Data Science and Management最新文献

Breathing rewards: dynamic market-aware portfolio optimization 呼吸奖励：动态市场感知投资组合优化

Data Science and Management Pub Date : 2026-09-01 Epub Date: 2026-01-30 DOI: 10.1016/j.dsm.2026.01.003

Qing Zhu, Baoqin Xie, Yuze Li, Jiamiao Zhao

{"title":"Breathing rewards: dynamic market-aware portfolio optimization","authors":"Qing Zhu, Baoqin Xie, Yuze Li, Jiamiao Zhao","doi":"10.1016/j.dsm.2026.01.003","DOIUrl":"10.1016/j.dsm.2026.01.003","url":null,"abstract":"<div><div>In recent years, rising geopolitical tensions, trade protectionism, and demand for safe-haven assets have driven a notable surge in financial market volatility, exposing the limitations of both traditional static and prediction-driven investment strategies. Existing reinforcement learning (RL) studies typically adopt fixed-reward designs, which limit their adaptability in non-stationary markets. To address this gap, this paper proposes a RL framework, variational mode decomposition-proximal policy optimization (VMD-PPO), that integrates VMD with PPO. The framework leverages VMD to extract multi-scale market signals, employs PPO to optimize trading policies, and introduces a market-state-adaptive reward mechanism that dynamically balances return, risk, and transaction costs, overcoming the rigidity of static rewards in prior research. An empirical study centered on portfolio construction demonstrates that the VMD-PPO framework achieves superior performance across key metrics, including returns, maximum drawdown, and risk-adjusted returns, while consistently exhibiting strong robustness under various market trends. Unlike prior research, which primarily focuses on prediction accuracy, this study emphasizes adaptability and deployability, providing both a foundation and a practical pathway for applying RL to highly volatile financial assets.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"9 3","pages":"Article 100178"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149050814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Governance failures in blockchain ecosystems: insights from a collaborative platform collapse 区块链生态系统中的治理失败：来自协作平台崩溃的见解

Data Science and Management Pub Date : 2026-09-01 Epub Date: 2026-07-09 DOI: 10.1016/j.dsm.2026.100193

Issam Najati

{"title":"Governance failures in blockchain ecosystems: insights from a collaborative platform collapse","authors":"Issam Najati","doi":"10.1016/j.dsm.2026.100193","DOIUrl":"10.1016/j.dsm.2026.100193","url":null,"abstract":"<div><div>This study examines governance failures in blockchain-based ecosystems through an in-depth case study of TradeLens, a collaborative supply chain platform co-developed by IBM and Maersk. Drawing on Elinor Ostrom's theory of the commons, reconceptualized for digital infrastructures, the analysis investigates how inadequate institutional arrangements contributed to the platform's premature discontinuation. A qualitative single-case design was employed, combining ten semi-structured expert interviews with an extensive documentary analysis, informed by informal discussions that provided contextual background. Data were coded through a three-phase iterative thematic process guided by Ostrom's design principles. The analysis identifies five interrelated governance shortcomings: excessive centralization of authority, limited procedural transparency and monitoring, rigidity of rules, limited small business involvement, and communication problems. These shortcomings eroded stakeholder trust and progressively undermined the platform's institutional viability. The study develops a conceptual model of governance breakdown in blockchain ecosystems and derives theoretical propositions regarding the institutional conditions for sustaining blockchain-based digital commons. By extending Ostrom's framework to blockchain-based infrastructures, this research contributes to the literature on decentralized governance and provides empirically grounded insights into the institutional design and governance of blockchain consortia.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"9 3","pages":"Article 100193"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148952650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The impact of digital transformation on sustainable supply chain performance: the mediating effect of service innovation 数字化转型对可持续供应链绩效的影响：服务创新的中介效应

Data Science and Management Pub Date : 2026-09-01 Epub Date: 2026-02-19 DOI: 10.1016/j.dsm.2026.02.001

