Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (123)

Search Parameters:
Keywords = imported financial risk network

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
22 pages, 2120 KiB  
Article
Machine Learning Algorithms and Explainable Artificial Intelligence for Property Valuation
by Gabriella Maselli and Antonio Nesticò
Real Estate 2025, 2(3), 12; https://doi.org/10.3390/realestate2030012 - 1 Aug 2025
Viewed by 191
Abstract
The accurate estimation of urban property values is a key challenge for appraisers, market participants, financial institutions, and urban planners. In recent years, machine learning (ML) techniques have emerged as promising tools for price forecasting due to their ability to model complex relationships [...] Read more.
The accurate estimation of urban property values is a key challenge for appraisers, market participants, financial institutions, and urban planners. In recent years, machine learning (ML) techniques have emerged as promising tools for price forecasting due to their ability to model complex relationships among variables. However, their application raises two main critical issues: (i) the risk of overfitting, especially with small datasets or with noisy data; (ii) the interpretive issues associated with the “black box” nature of many models. Within this framework, this paper proposes a methodological approach that addresses both these issues, comparing the predictive performance of three ML algorithms—k-Nearest Neighbors (kNN), Random Forest (RF), and the Artificial Neural Network (ANN)—applied to the housing market in the city of Salerno, Italy. For each model, overfitting is preliminarily assessed to ensure predictive robustness. Subsequently, the results are interpreted using explainability techniques, such as SHapley Additive exPlanations (SHAPs) and Permutation Feature Importance (PFI). This analysis reveals that the Random Forest offers the best balance between predictive accuracy and transparency, with features such as area and proximity to the train station identified as the main drivers of property prices. kNN and the ANN are viable alternatives that are particularly robust in terms of generalization. The results demonstrate how the defined methodological framework successfully balances predictive effectiveness and interpretability, supporting the informed and transparent use of ML in real estate valuation. Full article
Show Figures

Figure 1

30 pages, 1095 KiB  
Article
Unraveling the Drivers of ESG Performance in Chinese Firms: An Explainable Machine-Learning Approach
by Hyojin Kim and Myounggu Lee
Systems 2025, 13(7), 578; https://doi.org/10.3390/systems13070578 - 14 Jul 2025
Viewed by 434
Abstract
As Chinese firms play pivotal roles in global supply chains, multinational corporations face increasing pressure to ensure ESG accountability across their sourcing networks. Current ESG rating systems lack transparency in incorporating China’s unique industrial, economic, and cultural factors, creating reliability concerns for stakeholders [...] Read more.
As Chinese firms play pivotal roles in global supply chains, multinational corporations face increasing pressure to ensure ESG accountability across their sourcing networks. Current ESG rating systems lack transparency in incorporating China’s unique industrial, economic, and cultural factors, creating reliability concerns for stakeholders managing supply chain sustainability risks. This study develops an explainable artificial intelligence framework using SHAP and permutation feature importance (PFI) methods to predict the ESG performance of Chinese firms. We analyze comprehensive ESG data of 1608 Chinese listed companies over 13 years (2009–2021), integrating financial and non-financial determinants traditionally examined in isolation. Empirical findings demonstrate that random forest algorithms significantly outperform multivariate linear regression in capturing nonlinear ESG relationships. Key non-financial determinants include patent portfolios, CSR training initiatives, pollutant emissions, and charitable donations, while financial factors such as current assets and gearing ratios prove influential. Sectoral analysis reveals that manufacturing firms are evaluated through pollutant emissions and technical capabilities, whereas non-manufacturing firms are assessed on business taxes and intangible assets. These insights provide essential tools for multinational corporations to anticipate supply chain sustainability conditions. Full article
Show Figures

