Decision Analytics Journal最新文献_第2页

An adaptive learning framework for Alzheimer’s disease diagnosis using structural Magnetic Resonance Imaging data analytics 使用结构磁共振成像数据分析进行阿尔茨海默病诊断的自适应学习框架

Decision Analytics Journal Pub Date : 2026-03-01 Epub Date: 2025-12-12 DOI: 10.1016/j.dajour.2025.100667

Yingchao Huang , Yuhan Su , Xin Wang , Shanshan Yao

{"title":"An adaptive learning framework for Alzheimer’s disease diagnosis using structural Magnetic Resonance Imaging data analytics","authors":"Yingchao Huang , Yuhan Su , Xin Wang , Shanshan Yao","doi":"10.1016/j.dajour.2025.100667","DOIUrl":"10.1016/j.dajour.2025.100667","url":null,"abstract":"<div><div>Early and accurate diagnosis of Alzheimer’s disease (AD) is crucial for managing the disease and selecting therapies to slow its progression. Machine learning (ML) has demonstrated significant potential in improving its diagnostic accuracy with structural Magnetic Resonance Imaging (sMRI) data. However, developing robust ML models faces the challenge of domain shift in sMRI data caused by differences between datasets sources. These differences can lead to performance degradation when applying the ML models trained on one dataset to another. To address this issue, we propose a cross-domain learning framework tailored to classify AD, mild cognitive impairment (MCI), and cognitively normal (CN) subjects from sMRI data accounting for domain shift. Our approach begins by transfer-learning with pre-trained 3D ResNet50 using labeled images from the source domain. We then enhance the model through adversarial training using both source images and unlabeled target images and use the maximum mean discrepancy (MMD) to align the feature distributions across different domains at the same time. Building upon the adversarially trained model, we introduce a self-supervised learning stage with a teacher–student framework incorporated, which reduces class imbalance via dynamic class weights and reinforces domain alignment via MMD. Our proposed framework is validated to outperform existing domain adaptation approaches on 3T and 1.5T sMRI scans from Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset. Notably for MCI vs.CN classification, our model achieves a high enough accuracy of 86.86% to enable early detection of dementia.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"18 ","pages":"Article 100667"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145798619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An analytics-driven method for building ethical customer digital twins using neuromarketing and social media data 利用神经营销和社交媒体数据建立道德客户数字双胞胎的分析驱动方法

Decision Analytics Journal Pub Date : 2026-03-01 Epub Date: 2026-02-10 DOI: 10.1016/j.dajour.2026.100689

Ama Anomwaa Okyere Sefa , Mohammadreza Rezaei , Omid Fatahi Valilai

{"title":"An analytics-driven method for building ethical customer digital twins using neuromarketing and social media data","authors":"Ama Anomwaa Okyere Sefa , Mohammadreza Rezaei , Omid Fatahi Valilai","doi":"10.1016/j.dajour.2026.100689","DOIUrl":"10.1016/j.dajour.2026.100689","url":null,"abstract":"<div><div>As markets become increasingly digitalised, understanding the emotional and cognitive drivers of consumer behaviour is essential for developing responsive and targeted marketing strategies. This study contributes to the development of Customer Digital Twins (CDTs) by integrating neuromarketing techniques with social media analytics, positioning the work at the intersection of data science and behavioural psychology. The proposed framework combines electroencephalography (EEG) recordings with sentiment analysis of user-generated content to capture complementary dimensions of consumer emotion and decision making. An experimental design was implemented in which participants’ emotional responses were monitored via EEG during an online shopping task, followed by an ethical priming intervention and sentiment-based analysis of post-task responses. The study focuses on a fast-fashion e-commerce setting in which ethically framed information is introduced to examine how value-laden cues reshape cognitive and emotional states. The results show that EEG-derived indicators, including engagement, workload, and emotional valence, and text-based sentiment measures provide partially complementary views of consumer states, while also highlighting significant challenges in their direct integration. The joint use of these modalities offers richer descriptive insight into customer motivation and behaviour, but simple fusion strategies exhibit limited predictive power under real-world, asynchronous conditions. The findings identify both technical and ethical challenges associated with multimodal consumer modelling and establish a foundation for future work on temporally aligned and dynamically adaptive customer digital twin architectures. A proof-of-concept modelling exercise further explores the feasibility of using combined neuro-sentiment features to predict valence-related indices, serving as an initial diagnostic decision analytics layer rather than a fully realised digital twin.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"18 ","pages":"Article 100689"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147395644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A data-assimilative approach to air quality analytics for policy and emergency planning 为政策和应急规划采用数据同化的空气质量分析方法

