Optimizing predictive analytics: a comparative study of deep learning approaches in big data mining for supply chain risk mitigation

PurposeThis study tries to examine how supply chain (SC) absorptive capacity (AC), SC ambidexterity, SC risk mitigation and supply chain agility (SCA) affect SC efficacy (SCE) in manufacturing firms (MFs) in the Middle East region.Design/methodology/approachUsing a quantitative approach through a survey-based study, 1,004 questionnaires were distributed to the MFs that are listed in the chambers of the industries of Jordan, Egypt, Saudi Arabia and Bahrain in the Middle East region, with 239 useable and valid responses retrieved for analysis, representing a 23.8% response rate. The main respondents were chief executive managers, operations managers, managers and logistics managers from both mid and top levels. The conceptual model was tested by using a hypothesis-testing deductive approach. The findings are based on covariance-based analysis and structural equation modeling (SEM) using partial least squares-SEM (PLS-SEM) software.FindingsThis study illustrates a significant relationship between SC AC, SC ambidexterity, SC risk mitigation and SCA on SCE. Further, the findings indicate that there is a significant effect of SC risk mitigation as a mediating factor in the relationship between SC AC, and SC ambidexterity on SCE directly and indirectly, as well through a moderating effect of SCA in these relations. Finally, there is a significant direct and indirect effect of SCA in the relationship between SC AC and SC ambidexterity on SCE as a moderating factor.Originality/valueThis study presents theoretical and empirical insights that both SC risk mitigation and SCA are proper logistics features for mediating and moderating extends the literature by adding a positive role of SC AC and SC ambidextrousness in mitigating SC risks. However, this study adds up the SC literature by evidencing moderating role of SCA between the absorptive capacities, ambidexterity on SCE. Such findings of this study can provide insightful implications for managers and practitioners at different levels in and efficacy among MFs (MFs, stakeholders and policymakers regarding the importance of using the three mentioned enablers on SCE) in MFs, particularly in the Middle Eastern firms and in developing countries in general East region.

Purpose– As global supply networks proliferate, the strategic significance of supply chain risk management (SCRM) – defined as the identification, evaluation, and management of supply chain-related risks to reduce overall supply chain vulnerability – also increases. Yet, despite consistent evidence that firm performance is enhanced by appropriate fit between strategy and context, extant SCRM research focusses more on identifying sources of supply chain risk, types of SCRM strategy, and performance implications associated with SCRM than on the relative efficacy of alternative primary supply chain risk mitigation strategies in different risk contexts. Drawing on contingency theory, a conceptual framework is proposed that aligns well-established aspects of SCRM to present a rubric for matching primary alternative supply chain risk mitigation strategies (redundancy and flexibility) with particular risk contexts (severity and probability of risk occurrence). The paper aims to discuss these issues.Design/methodology/approach– Conceptual paper.Findings– The proposed framework addresses supply chain managers’ need for a basic rubric to help them choose and implement risk mitigation approaches. The framework may also prove helpful for introducing business students to the fundamentals of SCRM.Originality/value– The framework and associated research propositions provide a theoretically grounded basis for managing the firm’s portfolio of potential supply chain risks by applying appropriate primary risk mitigation strategies based on the specific context of each risk rather than taking a “one size fits all” approach to risk mitigation. An agenda for progressing research on contingency-based approaches to SCRM is also presented.

Purpose: The purpose of this case study is to develop and framework supply chain characteristics and risk mitigation strategies in the context of biodiesel downstream supply chain.Design/methodology/approach: This study employs an expert interview-based approach as a qualitative approach with a multi-perspectives view.Findings: There are vary strategies among perspectives, such as perspectives of organization and business types, stakeholder types, times and methods. These also shows that business strategy of collaborative, coordinative, and cooperative arise as alternative strategies for each perspective and each level of stakeholder. Those business strategies may apply in a vary operation strategies which linking through an energy security framework element as company’s competitive priorities.Research limitations/implications: The research scope includes only a certain area of the country’s territory and the target company’s supply chain areas of activity. The research method includes only internal stakeholders and experts as respondents and data sources. The level of analysis was only at corporate level in the corporate case study context. The research also targets only a downstream activities of biodiesel supply chain context. The interview-based approach as a qualitative approach faces some subjectivity challenges among respondents.Practical implications: The research result provides some positive implications for business practice, includes how to minimize the impact of supply chain risk on company’s business activities and performance, how supply chain experts and practitioners used risk mitigation practices, how to formulate strategic plans to minimize the impact of supply chain risk and enhance the effectivity and sustainability of the supply chain activities.Social implications: The implication for business practice was that company’s leaders implemented supply chain risk mitigation strategies that provide positive impacts on the more valuable relationship among supply chain actors and stakeholders.Originality/value: The first, is an activities areas and operation schemes-based of biodiesel supply chain point of view. The second, is a multi-perspectives-based biodiesel supply chain characteristics framework. The third, is an energy security framework-based biodiesel risk mitigation strategies framework.