Yongtao Peng, Zhijie Xiao, Yaya Li

{"title":"The impact of digital transformation on sustainable supply chain performance: the mediating effect of service innovation","authors":"Yongtao Peng, Zhijie Xiao, Yaya Li","doi":"10.1016/j.dsm.2026.02.001","DOIUrl":"10.1016/j.dsm.2026.02.001","url":null,"abstract":"<div><div>Amid accelerating global economic integration and escalating imperatives for sustainable development, digital transformation (DT) and service innovation (SI) have evolved into pivotal drivers of sustainable supply chain modernization. Although DT has been widely recognized for enhancing supply chain continuity and performance, the mediating role of SI remains insufficiently explored. This study examines how SI bridges the link between DT and sustainable supply chain performance (SSCP) by drawing on empirical data from Chinese A-share listed manufacturing firms from 2010 to 2023. The findings highlight SI as a significant partial mediator of DT’s impact on SSCP, with mediation effects occurring primarily through service process innovation, while service product innovation exhibits a statistically significant but economically very small mediating effect, whereas the mediating effect of service model innovation is negative but statistically non-significant. By identifying SI as a novel mediating mechanism, this study adds to the expanding body of research on DT and SSCP, offering both theoretical and actionable insights. It further provides a practical framework for organizations to bolster supply chain resilience and sustainability in real-world settings.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"9 3","pages":"Article 100179"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148995801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Generative artificial intelligence in education: a comprehensive analysis based on bibliometrics 教育中的生成式人工智能：基于文献计量学的综合分析

Data Science and Management Pub Date : 2026-09-01 Epub Date: 2026-03-27 DOI: 10.1016/j.dsm.2026.100181

Xiaojie Ma, Wenlong Zhu

{"title":"Generative artificial intelligence in education: a comprehensive analysis based on bibliometrics","authors":"Xiaojie Ma, Wenlong Zhu","doi":"10.1016/j.dsm.2026.100181","DOIUrl":"10.1016/j.dsm.2026.100181","url":null,"abstract":"<div><div>Currently, generative artificial intelligence (GAI) is advancing rapidly and being increasingly adopted. However, systematic and comprehensive analyses of its integration into educational management are scarce. This study employs bibliometric analysis supplemented by visualization tools to conduct multi-dimensional statistical analyses of 506 valid studies retrieved from the Web of Science database, aiming to depict the current research status and evolutionary trends of GAI in educational management. The quantitative analysis yielded four key findings: first, publication output showed an overall upward trend, with a sharp increase after 2022, suggesting that this topic may attract increasing research attention; second, GAI exhibits a dual nature in educational management applications, with no clear predominance of merits over demerits; third, research on GAI in educational management spans multiple application contexts, while cross-domain collaboration across subfields remains to be strengthened; fourth, the findings suggest that future research may increasingly focus on GAI tool innovation and intelligent educational management. Theoretically, this study delineates the research trajectory of GAI applications in educational management, offering data-backed support and decision-making insights for the formulation of relevant policies and practical implementation of GAI in educational management practices.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"9 3","pages":"Article 100181"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149003988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Digital economy, digital-real integration, and high-quality development of firms 数字经济、数实融合与企业高质量发展

Data Science and Management Pub Date : 2026-09-01 Epub Date: 2026-02-27 DOI: 10.1016/j.dsm.2026.02.002

Bin Li, Ang Li

{"title":"Digital economy, digital-real integration, and high-quality development of firms","authors":"Bin Li, Ang Li","doi":"10.1016/j.dsm.2026.02.002","DOIUrl":"10.1016/j.dsm.2026.02.002","url":null,"abstract":"<div><div>The digital economy (DE) plays an important role in promoting the high-quality development of firms (HQDF). Using data from Chinese A-share listed companies on the Shanghai and Shenzhen stock exchanges from 2012 to 2023, this study examines the impact of DE on HQDF and the underlying mechanisms. Findings indicate that DE significantly promotes HQDF through three key implementation mechanisms rooted in digital-real integration: technological breakthroughs, factor reallocation, and industrial transformation and upgrading. Compared with the equity dimension, DE shows larger estimated coefficients for the efficiency and sustainability dimensions of HQDF. Heterogeneity analysis shows that this effect is more pronounced in state-owned firms, non-high-tech firms, and regions with a high degree of digital-real integration (i.e., eastern and central China). Additionally, the positive role of DE in promoting HQDF is strengthened through improved intellectual property protection and digital infrastructure construction. This study enriches the literature on the coordinated development mechanism of DE and the real economy and provides new theoretical and empirical evidence on how firms can achieve high-quality development in the current economic context.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"9 3","pages":"Article 100180"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149003987","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Interpretable hydropower forecasting method using two-stage decomposition and its management applications 水电两阶段分解可解释预测方法及其管理应用