Decision Analytics Journal Pub Date : 2026-03-01 Epub Date: 2026-02-05 DOI: 10.1016/j.dajour.2026.100688

Eeshwar Prasad Poudel , Shankar Pariyar , Jeevan Kafle , Shree Ram Khadka

{"title":"A data-assimilative approach to air quality analytics for policy and emergency planning","authors":"Eeshwar Prasad Poudel , Shankar Pariyar , Jeevan Kafle , Shree Ram Khadka","doi":"10.1016/j.dajour.2026.100688","DOIUrl":"10.1016/j.dajour.2026.100688","url":null,"abstract":"<div><div>Air pollution remains a pressing environmental and public health concern, particularly in urban and industrial regions, underscoring the need for reliable dispersion modeling and effective emission control strategies. This study presents a unified framework for a two-dimensional advection–diffusion equation incorporating molecular and turbulent mixing. An analytical eigenfunction solution provides a rigorous benchmark, while an efficient Alternating Direction Implicit scheme is employed for numerical simulation. Noisy synthetic observations are assimilated using a Kalman Filter, leading to improved concentration estimates and reduced model uncertainty. Based on these filtered states, an optimal control formulation is introduced to determine emission strategies that minimize pollutant levels and control costs. Coupling Pontryagin’s Maximum Principle with Kalman-filter-based state estimation yields a closed-loop, real-time control framework driven by data-informed states rather than purely model-based predictions. The approach is demonstrated through a case study motivated by air-quality data from Nepal, illustrating its effectiveness in data-limited environments and its relevance for emission management and emergency response applications.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"18 ","pages":"Article 100688"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147395650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A predictive analytics approach for forecasting global stock index returns using deep learning techniques 使用深度学习技术预测全球股票指数回报的预测分析方法

Decision Analytics Journal Pub Date : 2026-03-01 Epub Date: 2026-02-02 DOI: 10.1016/j.dajour.2026.100685

Liang Hu, Yinru Shen

{"title":"A predictive analytics approach for forecasting global stock index returns using deep learning techniques","authors":"Liang Hu, Yinru Shen","doi":"10.1016/j.dajour.2026.100685","DOIUrl":"10.1016/j.dajour.2026.100685","url":null,"abstract":"<div><div>Accurately predicting stock index returns remains a critical yet complex task due to the inherent volatility of financial markets and the intricate temporal dependencies within financial time series. This study presents a robust machine learning framework to forecast the relative returns of major global stock indices, including the Standard & Poor’s 500 Index (S&P 500), Financial Times Stock Exchange 100 Index (FTSE 100), Nikkei 225, Deutscher Aktienindex 30 (DAX 30), and Cotation Assistée en Continu 40 (CAC 40). The framework employs advanced deep learning models, including Long Short-Term Memory (LSTM), Dual-Layer Long Short-Term Memory (DL-LSTM), and Transformer architectures with Multi-Head Self-Attention, trained on both technical and fundamental indicators. The technical indicators include Exponential Moving Average, Relative Strength Index, Moving Average Convergence Divergence, and Bollinger Bands. In contrast, the fundamental indicators comprise Earnings Per Share, Price-to-Earnings ratio, Net Profit Margin, Return on Assets, and Dividend Yield. Experimental results show that the Dual-Layer Long Short-Term Memory model consistently outperforms baseline methods, particularly on the Standard & Poor’s 500 Index, achieving up to 78 percent accuracy, 81 percent precision, 76 percent recall, an F1 score of 80 percent, and a Brier Score of 0.46. These findings underscore the potential of combining advanced machine learning techniques with a comprehensive set of market indicators to enhance financial forecasting and support data-driven investment decision-making.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"18 ","pages":"Article 100685"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147395652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A review of mathematical models for pricing, risk, and optimization in cryptocurrency analytics 加密货币分析中定价、风险和优化的数学模型综述

Decision Analytics Journal Pub Date : 2026-03-01 Epub Date: 2025-12-29 DOI: 10.1016/j.dajour.2025.100670

