Supply Chain Analytics最新文献

{"title":"A machine learning framework for classifying customer advocacy in sustainable supply chains","authors":"Brintha Rajendran ,&nbsp;Angappa Gunasekaran ,&nbsp;Manivannan Babu","doi":"10.1016/j.sca.2025.100137","DOIUrl":"10.1016/j.sca.2025.100137","url":null,"abstract":"<div><div>Sustainable supply chain management plays a pivotal role in shaping corporate reputation and enhancing customer loyalty in the contemporary market. This study uniquely integrates regional, demographic, and psychographic data with advanced machine learning methodologies, including clustering, decision trees, and association rule mining, to classify and predict customer advocacy based on Environmental, Social, and Governance (ESG) performance indicators and supply chain risk management. Unlike previous research, the analysis explicitly segments customers by their distinct ESG trust perceptions and advocacy behaviours, providing nuanced insights into how varying demographic and regional characteristics influence customer support for sustainable practices. Results reveal that customer advocacy patterns significantly differ across segments, particularly highlighting groups with strong environmental concerns and positive evaluations of governance practices. The study’s comprehensive approach not only advances theoretical understanding by integrating diverse customer attributes but also delivers precise, actionable recommendations for supply chain managers to foster targeted and effective sustainable initiatives.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"11 ","pages":"Article 100137"},"PeriodicalIF":0.0,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144296778","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}

{"title":"An analytical framework for evaluating the impact of Artificial Intelligence technologies in supply chains","authors":"Eduardo e Oliveira ,&nbsp;Maria Teresa Pereira ,&nbsp;Alcibíades P. Guedes","doi":"10.1016/j.sca.2025.100129","DOIUrl":"10.1016/j.sca.2025.100129","url":null,"abstract":"<div><div>This study introduces a novel framework for analyzing the impact of technologies through their effect and maturity, allowing for a clear presentation of the literature review results. We then conduct a literature review on applying Artificial Intelligence (AI) to Supply Chain (SC), focusing on evaluating the impact of existing technologies. The proposed framework is based on three axes: (1) maturity axis, which evaluates the readiness level of each technology and its current spread of use, (2) effect axis, which measures the disruption it can bring in terms of performance improvement and the number of potential applications, and (3) full axis, which combines the previous two axes. The proposed novel framework allows researchers to look at the existing literature differently. It makes it easier for practitioners to read and understand the impact of such AI technologies on SC. For the literature review that validates the framework, we have analyzed 24 literature review papers and 118 application papers on this topic. We have grouped the application papers into 90 technologies and used the proposed framework to evaluate them. From the analysis and discussion, we confirm some previous conclusions made in the literature as well as discover new gaps, and we suggest research avenues to be explored.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"11 ","pages":"Article 100129"},"PeriodicalIF":0.0,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144270763","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}

{"title":"A Markov decision process model for enhancing resilience in food supply chains during natural disasters","authors":"Mengfei Chen ,&nbsp;Mohamed Kharbeche ,&nbsp;Mohamed Haouari ,&nbsp;Weihong Guo Grace","doi":"10.1016/j.sca.2025.100136","DOIUrl":"10.1016/j.sca.2025.100136","url":null,"abstract":"<div><div>Natural disasters like hurricanes, earthquakes, and floods devastate food supply chains and can threaten food security and public health. These disruptions, from production to consumption, lead to shortages, increased waste, and heightened vulnerability among food-insecure populations. This study addresses the need for effective emergency strategies to ensure food continuity and equity during crises. A Markov Decision Process (MDP)-based model is proposed to enhance food supply chain resilience under disaster conditions. The model involves a two-stage decision-making process: Stage 1 focuses on strategic decisions for immediate response, such as facility reconstruction, and Stage 2 handles tactical decisions during relief efforts, such as transportation routes and product flow. The objective functions of our model include minimizing response time and costs and ensuring equity of food accessibility. A resilience assessment approach is proposed to evaluate the performance of Pareto solutions. The proposed method is applied to the Qatar beef supply chain during a flooding scenario, demonstrating practical effectiveness. Sensitivity analysis is conducted to identify critical thresholds for establishing alternative distribution centers, which helps to optimize responses based on facility capacity. This research improves disaster preparedness and response, ensuring that food supply chains can adapt and recover quickly while enhancing the equity of people’s access to food and nutrition. A case study on Qatar’s beef supply chain under flood conditions shows that the proposed method achieves up to 95 % reduction in response time cost, a 9 % improvement in system resilience, and maintains over 99.5 % food accessibility under severe disruption scenarios.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"11 ","pages":"Article 100136"},"PeriodicalIF":0.0,"publicationDate":"2025-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144296779","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}