Figure 1

22 pages, 3393 KiB  
Article
Stochastic Operation of BESS and MVDC Link in Distribution Networks Under Uncertainty
by Changhee Han, Sungyoon Song and Jaehyeong Lee
Electronics 2025, 14(13), 2737; https://doi.org/10.3390/electronics14132737 - 7 Jul 2025
Viewed by 245
Abstract
This study introduces a stochastic optimization framework designed to effectively manage power flows in flexible medium-voltage DC (MVDC) link systems within distribution networks (DNs). The proposed approach operates in coordination with a battery energy storage system (BESS) to enhance the overall efficiency and [...] Read more.
This study introduces a stochastic optimization framework designed to effectively manage power flows in flexible medium-voltage DC (MVDC) link systems within distribution networks (DNs). The proposed approach operates in coordination with a battery energy storage system (BESS) to enhance the overall efficiency and reliability of the power distribution. Given the inherent uncertain characteristics associated with forecasting errors in photovoltaic (PV) generation and load demand, the study employs a distributionally robust chance-constrained optimization technique to mitigate the potential operational risks. To achieve a cooperative and optimized control strategy for MVDC link systems and BESS, the proposed method incorporates a stochastic relaxation of the reliability constraints on bus voltages. By strategically adjusting the conservativeness of these constraints, the proposed framework seeks to maximize the cost-effectiveness of DN operations. The numerical simulations demonstrate that relaxing the strict reliability constraints enables the distribution system operator to optimize the electricity imports more economically, thereby improving the overall financial performance while maintaining system reliability. Through case studies, we showed that the proposed method improves the operational cost by up to 44.7% while maintaining 96.83% bus voltage reliability under PV and load power output uncertainty. Full article
(This article belongs to the Special Issue Advanced Control Techniques for Power Converter and Drives)
Show Figures

Figure 1

34 pages, 11268 KiB  
Article
Advancements and Innovation Trends of Information Technology Empowering Elderly Care Community Services Based on CiteSpace and VOSViewer
by Yanxiu Wang, Zichun Shao, Zhen Tian and Junming Chen
Healthcare 2025, 13(13), 1628; https://doi.org/10.3390/healthcare13131628 - 7 Jul 2025
Viewed by 629
Abstract
Background: In elderly community services, information technology is reshaping the daily lives of older adults in unprecedented ways. It effectively addresses the issue of frailty in the community by strengthening support networks and dynamic risk management. Despite its vast potential, there remains [...] Read more.
Background: In elderly community services, information technology is reshaping the daily lives of older adults in unprecedented ways. It effectively addresses the issue of frailty in the community by strengthening support networks and dynamic risk management. Despite its vast potential, there remains a need to explore further enabling methods in the realm of elderly community services. Objectives: This study aims to provide a significant theoretical and practical foundation for information technology in this field by systematically analyzing the progress and trends of digital transformation facilitated by information technology. Materials and method: To map the advancements and emerging trends in this evolving field, this study conducts a bibliometric analysis of 461 relevant publications from the Web of Science Core Collection (2004–2024). The research employs bibliometric methods and utilizes tools such as CiteSpace and VOSViewer to analyze collaborations, keywords, and citations, as well as to perform data visualization. Results: The findings indicate that current research hotspots mainly focus on “community care”, “access to care”, “technology”, and “older adults”.Potential development trends include (1) further exploration of information technology in elderly care to provide more precise health management solutions; (2) systematically building community elderly service systems to offer more detailed elderly care services; (3) strengthening interdisciplinary information sharing and research collaboration to drive innovation in community elderly care models; and (4) introducing targeted policy and financial support to improve the specific implementation framework of information technology in elderly community services. Conclusions: This study provides empirical support for the development of relevant theories and practices. Furthermore, the research outcomes offer valuable insights into business opportunities for practitioners and provide important recommendations for formulating elderly service policies. Full article
Show Figures

