This study conducts a comparative analysis of various machine learning and deep learning models for predicting order quantities in supply chain tiers. The models employed include XGBoost, Random Forest, CNN-BiLSTM, Linear Regression, Support Vector Regression (SVR), K-Nearest Neighbors (KNN), Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), Bidirectional LSTM (BiLSTM), Bidirectional GRU (BiGRU), Conv1D-BiLSTM, Attention-LSTM, Transformer, and LSTM-CNN hybrid models. Experimental results show that the XGBoost, Random Forest, CNN-BiLSTM, and MLP models exhibit superior predictive performance. In particular, the XGBoost model demonstrates the best results across all performance metrics, attributed to its effective learning of complex data patterns and variable interactions. Although the KNN model also shows perfect predictions with zero error values, this indicates a need for further review of data processing procedures or model validation methods. Conversely, the BiLSTM, BiGRU, and Transformer models exhibit relatively lower performance. Models with moderate performance include Linear Regression, RNN, Conv1D-BiLSTM, Attention-LSTM, and the LSTM-CNN hybrid model, all displaying relatively higher errors and lower coefficients of determination (R²). As a result, tree-based models (XGBoost, Random Forest) and certain deep learning models like CNN-BiLSTM are found to be effective for predicting order quantities in supply chain tiers. In contrast, RNN-based models (BiLSTM, BiGRU) and the Transformer show relatively lower predictive power. Based on these results, we suggest that tree-based models and CNN-based deep learning models should be prioritized when selecting predictive models in practical applications.

The presence of a crisis has consistently been an inherent aspect of the Supply Chain, mostly as a result of the substantial number of stakeholders involved and the intricate dynamics of their relationships. The objective of this study is to assess the potential of Big Data as a tool for planning risk management in Supply Chain crises. Specifically, it focuses on using computational analysis and modeling to quantitatively analyze financial risks. The “Web of Science—Elsevier” database was employed to fulfill the aims of this work by identifying relevant papers for the investigation. The data were inputted into VOS viewer, a software application used to construct and visualize bibliometric networks for subsequent research. Data processing indicates a significant rise in the quantity of publications and citations related to the topic over the past five years. Moreover, the study encompasses a wide variety of crisis types, with the COVID-19 pandemic being the most significant. Nevertheless, the cooperation among institutions is evidently limited. This has limited the theoretical progress of the field and may have contributed to the ambiguity in understanding the research issue.

The cultivation of red chili in East Java, Indonesia, has significant economic and social impacts, necessitating proactive supply chain measures. This research aimed to identify priority risk agents, develop effective risk mitigation, and enhance supply chain resilience using the SCOR model, House of Risk, Interpretative Structural Modelling (ISM), and synthesis analysis. Examining 238 respondents—including farmers, collectors, wholesalers, retailers, home-agroindustries, and experts—the findings highlight farmers’ critical role in supply chain resilience despite risks from crop failures, weather fluctuations, and pest infestations. Simultaneous planting led to market oversupply and price drops, but accurate pricing information facilitated quick market adaptation. Wholesalers influenced pricing dynamics and income levels, impacting farmers directly. To improve resilience, three main strategies were developed through ten key elements: proactive strategies (real-time SCM tracking, Weather Early Warning Systems, risk management team formation, and training), resistance strategies (partnerships, chili stock reserves, storage and drying technologies, GAP implementation, post-harvest management, agricultural insurance, and Fair Profit Sharing Agreements), and recovery and growth strategies (flexible distribution channels and customizable distribution centers). Furthermore, the study delves into the mediating and moderating effects between variables within the model. This research not only addresses a knowledge gap but also provides stakeholders with evidence to consider new strategies to enhance red chili supply resilience.

With its inherent characteristics of decentralization, immutability, and transparency, blockchain technology presents a promising opportunity to revolutionize the South African food supply chains. Blockchain technology, with its decentralized, immutable, and secure nature, offers solutions to these challenges by improving traceability and accountability across the supply chain. This study investigates the role of blockchain technology in enhancing transparency in the food supply chain among small and medium enterprises in South Africa. SMEs form a critical part of the country's agri-food sector but face challenges such as food fraud, inefficient inventory management, and lack of transparency, which impact food safety and trust. The research adopts a mixed-method approach, utilizing the Technology-Organization-Environment framework and Institutional Theory to explain blockchain adoption among SMEs. The results demonstrate that blockchain-enabled practices, such as smart contracts, records traceability, production tracking, and distribution monitoring, significantly enhance supply chain transparency. The findings highlight blockchain's potential to increase operational efficiency, regulatory compliance, and stakeholder trust. This research provides valuable insights for policymakers and practitioners, emphasizing the need for regulatory support and strategic investment in blockchain solutions to promote sustainability and competitiveness in the agri-food sector.

Global trade is based on coordinated factors, that means labor and products are moved from their point of origin to the point of use. Strategies have a significant impact on global trade because they enable the effective development of goods across international borders. The decision making is an important task for the development of Logistics Supply Chain (LSC) infrastructure and process. Decisions on supplier selection, production schedule, transportation routes, inventory levels, pricing strategies, and other issues need to be made. These decisions may have a big influence on customer service, profitability, operational efficiency, and overall competitiveness. The Artificial Intelligence (AI) approach of Fuzzy Preference Ranking Organization Method for Enrichment Evaluation (Fuzzy-Promethee-2) is used to assess the priority selection of the factors associated with the LSC and evaluate the importance in global trade. The role of AI is very useful compare to statistical analysis in terms of decision making. The computational analysis placed promotion of exports as the most important priority out of five selected attributes in LSC, with infrastructure development. The result suggests that LSC depends heavily on export promotion as the most significant attribute. Infrastructural development also appeared another factor influencing LSC. The foreign investment was ranked the lowest. The evaluated results are useful for the policy makers, supply chain managers and the logistics professionals associated with the supply chain management.