Jairo Dote-Pardo , María Teresa Espinosa-Jaramillo

{"title":"A review of mathematical models for pricing, risk, and optimization in cryptocurrency analytics","authors":"Jairo Dote-Pardo , María Teresa Espinosa-Jaramillo","doi":"10.1016/j.dajour.2025.100670","DOIUrl":"10.1016/j.dajour.2025.100670","url":null,"abstract":"<div><div>The rapid expansion of cryptocurrencies and decentralized finance (DeFi) has redefined global financial systems, creating new challenges in asset pricing, risk measurement, and systemic stability. This study conducts a comprehensive review of 93 peer-reviewed articles published between 2019 and 2024 to consolidate the fragmented literature on mathematical models applied to cryptocurrencies and DeFi platforms. Using a mixed bibliometric–systematic approach based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework, the review integrates performance indicators, conceptual mapping, and qualitative synthesis to identify methodological advances and research trends. The findings reveal a progressive convergence between econometric models, such as the Generalized Autoregressive Conditional Heteroskedasticity (GARCH), stochastic volatility, and Lévy processes, and data-driven approaches based on machine learning (ML), deep learning (DL), and reinforcement learning (RL). These hybrid frameworks enhance predictive accuracy and adaptability in high-frequency and non-linear blockchain markets. The review also highlights optimization-based decision models that integrate Conditional Value-at-Risk (CVaR), network theory, and portfolio analytics for decentralized finance operations. However, interpretability, governance, and environmental sustainability remain underexplored dimensions. The study contributes by classifying mathematical approaches to pricing, volatility, and risk propagation, identifying methodological gaps, and recommending future research on explainable artificial intelligence (AI), environmental and cyber-risk modeling, and real-time validation for transparent and resilient decentralized financial ecosystems.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"18 ","pages":"Article 100670"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An analysis of machine learning approaches for enhancing decision-making in complex discrete choice tasks 在复杂离散选择任务中增强决策的机器学习方法分析

Decision Analytics Journal Pub Date : 2026-03-01 Epub Date: 2025-12-23 DOI: 10.1016/j.dajour.2025.100668

Sheng Lun (Christine) Cao , Destenie Nock , Alex Davis

{"title":"An analysis of machine learning approaches for enhancing decision-making in complex discrete choice tasks","authors":"Sheng Lun (Christine) Cao , Destenie Nock , Alex Davis","doi":"10.1016/j.dajour.2025.100668","DOIUrl":"10.1016/j.dajour.2025.100668","url":null,"abstract":"<div><div>Discrete choice modeling is a common tool used for preference elicitation during policy-making, but this is typically done through parametric models. Machine learning can push the boundaries of discrete choice modeling for policy-based preference elicitation by adopting a data-driven approach for learning individual preferences. However, there is limited knowledge of how well machine learning methods can estimate individual discrete choice rules under individual heterogeneity, especially in the context of challenges often experienced during preference elicitation. This study evaluates four machine learning models (multinomial logistic regression, generalized additive model, twinned neural network, and Gaussian process) with respect to their capacity to learn and predict five choice rules that are important in the behavioral and social sciences (linear strong utility, monotonic strong utility, ideal point, lexicographic semiorder, and multiattribute linear ballistic accumulator). Monte Carlo experiments were performed to assess model performance when increasing a) the number of attributes in the choice alternatives, b) the number of training choice sets, and c) the choice rule’s determinism. The simulation results demonstrated that semi-parametric and non-parametric models generally outperform parametric models across all choice rules and experimental contexts. Model performance also generally improves by 6% to 96% and 0% to 55%, respectively, with an increase in training choice sets and choice rule determinism. A case study using real energy policy preference data was also conducted, where TNN performed best with a BIC of 13.351. This work demonstrated the viability and limitations of semi-parametric and non-parametric models in the context of policy-centric discrete choice modeling and showed how the choice task context should drive model selection.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"18 ","pages":"Article 100668"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An integrated bibliometric analysis of Benefit of the Doubt composite indicators for policy and decision analysis 综合文献计量学分析的怀疑利益综合指标的政策和决策分析

Decision Analytics Journal Pub Date : 2026-03-01 Epub Date: 2025-12-31 DOI: 10.1016/j.dajour.2025.100672

Thyago Nepomuceno , Flávia Barbosa , Hermilio Vilarinho , Ana Camanho

引用次数: 0

An analytical approach to multimodal backhaul optimization in agro supply chains 农业供应链中多模式回程优化的分析方法

Decision Analytics Journal Pub Date : 2026-03-01 Epub Date: 2026-01-16 DOI: 10.1016/j.dajour.2026.100677

Bruna Fernanda Ribeiro Lopes , Andréa Leda Ramos de Oliveira , Priscila Cristina Berbert Rampazzo , Diego A. de J. Pacheco

