Optimizing inventory management: a causal inference-driven Bayesian network with transfer learning adaptation

In the network era, the concept of supply chain management is a customer-centric. Through the analysis of the customer's actual needs and the prediction of the customers' future needs to pull the products and services. Based on such idea, many new modern supply chain management strategies constantly produced. Such as rapid response strategy, electronic ordering system and enterprise network-based supply chain system and so on. In the overall structure of the supply chain management, distribution, warehousing, transportation and other areas all have developed very well. But the supply chain management is still facing great difficulties. Although there are some difficulties in the technical and financial resources support the implementation of supply chain management. But the organization, trade partnerships, logistics costs and information-sharing and other issues will be the implementation of supply chain management. The demand has become increasingly evident in the optimization of the modern supply chain management for the virtual structure of the supply chain business contact. Through the cloud computing technology the efficiency of communications between supply chain enterprises can be maximized. The cloud computing can enhance the degree of information sharing in supply chain management.

The rising cost of quality healthcare is becoming an increasing concern. A significant part of healthcare cost is the pharmaceutical supply component. Improving healthcare supply chains is critical not only because of the financial magnitude but also because it impacts so many people. Efforts such as this project are essential in understanding the current operations of healthcare pharmacy systems and in offering decision support tools to managers struggling to make the best use of organizational resources. The purpose of this study is to address the objectives of a local hospital that exhibits typical problems in pharmacy supply chain management. We analyze the pharmacy supply network structure and the different, often conflicting goals in the decisions of the various stakeholders. We develop quantitative models useful in optimizing supply chain management and inventory management practices. We provide decision support tools that improve operational, tactical, and strategic decision making in the pharmacy supply chain and inventory management of pharmaceuticals. On one hand, advanced computerized technology that manages pharmaceutical dispensation and automates the ordering process offers considerable progress to support pharmacy product distribution. On the other hand, the available information is not utilized to help the managers in making the appropriate decisions and control the supply chain management. Quantitative methods are presented that provide simplified, practical solutions to pharmacy objectives and serve as decision support tools. For operational inventory decisions we provide the min and max par levels (reorder point and order up to level) that control the automated ordering system for pharmaceuticals. These parameters are based on two near-optimal allocation policies of cycle stock and safety stock under storage space constraint. For the tactical decision we demonstrate the influence of varying inventory holding cost rates on setting the optimal reorder point and order quantity for items. We present a strategic decision support tool to analyze the tradeoffs among the refill workload, the emergency workload, and the variety of drugs offered. We reveal the relationship of these tradeoffs to the three key performance indicators at a local care unit: the expected number of daily refills, the service level, and the storage space utilization.

In today’s dynamic business environment, the accurate prediction of sales orders plays a critical role in optimizing Supply Chain Management (SCM) and enhancing operational efficiency. In a rapidly changing, Fast-Moving Consumer Goods (FMCG) business, it is essential to analyze the sales of the products and accordingly plan the supply. Due to low data volume and complexity, traditional forecasting methods struggle to capture intricate patterns. Domain Adversarial Neural Networks (DANNs) offer a promising solution by integrating transfer learning techniques to improve prediction accuracy across diverse datasets. This study presents a new sales order prediction framework that combines DANN-based feature extraction and various machine learning models. The DANN method generalizes the data, maintaining the data behavior’s originality. The approach addresses challenges like limited data availability and high variability in sales behavior. Using the transfer learning approach, the DANN model is trained on the training data, and this pre-trained DANN model extracts relevant features from unknown products. In contrast, Machine Learning (ML) algorithms are used to build predictive models based on it. The hyperparameter tuning of ensemble models such as Decision Tree (DT) and Random Forest (RF) is also performed. Models like the DT and RF Regressor perform better than Linear Regression and Support Vector Regressor. Notably, even without hyperparameter tuning, the Extreme Gradient Boost (XGBoost) Regressor model outperforms all the other models. This comprehensive analysis highlights the comparative benefits of various models and establishes the superiority of XGBoost in predicting sales orders effectively.