{"title":"An analytics-driven framework for securing industrial IoT-Enabled Supply Chain Management Systems","authors":"Naveen Saran ,&nbsp;Nishtha Kesswani","doi":"10.1016/j.sca.2025.100128","DOIUrl":"10.1016/j.sca.2025.100128","url":null,"abstract":"<div><div>In today’s dynamic technological environment, the integration of IoT into Supply Chain Management Systems (SCMS) has significantly enhanced functionality, visibility, and decision-making. However, integrating Industrial-IoT (IIoT) with Supply Chain Networks (SCN) is an equally significant security concern because of interconnected systems amplified exposure and complexity. This study proposes an original Intrusion Detection System (IDS) framework based on the Staked Ensemble Model appropriate for IIoT-Enabled SCMS. A stacked ensemble model-based IDS framework operates as a novel solution to protect IIoT-Enabled SCMS. A multilayered system unites Extreme Gradient Boosting (XGBoost) with Light Gradient Boosting Machine (LightGBM) along with Deep Neural Networks (DNN) as a stacked ensemble design to enable decentralized and secure collaborative learning across the supply chain network and protect user data and maintain system stability as well as network reliability. On the other hand, Synthetic Minority Oversampling Technique (SMOTE) and Principal Component Analysis (PCA) are established techniques, and our contribution is in optimizing the application of those for IIoT traffic. We tackle the class imbalance in intrusion data with SMOTE to better detect rare attacks and to use PCA to reduce the high dimensions of feature space for less computational effort and more efficient pattern recognition. To meet the requirements of the IIoT use cases, these preprocessing techniques are effectively embedded in the framework. Moreover, the proposed modular IDS architecture, the curation and fine tuning of the various learners, and the approach to full validation are all novel. We rigorously evaluate the model under K-Fold Cross Validation using the IoT-23 dataset and prove superior detection performance when compared to state-of-the-art approaches. Specifically, this research contributes a scalable and efficient IDS for an IIoT scenarios such as real-world IIoT enabled SCMS, which improves security analytics and facilitates network defense in key operational functionalities such as low data rates, low computational resources availability and restricted communication over the year.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"11 ","pages":"Article 100128"},"PeriodicalIF":0.0,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144254828","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}

{"title":"A two-period game-theoretic model for the equilibrium decisions in the presence of strategic inventory in supply chain management","authors":"Subrata Saha","doi":"10.1016/j.sca.2025.100127","DOIUrl":"10.1016/j.sca.2025.100127","url":null,"abstract":"<div><div>Investment efforts by the upstream manufacturer and the downstream retailer to stimulate sales are prevalent in different industries. Likewise, the downstream retailers could hold inventory strategically as a bargaining chip to induce the upstream manufacturer to reduce future wholesale prices in the supply chain. Anticipating such strategic behavior of the retailer, the manufacturer responds by increasing the early period wholesale price, which might weaken the impact of the investment efforts due to a rising price. Our central research questions are: Under what conditions do the retailer and the manufacturer benefit from investment effort, and how does strategic inventory affect the efficiency of the supply chain? Therefore, we develop a two-period game-theoretic model and characterize the equilibrium decisions and profits for inventory holding and investment effort patterns. Results demonstrate that the retailer’s inventory holding decision can significantly reduce the impact of the manufacturer’s investment effort, and the manufacturer even receives lower profits compared to the scenario where strategic inventory is not withheld. The finding contrasts with the existing research, which suggests that the manufacturer always receives higher profit if the retailer holds inventory in a supply chain. Further, we investigate the incremental or detrimental effect of base demand on the second period. We find that the retailer’s strategic inventory can hurt both members of the supply chain even if there is a sizable increment in market size in the second period, and both members could be worse off.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"11 ","pages":"Article 100127"},"PeriodicalIF":0.0,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144254827","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}