Figure 1

27 pages, 3082 KiB  
Article
Analyzing Systemic Risk Spillover Networks Through a Time-Frequency Approach
by Liping Zheng, Ziwei Liang, Jiaoting Yi and Yuhan Zhu
Mathematics 2025, 13(13), 2070; https://doi.org/10.3390/math13132070 - 22 Jun 2025
Viewed by 512
Abstract
This paper investigates the spillover effects and transmission networks of systemic risk within China’s national economic sectors under extreme conditions from both time and frequency domain perspectives, building upon the spillover index methodology and calculating the ∆CoVaR index for Chinese industries. The findings [...] Read more.
This paper investigates the spillover effects and transmission networks of systemic risk within China’s national economic sectors under extreme conditions from both time and frequency domain perspectives, building upon the spillover index methodology and calculating the ∆CoVaR index for Chinese industries. The findings indicate the following: (1) Extreme-risk spillovers synchronize across industries but exhibit pronounced time-varying peaks during the 2008 Global Financial Crisis, the 2015 crash, and the COVID-19 pandemic. (2) Long-term spillovers dominate overall connectedness, highlighting the lasting impact of fundamentals and structural linkages. (3) In terms of risk volatility, Energy, Materials, Consumer Discretionary, and Financials are most sensitive to systemic market shocks. (4) On the risk spillover effect, Consumer Discretionary, Industrials, Healthcare, and Information Technology consistently act as net transmitters of extreme risk, while Energy, Materials, Consumer Staples, Financials, Telecom Services, Utilities, and Real Estate primarily serve as net receivers. Based on these findings, the paper suggests deepening the regulatory mechanisms for systemic risk, strengthening the synergistic effect of systemic risk measurement and early warning indicators, and coordinating risk monitoring, early warning, and risk prevention and mitigation. It further emphasizes the importance of avoiding fragmented regulation by establishing a joint risk prevention mechanism across sectors and departments, strengthening the supervision of inter-industry capital flows. Finally, it highlights the need to closely monitor the formation mechanisms and transmission paths of new financial risks under the influence of the pandemic to prevent the accumulation and eruption of risks in the post-pandemic era. Authorities must conduct annual “Industry Transmission Reviews” to map emerging risk nodes and supply-chain vulnerabilities, refine policy tools, and stabilize market expectations so as to forestall the build-up and sudden release of new systemic shocks. Full article
Show Figures

Figure 1

23 pages, 1601 KiB  
Article
Level-Wise Feature-Guided Cascading Ensembles for Credit Scoring
by Yao Zou and Guanghua Cheng
Symmetry 2025, 17(6), 914; https://doi.org/10.3390/sym17060914 - 10 Jun 2025
Viewed by 377
Abstract
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 [...] Read more.
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 article belongs to the Special Issue Symmetric Studies of Distributions in Statistical Models)
Show Figures

Figure 1

23 pages, 8927 KiB  
Article
Proposed Framework for Sustainable Flood Risk-Based Design, Construction and Rehabilitation of Culverts and Bridges Under Climate Change
by Cem B. Avcı and Muhsin Vanolya
Water 2025, 17(11), 1663; https://doi.org/10.3390/w17111663 - 30 May 2025
Viewed by 810
Abstract
The increasing frequency and intensity of hydrological events driven by climate change, particularly floods, present significant challenges for the design, construction, and maintenance of bridges and culverts. Additionally, the inadequate capacity of existing structures has resulted in substantial financial burdens on governments due [...] Read more.
The increasing frequency and intensity of hydrological events driven by climate change, particularly floods, present significant challenges for the design, construction, and maintenance of bridges and culverts. Additionally, the inadequate capacity of existing structures has resulted in substantial financial burdens on governments due to flood-related damages and the costs of their rehabilitation and replacement. A further concern is the oversight of existing hydraulic design standards, which primarily emphasize structural capacity and flood height, often overlooking broader social and environmental implications as two main pillars of sustainability. This oversight becomes even more critical under changing climatic conditions. This paper proposes a flood risk-based framework for the sustainable design, construction, and modification of bridge and culvert infrastructure in response to climate change. The framework integrates flood risk modeling with environmental and socio-economic considerations to systematically identify and assess vulnerabilities in existing infrastructure. A multi-criteria analysis (MCA) approach is employed to rapidly evaluate and integrate climate change, social, and environmental factors, such as population density, industrial activities, and the ecological impacts of floods following construction, alongside conventional hydrologic and hydraulic design criteria. The study utilizes hydrologic and hydraulic analyses, incorporating transportation networks (including roads, railways, and traffic) with socio-economic data through a GIS-based flood risk classification. Two case studies are presented: the first prioritizes the replacement of existing main bridges and culverts in the Ankara River Basin using the proposed MCA framework, while the second focuses on substructure sizing for a planned high-speed railway section in Mersin–Adana–Osmaniye–Gaziantep, Türkiye, accounting for climate change and upstream reservoirs. The findings highlight the critical importance of adopting a comprehensive and sustainable approach that integrates advanced risk assessment with resilient design strategies to ensure the long-term performance of bridge and culvert infrastructure under climate change. Full article
Show Figures

