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.

All sectors have an increasing interest in smart phone applications based on their many advantages that support business, especially the medical sector, which is constantly competing to develop the medical services provided, and accordingly in this research study we industrialized a mobile medical supplies and equipment ordering application (mobile medical app) classic and make an effort to authenticate it factually. When clients (hospitals doctors) create consumptions on the application, three dimensions can be identified: platform emotion stage, fear effect, and familiarity with product. This research designed to reinforce and brighten the most important magnitudes that improve a physician’s judgment of mobile medical app and the purpose to usage. Furthermore, this study inspected the availability of the model between hospital physicians in UAE. The classic ideal was observed by means of a model of 340 UAE clinic physicians and their personal assistant who utilize mobiles facilities in overall. The review technique, a calculable method, was applied; the fractional smallest cubes organizational calculation exhibiting systems was owned to inspect the planned agenda. The platform emotion dimension, especially fear and resistance to change, and the familiarity with the products were evaluated, and it was discovered that these factors positively influenced the objective to use the application. And the other side, the first dimension of emotion, fear, manifested as “apparent threat”, had no outcome on the purpose to using. These discoveries recommended that scholars should emphasis more on the facilities, merchandises, and the key task of the mobile medical app to control their inspirations on clients’ ordering purpose. This will progress the purchasing ways associated to acquiring medicinal materials utilizing mobile medical app and/or on other operational stages in unambiguously in UAE and the Central East at great.

The study examined the mediating role of supply chain security performance on the relationship between supply chain security practices and supply chain disruptions occurrences in the manufacturing industry in Ghana. Drawing on a survey of 336 manufacturing firms, dynamic capability, and contingency theories were applied using structural equation modeling (SEM) to test the conceptual model. It was discovered that both direct and indirect hypotheses supported the findings of the study. The results indicate that Ghanaian manufacturing firms have made progress in implementing supply chain security measures. The findings revealed that the adoption of comprehensive supply chain security practices is positively associated with improved performance metrics, including reduced inventory losses and damages, faster order fulfillment and delivery times, lower costs related to security incidents, and enhanced brand reputation and customer trust. Policymakers can leverage these insights to develop support programs aimed at strengthening the security capabilities of manufacturing firms, ensuring they are equipped to compete effectively in both local and global markets, improving security performance, and reducing the likelihood and impact of supply chain disruptions. In the quest of bridging the gap between theory and practice, this research contributes valuable knowledge to the discourse on supply chain security in developing countries, offering a roadmap for enhancing resilience and performance in the manufacturing sector.

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 study explores improving opportunities of forecasting accuracy from the traditional method through advanced forecasting techniques. This enables companies to optimize inventory management, production planning, and reducing the travelling time thorough vehicle route optimization. The article introduced a holistic framework by deploying advanced demand forecasting techniques i.e., AutoRegressive Integrated Moving Average (ARIMA) and Recurrent Neural Network-Long Short-Term Memory (RNN-LSTM) models, and the Vehicle Routing Problem with Time Windows (VRPTW) approach. The actual milk demand data came from the company and two forecasting models, ARIMA and RNN-LSTM, have been deployed using Python Jupyter notebook and compared them in terms of various precision measures. VRPTW established not only the optimal routes for a fleet of six vehicles but also tactical scheduling which contributes to a streamlined and agile raw milk collection process, ensuring a harmonious and resource-efficient operation. The proposed approach succeeded on dropping about 16% of total travel time and capable of making predictions with approximately 2% increased accuracy than before.