{"title":"An analytical approach to multimodal backhaul optimization in agro supply chains","authors":"Bruna Fernanda Ribeiro Lopes , Andréa Leda Ramos de Oliveira , Priscila Cristina Berbert Rampazzo , Diego A. de J. Pacheco","doi":"10.1016/j.dajour.2026.100677","DOIUrl":"10.1016/j.dajour.2026.100677","url":null,"abstract":"<div><div>Agro-industrial sectors in developing economies have achieved significant productivity gains through technology adoption, yet their global competitiveness remains constrained by high logistics costs and dependence on imported fertilizers. This study proposes an integrated multi-commodity optimization model for coordinated soybean and fertilizer logistics that incorporates multimodal transport options, operational capacity constraints, minimum-load requirements, and backhauling strategies. The model enables a comprehensive assessment of different logistical configurations and their impacts on product flow. Six scenarios are examined, including single-product and multi-product settings, with and without capacity constraints, and with return flows activated. The results indicate that capacity limitations substantially reshape flow patterns, leading to route diversification and increased reliance on alternative intermodal corridors. In the multi-product configurations, backhauling strategies enhance the integration between soybean and fertilizer supply chains, promoting a more balanced use of transport resources and improving system adaptability. These effects are particularly evident under constrained conditions, where return flows reduce the dependence on saturated corridors. Overall, the findings highlight the importance of collaborative logistics and intermodal planning. The analysis suggests that Scenario 6 represents the most appropriate operational configuration, since it shows that under more restrictive conditions, backhaul strategies play a decisive role in reorganizing freight flows and mitigating inefficiencies, leading to a more balanced logistics network. The proposal offers valuable insights for infrastructure planning and strategic decision-making.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"18 ","pages":"Article 100677"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An analytical framework for optimizing task scheduling and routing in internet installation services 互联网安装服务中优化任务调度和路由的分析框架

Decision Analytics Journal Pub Date : 2026-03-01 Epub Date: 2026-01-10 DOI: 10.1016/j.dajour.2026.100675

Apicha Kotekangpoo, Pavee Siriruk

{"title":"An analytical framework for optimizing task scheduling and routing in internet installation services","authors":"Apicha Kotekangpoo, Pavee Siriruk","doi":"10.1016/j.dajour.2026.100675","DOIUrl":"10.1016/j.dajour.2026.100675","url":null,"abstract":"<div><div>The growing demand for internet installation services in Thailand has led to persistently full schedules, resulting in delays beyond standard working hours or task cancellations. These delays stem from inefficient scheduling, which results in unbalanced task distribution, varying task complexity, and impractical time allocations for cable installation and travel. To address these challenges, this study proposes task allocation optimization techniques to mitigate installation delays. The earliest due date rule is applied to prioritize installation tasks based on customer appointments, and K-medoids clustering is employed to group customer locations and reduce the complexity of a mixed-integer programming model. Unlike prior studies, the capacitated vehicle routing problem of this study is adapted to internet installation services by incorporating real-world operational conditions into both the objective function and the operational constraint set. Numerical experiments demonstrate that the proposed methodology reduces delayed tasks, total time, and total cost by 84.27%, 33.65%, and 37.73%, respectively. Each installation team operates within allotted working hours, with no more than five tasks per day. Overall, the proposed framework effectively eliminates delayed and cancelled installation tasks, thereby improving scheduling efficiency and enhancing operational performance.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"18 ","pages":"Article 100675"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A social welfare analytics approach to order allocation under passenger cancellations 乘客取消情况下订单分配的社会福利分析方法

Decision Analytics Journal Pub Date : 2026-03-01 Epub Date: 2025-12-30 DOI: 10.1016/j.dajour.2025.100671

Yan Xia, Chunyi Ji, Wuyong Qian

{"title":"A social welfare analytics approach to order allocation under passenger cancellations","authors":"Yan Xia, Chunyi Ji, Wuyong Qian","doi":"10.1016/j.dajour.2025.100671","DOIUrl":"10.1016/j.dajour.2025.100671","url":null,"abstract":"<div><div>The rise of ride-hailing platforms has transformed passenger experiences and reshaped taxi market operations. To enhance cruising efficiency and increase revenue, Chinese taxis have adopted a dual-mode operation combining online and offline services. This study examines passenger order cancellation behavior when taxis receive both online platform dispatches and street-hail pickups. We develop a probability model for order cancellations triggered by encountering vacant cruising taxis. A social welfare model is constructed to analyze the revenue structures of platforms, drivers, and passengers. Optimal order allocation ratios are investigated through sensitivity analysis, considering passenger time costs, cancellation penalties, ride-hailing prices, and differential taxi pricing strategies. Key findings reveal seven distinct cancellation scenarios. Reducing taxi order allocation ratios improves passenger experience. Optimal utility for platforms, drivers, and passengers is achieved with shorter online dispatch arrival times, informing recommended pickup durations. Driver earnings are suboptimal in certain scenarios, suggesting platform dispatch decisions should balance platform revenue, passenger utility, and social welfare. This research provides actionable insights for platform operations while advancing theoretical understanding of dual-mode taxi services in ride-hailing ecosystems.</div></div>","PeriodicalId":100357,"journal":{"name":"Decision Analytics Journal","volume":"18 ","pages":"Article 100671"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0