Figure 1

28 pages, 5652 KiB  
Article
Risk Identification and Spatiotemporal Evolution in Rural Land Trusteeship
by Jianying Xiao and Xinran Fang
Land 2025, 14(6), 1132; https://doi.org/10.3390/land14061132 - 22 May 2025
Viewed by 329
Abstract
Rural land trusteeship, as an innovative agricultural business model, has played an important role in enhancing agricultural production efficiency and optimizing land resource allocation. However, the model has also revealed many risks in the process of its implementation, posing challenges to its sustainable [...] Read more.
Rural land trusteeship, as an innovative agricultural business model, has played an important role in enhancing agricultural production efficiency and optimizing land resource allocation. However, the model has also revealed many risks in the process of its implementation, posing challenges to its sustainable development. Based on the cases of land trusteeship risk disputes made public by the China Judges and Records Network from 2013 to 2023, this paper uses Nvivo 12 Plus qualitative analysis software to identify and characterize the risks and utilizes the spatial analysis method to explore the spatial and temporal evolution of the risks. The study found the following: (1) Risks of rural land trusteeship can be categorized as market, operational, financial, natural, and contractual risks, with financial and contractual risks being more prominent. (2) The number of land trusteeship disputes gradually increased from 2013 to 2020, reaching a peak in 2020. Subsequently, the number has shown a decreasing trend, which reflects the positive effect of policy. (3) In terms of spatial pattern, land trusteeship risks have a significant northeast–southwest clustering trend, North China and Northeast China being high-risk clustering areas, while South China and Southwest China have relatively low risks. (4) There are significant differences in the spatial distributions of different types of risks, with market and operational risks being highly concentrated in economically active areas, while natural risks are more influenced by the geographic environment. Full article
(This article belongs to the Section Land Systems and Global Change)
Show Figures