Data Science and Management Pub Date : 2026-09-01 Epub Date: 2026-05-12 DOI: 10.1016/j.dsm.2026.100191

Jiacheng Lin, Binrong Wu, Ruiyu Gao, Huanze Zeng

{"title":"Interpretable hydropower forecasting method using two-stage decomposition and its management applications","authors":"Jiacheng Lin, Binrong Wu, Ruiyu Gao, Huanze Zeng","doi":"10.1016/j.dsm.2026.100191","DOIUrl":"10.1016/j.dsm.2026.100191","url":null,"abstract":"<div><div>As a premier renewable energy source for power generation, hydropower boasts substantial construction scale and robust generation capacity. Amid the global energy crisis, precise hydropower forecasting is becoming increasingly crucial, providing governments with a vital foundation for devising energy strategies and supporting the transition to a stable, clean energy future. Although previously applied methods for predicting hydropower generation have achieved commendable results, it is difficult for them to capture the significant seasonality and inherent uncertainty of hydropower generation, and they tend to overlook the importance of internal explainability in forecasting models. An innovative and explainable hydropower generation prediction model consisting of a two-stage decomposition method for input data processing, polar lights optimization (PLO) for hyperparameter optimization, and a temporal fusion transformer (TFT) is employed to address the above limitations. First, a series of subsequences is adaptively obtained using a two-stage decomposition strategy, allowing for a more thorough exploration of the inherent wave characteristics of complex short-term hydroelectric power generation sequences. Subsequently, polar lights optimization was utilized to intelligently and effectively optimize the parameters in the TFT model, guaranteeing the steadfastness and dependability of the prognostic structure. The empirical results indicate that the proposed model exhibits good predictive performance on the evaluated test sets in short-term hydropower forecasting datasets. By exploring the interpretation of hydropower forecasting results, decision-makers can gain a better understanding of future hydropower production capacity, thereby optimizing resource allocation, managing risks, and ensuring the stability of electricity supply.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"9 3","pages":"Article 100191"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149153333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Immersion for all? Rethinking equity and fatigue in the XR era: a literature review of immersive technology 让所有人都沉浸其中？重新思考XR时代的公平和疲劳：沉浸式技术的文献综述

Data Science and Management Pub Date : 2026-09-01 Epub Date: 2026-07-02 DOI: 10.1016/j.dsm.2026.100192

Eunji Choi, Jian Mou

{"title":"Immersion for all? Rethinking equity and fatigue in the XR era: a literature review of immersive technology","authors":"Eunji Choi, Jian Mou","doi":"10.1016/j.dsm.2026.100192","DOIUrl":"10.1016/j.dsm.2026.100192","url":null,"abstract":"<div><div>Immersive technologies, including virtual, augmented, mixed, and extended reality (XR), are transforming how people learn, heal, travel, and consume. This literature review analyzed 95 peer-reviewed publications published between 2017 and 2025 across six domains: education, healthcare, tourism and cultural heritage, business and marketing, the metaverse, and others (e.g., review papers). The findings revealed that immersive applications could significantly enhance engagement, empathy, and learning effectiveness; however, they frequently induce cognitive overload, privacy risks, and unequal access. In education and healthcare, immersive technologies offer substantial benefits for training and rehabilitation but remain challenged by fatigue, ethical safeguards, and technological dependence. Tourism and cultural heritage research has highlighted that immersive storytelling fosters empathy and preservation, but long-term inclusivity and sustainability are limited. In business and marketing, XR-enabled experiences strengthened trust and consumer–brand relationships, but increased user exhaustion and exclusion. Furthermore, metaverse research has underscored the importance of social presence, identity formation, and collaboration, while revealing persistent governance and accessibility gaps. Synthesizing across these domains, the review identifies four crosscutting challenges: (1) emotional polarization, (2) cognitive and ethical fatigue, (3) design-context misalignment, and (4) socioeconomic inequities. From a sociotechnical perspective, these tensions illustrate how immersive technologies empower and exhaust users. This study advances theoretical understanding by integrating the affective and structural dimensions of XR adoption, and offers practical guidance for designing emotionally sustainable, contextually grounded, and socially responsible immersive environments.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"9 3","pages":"Article 100192"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149153332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Information systems auditing of psychiatric diagnoses using context-enriched QA-based language models 使用上下文丰富的基于qa的语言模型的精神诊断信息系统审计