Uncertainty and supply chain risk: The moderating role of supply chain flexibility in risk mitigation

PT. VUB is engaged in construction manufacturing which is under the auspices of PT. Semen Indonesia Beton which will then be sent to retailers or distributors throughout Indonesia. The problem faced today is that companies often experience out of stock due to the fluctuating number of requests and inappropriate raw material planning that hampers the production process. This study aims to identify risky activity factors, plan appropriate strategies to minimize risk factors that occur in the company and provide solutions that can improve supply chain performance. The method used in supply chain risk mitigation at PT. VUB BM plant Pandaan is Fine-Kinney which aims to expose the value of risk factors based on the level of impact of the severity of the risk, and the solution uses the Anaytical Hierarchy Process (AHP) method as a determinant of the weight of risk mitigation strategies in the supply chain. From the results of risk identification at PT. VUB BM Pandaan was found that the highest risk occurred in the variable lack of K3 implementation in the production process with a risk rating value of 420 which has a very high risk factor because it can cause work accidents to employees. And the results of risk analysis with the criteria of raw material suppliers, production processes and distributors using the AHP method obtained 7 alternative supply chain risk mitigation strategies. With this research, it is hoped that it can help companies to reduce the risk of the company's supply chain.

PurposeIn India, artificial intelligence (AI) application in supply chain management (SCM) is still in a stage of infancy. Therefore, this article aims to study the factors affecting artificial intelligence adoption and validate AI’s influence on supply chain risk mitigation (SCRM).Design/methodology/approachThis study explores the effect of factors based on the technology, organization and environment (TOE) framework and three other factors, including supply chain integration (SCI), information sharing (IS) and process factors (PF) on AI adoption. Data for the survey were collected from 297 respondents from Indian agro-industries, and structural equation modeling (SEM) was used for testing the proposed hypotheses.FindingsThis study’s findings show that process factors, information sharing, and supply chain integration (SCI) play an essential role in influencing AI adoption, and AI positively influences SCRM. The technological, organizational and environmental factors have a nonsignificant negative relation with artificial intelligence.Originality/valueThis study provides an insight to researchers, academicians, policymakers, innovative project handlers, technology service providers, and managers to better understand the role of AI adoption and the importance of AI in mitigating supply chain risks caused by disruptions like the COVID-19 pandemic.

A structural equation modeling framework for exploring the industry 5.0 and sustainable supply chain determinants

The increasing complexity of healthcare supply chains characterized by fluctuating demand, stringent regulatory requirements, globalized procurement networks, and the critical need for real-time resource availability has accelerated the adoption of Artificial Intelligence (AI) as a transformative operational tool. This systematic review synthesizes emerging trends, empirical findings, and technological innovations in AI-enabled supply chain management within healthcare systems. Drawing on peer-reviewed literature from the past decade, the study examines how AI-driven techniques such as machine learning, predictive analytics, natural language processing, optimization algorithms, and intelligent automation enhance procurement forecasting, inventory management, logistics optimization, clinical resource allocation, and risk mitigation. The review highlights the growing integration of AI with enabling technologies such as digital twins, Internet of Medical Things (IoMT), blockchain, and cloud-based analytics to strengthen supply chain visibility, traceability, and resilience. Evidence shows that AI significantly reduces stock-outs, improves demand prediction accuracy, enhances cold-chain monitoring, and supports decision-making in critical service lines such as pharmaceuticals, surgical supplies, and emergency care. Despite these advancements, major challenges remain, including data fragmentation, interoperability limitations, model transparency concerns, workforce capacity gaps, and ethical issues relating to bias, privacy, and automation risks. The review concludes by outlining future research directions, emphasizing the need for explainable AI (XAI), scalable real-time analytics, integrated data governance frameworks, and hybrid human-AI decision architectures. This study provides a consolidated knowledge base for policymakers, healthcare administrators, and supply chain professionals seeking evidence-based pathways for AI adoption in healthcare operations.