Figure 1

27 pages, 297 KiB  
Article
A Practical Performance Benchmark of Post-Quantum Cryptography Across Heterogeneous Computing Environments
by Maryam Abbasi, Filipe Cardoso, Paulo Váz, José Silva and Pedro Martins
Cryptography 2025, 9(2), 32; https://doi.org/10.3390/cryptography9020032 - 21 May 2025
Viewed by 3206
Abstract
The emergence of large-scale quantum computing presents an imminent threat to contemporary public-key cryptosystems, with quantum algorithms such as Shor’s algorithm capable of efficiently breaking RSA and elliptic curve cryptography (ECC). This vulnerability has catalyzed accelerated standardization efforts for post-quantum cryptography (PQC) by [...] Read more.
The emergence of large-scale quantum computing presents an imminent threat to contemporary public-key cryptosystems, with quantum algorithms such as Shor’s algorithm capable of efficiently breaking RSA and elliptic curve cryptography (ECC). This vulnerability has catalyzed accelerated standardization efforts for post-quantum cryptography (PQC) by the U.S. National Institute of Standards and Technology (NIST) and global security stakeholders. While theoretical security analysis of these quantum-resistant algorithms has advanced considerably, comprehensive real-world performance benchmarks spanning diverse computing environments—from high-performance cloud infrastructure to severely resource-constrained IoT devices—remain insufficient for informed deployment planning. This paper presents the most extensive cross-platform empirical evaluation to date of NIST-selected PQC algorithms, including CRYSTALS-Kyber and NTRU for key encapsulation mechanisms (KEMs), alongside BIKE as a code-based alternative, and CRYSTALS-Dilithium and Falcon for digital signatures. Our systematic benchmarking framework measures computational latency, memory utilization, key sizes, and protocol overhead across multiple security levels (NIST Levels 1, 3, and 5) in three distinct hardware environments and various network conditions. Results demonstrate that contemporary server architectures can implement these algorithms with negligible performance impact (<5% additional latency), making immediate adoption feasible for cloud services. In contrast, resource-constrained devices experience more significant overhead, with computational demands varying by up to 12× between algorithms at equivalent security levels, highlighting the importance of algorithm selection for edge deployments. Beyond standalone algorithm performance, we analyze integration challenges within existing security protocols, revealing that naive implementation of PQC in TLS 1.3 can increase handshake size by up to 7× compared to classical approaches. To address this, we propose and evaluate three optimization strategies that reduce bandwidth requirements by 40–60% without compromising security guarantees. Our investigation further encompasses memory-constrained implementation techniques, side-channel resistance measures, and hybrid classical-quantum approaches for transitional deployments. Based on these comprehensive findings, we present a risk-based migration framework and algorithm selection guidelines tailored to specific use cases, including financial transactions, secure firmware updates, vehicle-to-infrastructure communications, and IoT fleet management. This practical roadmap enables organizations to strategically prioritize systems for quantum-resistant upgrades based on data sensitivity, resource constraints, and technical feasibility. Our results conclusively demonstrate that PQC is deployment-ready for most applications, provided that implementations are carefully optimized for the specific performance characteristics and security requirements of target environments. We also identify several remaining research challenges for the community, including further optimization for ultra-constrained devices, standardization of hybrid schemes, and hardware acceleration opportunities. Full article
Show Figures

Figure 1

24 pages, 4341 KiB  
Article
Intraday and Post-Market Investor Sentiment for Stock Price Prediction: A Deep Learning Framework with Explainability and Quantitative Trading Strategy
by Guowei Sun and Yong Li
Systems 2025, 13(5), 390; https://doi.org/10.3390/systems13050390 - 18 May 2025
Cited by 1 | Viewed by 3540
Abstract
The inherent uncertainty and information asymmetry in financial markets create significant challenges for accurate price forecasting. Although investor sentiment analysis has gained traction in recent research, the temporal dimension of sentiment dynamics remains underexplored. This study develops a novel framework that enhances stock [...] Read more.
The inherent uncertainty and information asymmetry in financial markets create significant challenges for accurate price forecasting. Although investor sentiment analysis has gained traction in recent research, the temporal dimension of sentiment dynamics remains underexplored. This study develops a novel framework that enhances stock price prediction by integrating time-partitioned investor sentiment, while improving model interpretability via Shapley additive explanations (SHAP) analysis. Employing the ERNIE (enhanced representation through knowledge integration) 3.0 model for sentiment extraction from China’s Eastmoney Guba stock forum, we quantitatively distinguish intraday and post-market investor sentiment then integrate these temporal components with technical indicators through neural network architecture. Our results indicate that temporal sentiment partitioning effectively reduces uncertainty. Empirical evidence demonstrates that our long short-term memory (LSTM) model integrating intraday and post-market sentiment indicators achieves better prediction accuracy, and SHAP analysis reveals the importance of intraday and post-market investor sentiment to stock price prediction models. Implementing quantitative trading strategies based on these insights generates significantly more annualized returns for representative stocks with controlled risk, outperforming sentiment-agnostic and non-temporal sentiment models. This research provides methodological innovations for processing temporal unstructured data in finance, while the SHAP framework offers regulators and investors actionable insights into sentiment-driven market dynamics. Full article
Show Figures