Data Science and Management Pub Date : 2026-09-01 Epub Date: 2026-02-13 DOI: 10.1016/j.dsm.2026.01.002

William (Hongmin) Du, Guanghua Wang, Jiahui (Norah) Xu, Miklos A. Vasarhelyi

引用次数: 0

Multi-source heterogeneous data fusion using vector concatenation for quality fluctuation analysis 基于矢量拼接的多源异构数据融合质量波动分析

Data Science and Management Pub Date : 2026-06-01 Epub Date: 2025-10-27 DOI: 10.1016/j.dsm.2025.10.003

Sheng Hu, Xinyu Zheng, Qingan Qiu, Rongfa Wei

{"title":"Multi-source heterogeneous data fusion using vector concatenation for quality fluctuation analysis","authors":"Sheng Hu, Xinyu Zheng, Qingan Qiu, Rongfa Wei","doi":"10.1016/j.dsm.2025.10.003","DOIUrl":"10.1016/j.dsm.2025.10.003","url":null,"abstract":"<div><div>Big data mining is an important driver of quality control in intelligent manufacturing; however, conventional approaches often rely on a single data source, limiting their accuracy and applicability. In this study, a multi-source heterogeneous data integration method was developed for modeling quality fluctuations. One-dimensional image data are characterized using gray-level co-occurrence matrix parameters and fused with structured process data through vector concatenation. The fused features are then extracted using kernel principal component analysis to capture quality variations accurately. Experiments demonstrated a monitoring accuracy of 98.57% for the training set and 96.67% for the test set, outperforming models based on single-source data. From a managerial perspective, the proposed approach provides a data-driven tool for early detection of process anomalies, enabling production managers to reduce defects, improve operational efficiency, and support informed decision-making in intelligent manufacturing environments. This methodology advances both the precision and the applicability of industrial quality monitoring, offering practical value for data-driven production management.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"9 2","pages":"Article 100172"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148527435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Investors’ behavior-based nonlinear goal programming models for financial portfolio selection considering future stock market trends 考虑未来股市走势的基于投资者行为的非线性目标规划模型

Data Science and Management Pub Date : 2026-06-01 Epub Date: 2025-10-09 DOI: 10.1016/j.dsm.2025.09.004

Mohamed Sadok Cherif, Nabil Mansour

{"title":"Investors’ behavior-based nonlinear goal programming models for financial portfolio selection considering future stock market trends","authors":"Mohamed Sadok Cherif, Nabil Mansour","doi":"10.1016/j.dsm.2025.09.004","DOIUrl":"10.1016/j.dsm.2025.09.004","url":null,"abstract":"<div><div>Financial markets are ever-changing, and portfolio selection (PS) problems frequently involve multiple optimization objectives in an imprecise investment environment. Real-world investors attempt to select a portfolio based on their preferences for each objective and their decision-making behaviors. Moreover, integrating investor behavior according to predicted future stock market trends results in more appropriate portfolios. To address such situations, we propose a multi-objective approach for modeling investors’ preferences regarding several objectives (portfolio return, risk, and beta) as well as their decision behaviors in relation to future market scenarios. Additionally, real-world features such as cardinality and diversification constraints were considered. This study proposes a novel behavior-based nonlinear goal programming model for PS that aligns with stock market trends. The concept of behavioral functions is introduced to model investors’ decisions in the portfolio optimization process. To clarify the effects of different risk attitudes on PS, we examined three commonly used types of risk: risk-averse, risk-neutral, and risk-seeking. Our approach is validated using the S&P 100, where three distinct investment scenarios (sideways, upward, and downward moving market trends) are analyzed separately. The proposed PS models are then applied to determine the best portfolios, demonstrating their effectiveness in formulating and integrating investor preferences and behaviors.</div></div>","PeriodicalId":100353,"journal":{"name":"Data Science and Management","volume":"9 2","pages":"Article 100168"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148527434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0