This review proposes a comprehensive framework that integrates data fusion with Distributed Ledger Technologies (DLT) to enhance sustainability in supply chain management. In today’s global supply chains, ensuring transparency, efficiency, and environmental responsibility is critical, yet the lack of real-time visibility and data fragmentation presents significant challenges. The framework addresses these issues by merging data from multiple sources, including IoT devices, operational databases, and external environmental factors, using advanced data fusion algorithms. DLT, with its decentralized, immutable, and transparent nature, ensures the integrity and security of the data, allowing all stakeholders to access accurate and tamper-proof information. The fusion of data within a DLT infrastructure not only improves traceability and accountability but also enables the automation of sustainability checks via smart contracts. These contracts can trigger actions based on predefined sustainability metrics such as carbon emissions, energy consumption, and resource efficiency. Furthermore, predictive analytics and machine learning algorithms integrated into the system provide real-time monitoring and optimization of sustainability performance throughout the supply chain. The proposed review offers numerous benefits, including enhanced transparency, reduced operational costs, improved sustainability outcomes, and risk mitigation. It also addresses challenges such as scalability, data privacy, and regulatory compliance, offering solutions to overcome these hurdles. By exploring case studies of successful implementations, this review demonstrates the practical applications and future potential of combining DLT and data fusion for sustainable supply chain management, positioning it as a critical tool for organizations aiming to meet environmental and regulatory demands in an increasingly digital and eco-conscious world.

Purpose This study aims to investigate the two-way relationship between information and communication digital technologies (ICDT) and supply chain management (SCM). It addresses current gaps in understanding how digital technologies not only support but are also shaped by SCM practices. A conceptual framework [SCM information technology (SCMIT)] is introduced to align technological innovation with supply chain processes. Design/methodology/approach A systematic literature review of 705 peer-reviewed articles (1993–2024) was conducted using Scopus and PRISMA protocols. Bibliometric analysis and thematic clustering (via the Louvain algorithm) were used to identify key trends, technologies and research gaps in the field. Findings The study highlights the role of technologies such as blockchain, IoT and artificial intelligence (AI) in improving supply chain visibility, agility and resilience. However, it also identifies persistent barriers, including workforce skills, regulatory misalignment and limited integration of emerging tools. The SCMIT framework offers a structured view of how ICDT technologies can be integrated across supply chain layers to support strategic and operational goals. Research limitations/implications This review contributes a comprehensive framework (SCMIT) for analyzing the mutual relationship between ICDT and SCM. It draws attention to underexplored areas, such as human–AI collaboration and the need for empirical research linking technological adoption with supply chain performance in real-world settings. Practical implications The study recommends actionable strategies for practitioners, including prioritizing workforce development, investing in interoperable systems and aligning digital transformation efforts with sustainability objectives. SCMIT serves as a guide for organizations to improve decision-making and risk mitigation through targeted technology use. Originality/value To the best of the authors’ knowledge, this research provides one of the first structured efforts to model the dual influence of digital technologies and SCM practices. It supports both researchers and managers by offering insight into how emerging technologies can be strategically leveraged to improve supply chain performance and adaptability.

The paper presents possible solutions to small farmers in the agricultural sector in a small island setting grappling with challenges of enhancing their local industry and import substitution through a supply-demand chain framework. In 2005, Hawaiian farms produced approximately 363,200 kg of avocados. However, Hawaiian demand for these fruits required an additional 908,000 kg of avocados that were supplied through imports. At the same time, it is worth noting; almost 49% of locally produced avocados did not reach the market. These facts clearly suggest inefficiencies in the local avocado supply chain. Review of the literature on supply chain management suggests a sustainable avocado industry requires an integrated supply and demand chain management system. Hence, a modified conceptual model of supply-chain management called the Supply Demand Integrated Management (SDIM) model is proposed in this paper. Traditional supply chains contain three functional components: supply coordination, physical production and logistic management. In the new model, we propose adding R4D (Research for Development), a public good provided by the government to agricultural industries as an integral part of the supply-demand chain system. It articulates the significance of research and supply chain partnerships between small growers, industry groups, and public agencies. A well-integrated demand/supply chain in the avocado industry allows sharing of vital market information which can contribute to long-term strategic decisions that help local avocado growers increase their competitiveness against foreign imports. It also provides metrics in terms of consumer satisfaction, profitability, competitiveness, self-sufficiency, import substitution and sustainability. The SDIM model as applied to the avocado industry suggests two hypotheses relevant to the current situation. The hypotheses are: (1) There is a lack of coordination between what the farmers are growing and the chefs' (a high-end customer/buyer) preferences; (2) Forming an avocado farmer cooperative will enhance the profitability of local farmers. Survey data was collected from Hawaiian chefs and avocado farmers. Data was analysed using a Duncan multi-range test and a mathematical model, respectively, to test the hypotheses. The test revealed a lack of coordination between what the farmers are growing and buyer preferences. The results from the mathematical model suggested that formation of an avocado marketing cooperative would enhance the profitability of local farmers. Thus, the SDIM framework expands existing body of knowledge about supply chain management and provides useful information to local avocado growers that can help strengthen their supply and demand chain management.