Figure 1

29 pages, 515 KiB  
Article
Artificial Intelligence Models for Bankruptcy Prediction in Agriculture: Comparing the Performance of Artificial Neural Networks and Decision Trees
by Dominika Gajdosikova and Jakub Michulek
Agriculture 2025, 15(10), 1077; https://doi.org/10.3390/agriculture15101077 - 16 May 2025
Cited by 1 | Viewed by 1295
Abstract
Debt levels are a crucial factor when assessing the financial stability of agricultural firms, and excessive indebtedness is usually the most important indicator of financial distress. As agriculture is a capital-intensive sector with a high reliance on borrowed funds, firms in this sector [...] Read more.
Debt levels are a crucial factor when assessing the financial stability of agricultural firms, and excessive indebtedness is usually the most important indicator of financial distress. As agriculture is a capital-intensive sector with a high reliance on borrowed funds, firms in this sector are more vulnerable to insolvency. This study examines the performance of artificial neural networks (ANNs) and decision trees (DTs) in predicting the bankruptcy of Slovak agricultural enterprises. In an attempt to compare the models’ performances, the most consequential indebtedness ratios are investigated through machine learning approaches. ANN and DT models are found to perform significantly better than traditional forecast methods. ANN achieved an AUC of 0.9500, accuracy of 96.37%, precision of 96.60%, recall of 99.68%, and an F1-score of 98.12%, determining its robust predictive ability. DT performed a little better on AUC (0.9550) and achieved an accuracy of 97.78%, precision of 98.69%, recall of 99.01%, and an F1-score of 98.85%, determining its predictive ability and interpretability. These findings confirm the potential for applying AI-based models to enhance financial risk assessment. This study provides informative results for financial analysts, policymakers, and corporate managers in support of early intervention strategies. Additional research would be required to explore state-of-the-art AI techniques to further refine bankruptcy forecasting and financial decision-making in vulnerable sectors like agriculture. Full article
Show Figures

Figure A1

19 pages, 2005 KiB  
Article
Network Risk Diffusion and Resilience in Emerging Stock Markets
by Jiang-Cheng Li, Yi-Zhen Xu and Chen Tao
Entropy 2025, 27(5), 533; https://doi.org/10.3390/e27050533 - 16 May 2025
Viewed by 496
Abstract
With the acceleration of globalization, the connections between emerging market economies are becoming increasingly intricate, making it crucial to understand the mechanisms of risk transmission. This study employs the transfer entropy model to analyze risk diffusion and network resilience across ten emerging market [...] Read more.
With the acceleration of globalization, the connections between emerging market economies are becoming increasingly intricate, making it crucial to understand the mechanisms of risk transmission. This study employs the transfer entropy model to analyze risk diffusion and network resilience across ten emerging market countries. The findings reveal that Brazil, Mexico, and Saudi Arabia are the primary risk exporters, while countries such as India, South Africa, and Indonesia predominantly act as risk receivers. The research highlights the profound impact of major events such as the 2008 global financial crisis and the 2020 COVID-19 pandemic on risk diffusion, with risk diffusion peaking during the pandemic. Additionally, the study underscores the importance of network resilience, suggesting that certain levels of noise and shocks can enhance resilience and improve network stability. While the global economy gradually recovered following the 2008 financial crisis, the post-pandemic recovery has been slower, with external shocks and noise presenting long-term challenges to network resilience. This study emphasizes the importance of understanding network resilience and risk diffusion mechanisms, offering new insights for managing risk transmission in future global economic crises. Full article
(This article belongs to the Special Issue Complexity in Financial Networks)
Show Figures