Contributors

A bibliometric analysis of IoT applications in logistics and supply chain management

Amidst the swift expansion of the global trade economy, enterprises are confronted with escalating competition within their industries. Enhancing market competitiveness to boost economic efficiency emerges as a pivotal strategy for ensuring corporate viability. This study employs applied mathematics to refine the optimization of supply chain management, thereby offering a novel approach to augmenting management efficacy in enterprise supply chains. Initially, the research adopts mathematical models tuned to the traditional structure of enterprise supply chains, addressing prevalent profiling issues. Subsequently, it introduces a two-tier planning model to facilitate multi-objective decision-making in supply chain management. This model is rigorously applied to resolve various decision-making scenarios. An empirical analysis is conducted using Company M as a case study. Post-optimization, Company M's inventory exhibited only one instance of material shortfall, involving 132 items. The capital tied up in inventory was significantly reduced to 214,092 yuan—a decrease of 36,319 yuan compared to the capital occupied under traditional supply chain management methods. Furthermore, the optimized supply chain management system demonstrated a notable increase in the average inventory turnover rate to 12.3507%, marking an improvement of 3.6923% over the traditional model. The findings underscore the efficacy of the proposed optimization in enhancing the economic efficiency of enterprise supply chain management. This optimization not only streamlines operations but also provides robust support for the ongoing development of enterprise supply chains.

Production forecasting is vital in the oil and gas sector, empowering engineers with insights for effective reservoir management. This paper introduces the concept of Transfer Learning as a powerful tool in the domain of machine-learning-assisted production forecasting that accounts of 3D spatial distributions of three geological properties, namely porosity, permeability, and saturation, two completion parameters, namely hydraulic fracture height and length, and production constraint. Transfer learning efficiently leverages knowledge from one problem to improve generalization on another, especially when data is scarce and computational resources are limited. To demonstrate the utility of transfer learning, we evaluate two scenarios of transfer learning. The first transfer learning scenario demonstrates the generalization of the forecasting to cases with variable hydraulic fracture spacing using limited training data. The second transfer learning scenario demonstrates the generalization of the forecasting to cases with variable natural fracture spacing and natural fracture permeability using limited training data. Source dataset contained 2000 realizations, while the target dataset contained 20, 40, 60, 80, 100, 250, 500, or 1000 realizations to represent the scenarios of limited training-data availability. The study confirms the benefits of transfer learning when the training dataset size is small (generally less than 100 training realizations); however, under large training dataset size (around 500 or more training realizations), transfer learning is not needed. For the first scenario involving variable hydraulic fracture spacing, the use of transfer learning ensured that the source model can be trained on target dataset with 80 realizations for gas rate forecasting at an accuracy of 25% in terms of MAPE, and with 500 realizations for condensate rate forecasting at an accuracy of 12% in terms of MAPE. Similarly, for the second scenario involving variable natural fracture spacing and natural fracture permeability, the use of transfer learning ensured that the source model can be trained on target dataset with 250 realizations for gas rate forecasting at an accuracy of 24% in terms of MAPE, and with 500 realizations for condensate rate forecasting at an accuracy of 23% in terms of MAPE. This illustrates the potential of transfer learning in improving forecasting models with limited data using a well pre-trained model and enhanced hyperparameter tuning of the transfer learning model. For cases with 500 or more training realizations, transfer learning severely underperforms as compared to training a conventional machine-learning model from scratch. The paper explores two cases of transfer learning.

This abstract delves into the realm of manufacturing productivity enhancement through the review of AI-driven supply chain management (SCM) optimization and Enterprise Resource Planning (ERP) systems integration. As industries strive for operational excellence, the convergence of artificial intelligence (AI) and supply chain management emerges as a transformative force in driving efficiency, agility, and competitiveness. Through a comprehensive analysis, this abstract examines the synergistic relationship between AI-driven SCM optimization and the integration of ERP systems, elucidating their collective impact on manufacturing productivity. AI-driven SCM optimization encompasses a spectrum of technologies and methodologies, including predictive analytics, machine learning, and autonomous decision-making systems, aimed at optimizing various facets of the supply chain, from demand forecasting and inventory management to production planning and logistics optimization. By harnessing the power of AI, manufacturers can enhance forecasting accuracy, reduce lead times, optimize inventory levels, and mitigate supply chain disruptions, thereby improving overall productivity and customer satisfaction. Integration of ERP systems plays a complementary role in manufacturing productivity enhancement by providing a centralized platform for data management, process automation, and cross-functional collaboration. Through seamless integration with AI-driven SCM optimization tools, ERP systems enable real-time data exchange, actionable insights, and end-to-end visibility across the supply chain, facilitating informed decision-making and agile response to dynamic market conditions. Drawing insights from case studies and industry examples, this abstract highlights best practices, challenges, and emerging trends in AI-driven SCM optimization and ERP systems integration. Strategies for successful implementation, including organizational readiness assessment, change management, and stakeholder engagement, are discussed to guide manufacturers in unlocking the full potential of these transformative technologies. In conclusion, the convergence of AI-driven SCM optimization and ERP systems integration offers a compelling pathway for enhancing manufacturing productivity, driving operational excellence, and sustaining competitive advantage in the digital era.. Keywords: Artificial Intelligence, Supply Chain Management, Enterprise Resource Planning, Manufacturing Productivity, AI Integration, Predictive Analytics.

