseminated across the shipping market can help shipping companies to improve operational efficiency by making them more responsive to market changes. When shipping companies can anticipate market changes, they can swiftly respond and adjust their operations accordingly. In addition, volatility transmission in the shipping industry is crucial for policymakers seeking to improve the economic outlook of individuals and business entities that depend on the shipping industry. By monitoring the flow of volatility between shipping markets, they can promote effective pro-industry economic policies by more accurately estimating the effects of introducing new shocks to one freight market on another one. Therefore, understanding the volatility transmission between the container and dry bulk freight markets could provide an effective risk management mechanism that improves decision- making in shipping. This study analyzes volatility transmission between the container and dry bulk freight markets during the coronavirus disease-2019 pandemic using an asymmetric BEKK-GARCH(1,1) model that can also serve as a weak efficiency test. The results indicate that there was bidirectional volatility transmission between the container and dry bulk freight markets during the pandemic and that transmission from the container to dry bulk freight market was dominant. These findings support the price formation hypothesis of shipping, which states that dry bulk freight rates will follow container freight rates when freight rates exhibit an upward trend. Furthermore, the statistical significance of volatility transmission suggests that container and dry bulk freight rates can be used as a prediction mechanism for each other, serving as a market inefficiency indicator for both freight markets.
The assessment of risk based on historical data faces many challenges, in particular due to the limited amount of available data, lack of stationarity, and heavy tails. While estimation on a short-term horizon for less extreme percentiles tends to be reasonably accurate, extending it to longer time horizons or extreme percentiles poses significant difficulties. The application of theoretical risk scaling laws to address this issue has been extensively explored in the literature. This paper presents a novel approach to scaling a given risk estimator, ensuring that the estimated capital reserve is robust and conservatively estimates the risk. We develop a simple statistical framework that allows efficient risk scaling and has a direct link to backtesting performance. Our method allows time scaling beyond the conventional square-root-of-time rule, enables risk transfers, such as those involved in economic capital allocation, and could be used for unbiased risk estimation in small sample settings. To demonstrate the effectiveness of our approach, we provide various examples related to the estimation of value-at-risk and expected shortfall together with a short empirical study analysing the impact of our method.
In the stock market, a successful investment requires a good balance between profits and risks. Based on the learning to rank paradigm, stock recommendation has been widely studied in quantitative finance to recommend stocks with higher return ratios for investors. Despite the efforts to make profits, many existing recommendation approaches still have some limitations in risk control, which may lead to intolerable paper losses in practical stock investing. To effectively reduce risks, we draw inspiration from adversarial learning and propose a novel Split Variational Adversarial Training (SVAT) method for risk-aware stock recommendation. Essentially, SVAT encourages the stock model to be sensitive to adversarial perturbations of risky stock examples and enhances the model's risk awareness by learning from perturbations. To generate representative adversarial examples as risk indicators, we devise a variational perturbation generator to model diverse risk factors. Particularly, the variational architecture enables our method to provide a rough risk quantification for investors, showing an additional advantage of interpretability. Experiments on several real-world stock market datasets demonstrate the superiority of our SVAT method. By lowering the volatility of the stock recommendation model, SVAT effectively reduces investment risks and outperforms state-of-the-art baselines by more than 30% in terms of risk-adjusted profits. All the experimental data and source code are available at https://drive.google.com/drive/folders/14AdM7WENEvIp5x5bV3zV_i4Aev21C9g6?usp=sharing.
The optimized location and allocation of earthquake emergency shelters are critical for improving the resilience of communities. However, the existing disaster shelters location–allocation optimization models usually select new shelters from candidate shelters neglecting the existing or planned shelters. The research into comparisons before and after location–allocation optimization between the current planning scenario (CLA scenario) and the supplementary new candidate shelter scenario (SLA scenario) is thus imperative for disaster risk reduction. This article develops a multi-criteria multi-objective multi-scenario supplemental location–allocation optimization model that addresses the concerns related to optimization comparison based on the above two scenarios and provides a higher degree of realism by integrating multi-criteria evaluation and optimization comparison into location–allocation problems. The solutions obtained under the two scenarios are then compared with a case study in Huairou Science City. The results show that the solution under the SLA scenario is superior to the corresponding CLA scenario regardless of the minimal-distance scheme or the minimal-area scheme. The proposed model is proven to be useful for the location–allocation optimization of earthquake emergency shelters, and the presented results can be used as a reference for balancing the interests of the government and residents during the reconstruction and expansion projects of shelters.