Figure 1

27 pages, 5478 KiB  
Article
Hybrid LSTM–Transformer Architecture with Multi-Scale Feature Fusion for High-Accuracy Gold Futures Price Forecasting
by Yali Zhao, Yingying Guo and Xuecheng Wang
Mathematics 2025, 13(10), 1551; https://doi.org/10.3390/math13101551 - 8 May 2025
Viewed by 1943
Abstract
Amidst global economic fluctuations and escalating geopolitical risks, gold futures, as a pivotal safe-haven asset, demonstrate price dynamics that directly impact investor decision-making and risk mitigation effectiveness. Traditional forecasting models face significant limitations in capturing long-term trends, addressing abrupt volatility, and mitigating multi-source [...] Read more.
Amidst global economic fluctuations and escalating geopolitical risks, gold futures, as a pivotal safe-haven asset, demonstrate price dynamics that directly impact investor decision-making and risk mitigation effectiveness. Traditional forecasting models face significant limitations in capturing long-term trends, addressing abrupt volatility, and mitigating multi-source noise within complex market environments characterized by nonlinear interactions and extreme events. Current research predominantly focuses on single-model approaches (e.g., ARIMA or standalone neural networks), inadequately addressing the synergistic effects of multimodal market signals (e.g., cross-market index linkages, exchange rate fluctuations, and policy shifts) and lacking the systematic validation of model robustness under extreme events. Furthermore, feature selection often relies on empirical assumptions, failing to uncover non-explicit correlations between market factors and gold futures prices. A review of the global literature reveals three critical gaps: (1) the insufficient integration of temporal dependency and global attention mechanisms, leading to imbalanced predictions of long-term trends and short-term volatility; (2) the neglect of dynamic coupling effects among cross-market risk factors, such as energy ETF-metal market spillovers; and (3) the absence of hybrid architectures tailored for high-frequency noise environments, limiting predictive utility for decision support. This study proposes a three-stage LSTM–Transformer–XGBoost fusion framework. Firstly, XGBoost-based feature importance ranking identifies six key drivers from thirty-six candidate indicators: the NASDAQ Index, S&P 500 closing price, silver futures, USD/CNY exchange rate, China’s 1-year Treasury yield, and Guotai Zhongzheng Coal ETF. Second, a dual-channel deep learning architecture integrates LSTM for long-term temporal memory and Transformer with multi-head self-attention to decode implicit relationships in unstructured signals (e.g., market sentiment and climate policies). Third, rolling-window forecasting is conducted using daily gold futures prices from the Shanghai Futures Exchange (2015–2025). Key innovations include the following: (1) a bidirectional LSTM–Transformer interaction architecture employing cross-attention mechanisms to dynamically couple global market context with local temporal features, surpassing traditional linear combinations; (2) a Dynamic Hierarchical Partition Framework (DHPF) that stratifies data into four dimensions (price trends, volatility, external correlations, and event shocks) to address multi-driver complexity; (3) a dual-loop adaptive mechanism enabling endogenous parameter updates and exogenous environmental perception to minimize prediction error volatility. This research proposes innovative cross-modal fusion frameworks for gold futures forecasting, providing financial institutions with robust quantitative tools to enhance asset allocation optimization and strengthen risk hedging strategies. It also provides an interpretable hybrid framework for derivative pricing intelligence. Future applications could leverage high-frequency data sharing and cross-market risk contagion models to enhance China’s influence in global gold pricing governance. Full article
(This article belongs to the Special Issue Complex Process Modeling and Control Based on AI Technology)
Show Figures