{"title":"An analytical review of predictive methods for delivery delays in supply chains","authors":"Norman Müller,&nbsp;Peter Burggräf,&nbsp;Fabian Steinberg,&nbsp;Carl René Sauer,&nbsp;Maximilian Schütz","doi":"10.1016/j.sca.2025.100130","DOIUrl":"10.1016/j.sca.2025.100130","url":null,"abstract":"<div><div>Predicting delivery delays is crucial for companies, especially in times of increasing global uncertainty and vulnerable supply chains. Machine learning (ML) offers significant potential to improve the forecast performance and quality of delivery delay prediction. Although various prediction approaches have been proposed in research, a structured and comprehensive overview is lacking. This paper addresses this gap by conducting a systematic literature review on the direct prediction of delivery delays. The objective is to identify applied prediction approaches and data sources, assess their readiness for real-world implementation, and derive a research agenda. The findings reveal that current research often focuses on marginal optimization of prediction performance while lacking practical applicability. Furthermore, most studies emphasize classifying deliveries as on time or delayed, rather than predicting the actual delay magnitude. Regarding the data used for prediction, combining enterprise resource planning (ERP) data with data from logistics improves prediction performance. However, environmental and location data, which could be easily integrated into ERP-based ML models, are rarely considered. This indicates a misalignment in current research, emphasizing the need for models combining practical applicability with predictive accuracy. Further research is required to address these identified deficits. Therefore, the present paper proposes a research agenda, to prioritize the most important deficits. These include, among others the industrial application, optimal prediction timing and ideal data combinations to achieve high prediction accuracy. It also highlights the need for integrated decision support systems that provide prediction-based recommendations, enhancing the practical value of predictive models in supply chain management.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"11 ","pages":"Article 100130"},"PeriodicalIF":0.0,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144169020","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}

{"title":"An optimization framework for emergency supply chains prioritizing elderly populations during pandemics","authors":"Behzad Mosallanezhad ,&nbsp;Neale R. Smith ,&nbsp;Fatemeh Gholian-Jouybari ,&nbsp;Mostafa Hajiaghaei-Keshteli","doi":"10.1016/j.sca.2025.100131","DOIUrl":"10.1016/j.sca.2025.100131","url":null,"abstract":"<div><div>Pandemics have severely disrupted supply chains, making it challenging to meet the demands of the elderly and other vulnerable populations. This study addresses the importance of developing a sustainable emergency supply chain network that ensures timely and fair resource allocation for elderly communities. Therefore, an age-structured Susceptible-Infected-Recovered (SIR) system dynamics framework is utilized to simulate pandemic development and estimate age-specific demand for highly-demand items. Then, a multi-objective stochastic mathematical model is proposed to optimize cost, decrease unfulfilled demand, and reduce environmental effects. A numerical example inspired by the recent COVID-19 pandemic in Mexico is introduced, which focuses on the distribution of personal protective equipment (PPE), medical supplies, and test kits to hospitals, pharmacies, and other demand points. This approach couples the estimated demand from the system dynamics model and then optimizes the stochastic model. The results present optimal decisions for allocation, inventory, product flow, distribution, and waste management under different scenarios. A sensitivity analysis for the demand parameter is also performed, showing that total cost, unmet demand, and environmental effects increase as demand rises. The study demonstrates the model's capacity to enhance supply chain resilience and adaptability, providing valuable insights to improve emergency responses for at-risk populations.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"11 ","pages":"Article 100131"},"PeriodicalIF":0.0,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144125177","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}