In the context of the continuous development of the digital economy, studying the role of supply chain finance in mitigating supply chain risks and enhancing enterprise risk-bearing capacity is of great significance for promoting sustainable development. This study uses data from 2007 to 2019 as samples to empirically analyze the impact of supply chain finance on enterprise risk-bearing capacity. The research results show that supply chain finance plays a positive role in improving enterprise risk-bearing capacity. Mechanism tests reveal that supply chain finance functions through alleviating financing constraints and enhancing innovation capabilities in influencing enterprise risk-bearing. Further exploratory research finds that the influence of supply chain finance on enterprise risk-bearing is more pronounced in state-owned enterprises, while executive incentives do not show significant differences. These findings highlight the important role of supply chain finance in mitigating supply chain risks and enhancing enterprise risk-bearing capacity, providing valuable insights for sustainable development.

Contributors

Through an international business risk management lens, the widespread and catalytic implications of the 2020 COVID-19 pandemic on the supply chains (SCs) of fashion multinational corporations (MNC) are analyzed to contribute to existing research on supply chain management (SCM). While a movement towards agile, networked supply chain models had been in consideration for many firms prior to the outbreak, the pandemic highlights issues inherent in supply chains that employ concentrated production. We examined the current state of fashion supply chains, risks that have arisen historically and recently, and existing risk mitigation methods. We found that while lean supply chain management is primarily favored for its cost and waste reduction advantages, the structure is limited by the lack of supply chain transparency that results as well as the increasing demand volatility observed even before the COVID-19 outbreak. Although this problem might exist in the agile supply chain, agile supply chains combat this by focusing on enhancing communication and buyer-supplier relationships to improve information exchange. However, this structure also entails an associated increase in inventory and inventory costs. The COVID-19 pandemic has caused supply and demand disruptions which have resonating effects on supply chain activities and management, indicating a need to build flexibility to mitigate epidemic and demand risks. To address this, several strategies that firms can adopt to control for such risks are outlined and key areas for further research are identified which consider parties both upstream and downstream of the fashion supply chain.

The integration of machine learning (ML) in supply chain management (SCM) is revolutionizing the way financial transactions are processed, monitored, and optimized. Traditional financial transaction systems within supply chains often suffer from inefficiencies, latency, fraud vulnerabilities, and limited scalability. This paper explores various machine learning approaches that enhance financial transactions in SCM by improving accuracy, speed, security, and decision-making. Specifically, the study examines supervised learning techniques such as regression and classification for credit risk assessment and payment forecasting, as well as unsupervised learning for anomaly detection and fraud prevention in transactional data. Reinforcement learning is also discussed in the context of dynamic pricing, payment scheduling, and financial risk optimization across supplier networks. Deep learning models, particularly those using neural networks, are highlighted for their capabilities in real-time financial transaction processing and predictive analytics in complex, multi-tiered supply chains. Case studies from leading industries demonstrate the effectiveness of ML in enhancing transparency, reducing transaction costs, and increasing trust between supply chain partners. Furthermore, the paper addresses challenges such as data quality, interpretability of models, regulatory compliance, and the need for robust infrastructure to support ML implementation. The research also outlines best practices for integrating ML into existing financial systems and supply chain platforms, emphasizing the importance of cross-functional collaboration among IT, finance, and operations teams. The study concludes that the adoption of ML-driven solutions can significantly elevate the performance of financial transaction systems in SCM, resulting in improved cash flow management, better supplier relationships, and more resilient supply networks. These findings offer valuable insights for businesses seeking to leverage machine learning for strategic financial and supply chain innovation. Keywords: Machine Learning, Financial Transactions, Supply Chain Management, Predictive Analytics, Anomaly Detection, Reinforcement Learning, Credit Risk Assessment, Fraud Prevention, Dynamic Pricing, Transaction Optimization.