Figure 1

27 pages, 1758 KiB  
Article
Cybersecure XAI Algorithm for Generating Recommendations Based on Financial Fundamentals Using DeepSeek
by Iván García-Magariño, Javier Bravo-Agapito and Raquel Lacuesta
AI 2025, 6(5), 95; https://doi.org/10.3390/ai6050095 - 2 May 2025
Viewed by 1401
Abstract
Background: Investment decisions in stocks are one of the most complex tasks due to the uncertainty of which stocks will increase or decrease in their values. A diversified portfolio statistically reduces the risk; however, stock choice still substantially influences the profitability. Methods: This [...] Read more.
Background: Investment decisions in stocks are one of the most complex tasks due to the uncertainty of which stocks will increase or decrease in their values. A diversified portfolio statistically reduces the risk; however, stock choice still substantially influences the profitability. Methods: This work proposes a methodology to automate investment decision recommendations with clear explanations. It utilizes generative AI, guided by prompt engineering, to interpret price predictions derived from neural networks. The methodology also includes the Artificial Intelligence Trust, Risk, and Security Management (AI TRiSM) model to provide robust security recommendations for the system. The proposed system provides long-term investment recommendations based on the financial fundamentals of companies, such as the price-to-earnings ratio (PER) and the net margin of profits over the total revenue. The proposed explainable artificial intelligence (XAI) system uses DeepSeek for describing recommendations and suggested companies, as well as several charts based on Shapley additive explanation (SHAP) values and local-interpretable model-agnostic explanations (LIMEs) for showing feature importance. Results: In the experiments, we compared the profitability of the proposed portfolios, ranging from 8 to 28 stock values, with the maximum expected price increases for 4 years in the NASDAQ-100 and S&P-500, where both bull and bear markets were, respectively, considered before and after the custom duties increases in international trade by the USA in April 2025. The proposed system achieved an average profitability of 56.62% while considering 120 different portfolio recommendations. Conclusions: A t-Student test confirmed that the difference in profitability compared to the index was statistically significant. A user study revealed that the participants agreed that the portfolio explanations were useful for trusting the system, with an average score of 6.14 in a 7-point Likert scale. Full article
(This article belongs to the Special Issue AI in Finance: Leveraging AI to Transform Financial Services)
Show Figures

Figure 1

23 pages, 4798 KiB  
Article
Rating the Impact of Risks in Banking on Performance: Utilizing the Adaptive Neural Network-Based Fuzzy Inference System (ANFIS)
by Riyadh Mehdi, Ibrahim Elsiddig Ahmed and Elfadil A. Mohamed
Risks 2025, 13(5), 85; https://doi.org/10.3390/risks13050085 - 30 Apr 2025
Cited by 1 | Viewed by 1661
Abstract
This study aims to rate the impact of the three major risks (credit, capital adequacy, and liquidity) on three financial performance measures (return on equity (ROE), earnings per share (EPS), and price-earnings ratio (PER)). This study stands out as one of the few [...] Read more.
This study aims to rate the impact of the three major risks (credit, capital adequacy, and liquidity) on three financial performance measures (return on equity (ROE), earnings per share (EPS), and price-earnings ratio (PER)). This study stands out as one of the few in its field, and the only one focusing on banks in the Middle East and Africa, to employ the adaptive neural network-based fuzzy inference system (ANFIS) that combines neural networks and fuzzy logic systems. The significance of this study lies in its comprehensive coverage of major risks and performance variables and its application of highly technical, sophisticated, and precise AI techniques (ANFIS). The main findings indicate that credit risk, as measured by the non-performing loans (NPL) has significant impact on both ROE and EPS. Liquidity risk comes second in importance for ROE and EPS, with the loan-deposit ratio (LDR) being the dominant component. In contrast, liquidity risk is the most significant determinant of PER, followed by capital adequacy. Our results also show that CAR, LDR, and NPL are the most significant risk components of capital adequacy, liquidity, and credit risks, respectively. The study contributes to business knowledge by applying the ANFIS technique as an accurate predictor of risk rating. Future research will explore the relationship between risks and macroeconomic indicators and differences among countries. Full article
Show Figures

Figure 1

Back to TopTop