{"title":"Optimization-based model of a circular supply chain for coffee waste","authors":"Hanieh Zohourfazeli ,&nbsp;Ali Sabaghpourfard ,&nbsp;Amin Chaabane ,&nbsp;Armin Jabbarzadeh","doi":"10.1016/j.sca.2025.100126","DOIUrl":"10.1016/j.sca.2025.100126","url":null,"abstract":"<div><div>Spent coffee grounds (SCG) waste poses significant environmental challenges, including greenhouse gas emissions and contamination risks. However, the existing reverse logistics (RL) systems remain inefficient, costly, and prone to contamination. Although previous studies have explored RL strategies, economically viable logistics models for small-scale SCG operations remain underdeveloped. However, the role of digitalization in optimizing SCG collection has not yet been explored. This study addresses these gaps by developing and evaluating sustainable business models that integrate circular economy principles with Industry 4.0. A mixed-integer linear programming (MILP) model was formulated to optimize the location, allocation, and routing decisions for “circular coffee shops, ” which serve as local collection and preprocessing nodes. Using real data from 1000 coffee shops in Montreal, three case scenarios were analyzed to assess the impact of pre-drying technologies and smart logistics on cost reduction and environmental performance. The results show that, while smart bins and real-time data analytics improve network efficiency and sustainability, the strategic placement of pre-drying technologies significantly reduces transportation and processing costs. By introducing a novel framework that integrates digitalization and collaborative waste management, this study advances SCG valorization and minimizes waste-related environmental impact. The findings offer actionable strategies for municipalities and food service stakeholders, providing a scalable, data-driven approach to promote the adoption of circular economy principles in urban organic waste management.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"10 ","pages":"Article 100126"},"PeriodicalIF":0.0,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143928288","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}

{"title":"A bibliometric analysis of industry 5.0 and healthcare supply chain research: Emerging opportunities and future challenges","authors":"Rajesh Matha ,&nbsp;Subhodeep Mukherjee ,&nbsp;Rashmi Ranjan Panigrahi ,&nbsp;Avinash K Shrivastava","doi":"10.1016/j.sca.2025.100125","DOIUrl":"10.1016/j.sca.2025.100125","url":null,"abstract":"<div><div>This paper explores the emerging field of Industry 5.0 in the context of healthcare supply chains (HSC). It aims to improve resilience, sustainability, and efficiency through human-centred techniques and cutting-edge technology. This study focuses on HSC management and emerging technologies such as artificial intelligence (AI), the Internet of Things (IoT), and robotics. Using a bibliometric analysis of 142 academic publications, this paper identifies key publication trends, significant research contributions, and thematic clusters. The results show a steady increase in research interest since 2018, with a growth rate of 15 % year-on-year in publications and contributions from 20 countries, led by the United States of America, China and the United Kingdom. These suggest implementing Industry 5.0 technology to optimize operational processes, improve demand forecasting, and advance sustainable practices. Identified topic clusters highlight key aspects such as decision support systems, sustainability, resilience, and technological integration, demonstrating the potential of Industry 5.0 to transform healthcare logistics. Integrating human expertise with intelligent systems, Industry 5.0 addresses healthcare delivery challenges while ensuring high-quality patient care. Future research can build on this study’s contributions to explore the intersection of HSC management and technological advancements.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"10 ","pages":"Article 100125"},"PeriodicalIF":0.0,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143907779","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}

{"title":"An analytics-driven economic order quantity model integrating fuzzy learning for deteriorating imperfect items in sustainable supply chains","authors":"M. Palanivel ,&nbsp;M. Venkadesh ,&nbsp;S. Vetriselvi ,&nbsp;M. Suganya","doi":"10.1016/j.sca.2025.100120","DOIUrl":"10.1016/j.sca.2025.100120","url":null,"abstract":"<div><div>This study presents an advanced Economic Order Quantity inventory model that integrates intuitionistic fuzzy sets and fuzzy learning to enhance decision-making under environmental uncertainty. The model systematically incorporates green technology adoption and accounts for the uncertain impact of emerging technologies on carbon emissions. The proposed framework embeds carbon reduction incentives and tax policies into the inventory decision-making process by leveraging real-time data from environmental regulations and technological advancements. Additionally, the study explores the role of fuzzy learning in optimizing supply chain networks, enabling improved environmental performance, and minimizing carbon emissions. Integrating intuitionistic fuzzy sets, fuzzy learning, green technology, and carbon emission reduction strategies provides a mathematically rigorous approach to developing adaptive inventory models that achieve economic efficiency and environmental sustainability. Numerical experiments are validated by MATLAB software. Based on the numerical experiments, sensitivity analyses are performed on key model parameters to validate the effectiveness of the proposed methodology. The findings are further reinforced by computational simulations and mathematical insights, demonstrating the practical applicability and robustness of the model.</div></div>","PeriodicalId":101186,"journal":{"name":"Supply Chain Analytics","volume":"10 ","pages":"Article 100120"},"PeriodicalIF":0.0,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143869763","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}