Transportation management is able to integrate various components that are highly needed in order to ensure the distribution of goods and services takes place effectively and efficiently. The effects of integrated transportation systems have major contribution to business processes and the sustainability of supply chain system in an area. This study measures role of transportation management, supply chain management, and business performance which carries out business in industrial estate. Survey was conducted on employees working in manufacturing industry in Bekasi region. Analysis technique in this study uses structural equation modeling (SEM). Conclusion obtained from results of analysis states that transportation management has significant influence on supply chain management, and has significant impact on business performance, especially for manufacturing industry. In order to grow and develop and even produce optimal business performance, transportation management support with good, integrated and supported management from various sectors is needed to create superior supply chain management so that transportation management support is needed with good governance, integrated, and supported from various sectors so as to create superior supply chain management so as to ensure the availability of industry needs. Suggestions are recommended in relation to planning of transportation management systems that support needs in industrial estate so as to understand strategies that must be carried out for success of business.

The aim of this paper is to present a novel idea to revolutionize hospital services by integrating healthcare supply chain management principles. By using a web application which enables hospitals to establish a real-time connection and streamline patient transfers. Many sectors focus on supply chain management optimization and qualifications to construct a better network of suppliers for their end consumers. Especially in healthcare sector, not only for pharmaceutical products but also for hospital materials, supply chain management gets importance for service quality and patient satisfaction. Thus, there are many studies about supply chain management in healthcare to emphasize its importance. In this study it is aim to put forward more review of existing solution on healthcare management system and patient transfer. Keywords- Supply Chain Management, Healthcare Service Delivery, MERN stack web application, Real-time data processing, Patient Transfers, Predictive Analytics, Patient-Centric Care, Efficiency, Seamless Coordination, Fast Connectivity

A typical issue with development of 3D image recognition models and systems is that 3D images often come with large volumes of data and require expensive computational cost for image reconstruction and model training. Transfer learning is a machine learning technique where a model trained on one task is reused on another related task. In this research, we propose a Transfer Learning method that allows training a 3D object recognition model with very limited training data, so requires much fewer reconstructed image slices, and help reduce the computational cost of both image reconstruction and training such models. To the best of our knowledge, this is the first report regarding Transfer Learning for 3D object recognition using integral imaging.

With the intensification of global economic competition, enterprises face the challenge of improving the supply chain management efficiency, and AI technology, as an emerging field in computer science, can provide effective solutions. As a leading e-commerce logistics service provider in China, JD Logistics has accumulated a wealth of logistics technology capabilities and digital transformation experience within and outside the JD Group. Using JD Logistics as a case study, this paper discusses the application of AI technology in supply chain management and its impact on enterprise responsiveness and operational efficiency. AI technology has significantly improved the supply chain operational efficiency and responsiveness of JD Logistics by applying intelligent supply chain planning, predictive analysis and intelligent decision-making. The study systematically summarizes the key role of AI technology in optimizing supply chain management through a literature review and specific case studies, providing an important reference and practical experience for enterprises to achieve digital transformation.

<p><strong>Abstract </strong></p>\n\n<p>The information system plays an important role in optimizing the supply chain management (planning and performance, platform and transport), in order to ensure good coordination between them, as well as allowing optimization of the supply chain (production, storage, and transport) (BOUROUBA 2013). This paper presents the role of information systems in optimization of the supply chain management and it application in CEVITAL Company.</p>\n\n<p><strong>Key word: </strong>Supply chain management , information system.</p>

In the era of globalization and digital transformation, Supply Chain Management (SCM) has become increasingly complex due to the exponential growth of data generated from various sources. Advanced data mining applications have emerged as pivotal tools for optimizing SCM by extracting actionable insights from vast datasets. This paper explores the integration of sophisticated data mining techniques into SCM processes to enhance decision-making, improve operational efficiency, and increase overall competitiveness. Through an extensive literature review and empirical analysis, the study highlights the significant benefits, challenges, and future directions of leveraging data mining in SCM. The findings indicate that data mining not only facilitates accurate demand forecasting and inventory optimization but also enhances supplier evaluation and logistics management, thereby contributing to a more resilient and agile supply chain.

We propose a technique for use in supply-chain management that assists the decision-making process for purchases of direct goods Based on projections for future prices and demand, requests-for-quotes are constructed and quotes are accepted that optimize the level of inventory each day, while minimizing total cost The problem is modeled as a Markov decision process (MDP), which allows for the computation of the utility of actions to be based on the utilities of consequential future states Dynamic programming is then used to determine the optimal quote requests and accepts at each state in the MDP The model is then used to formalize the subproblem of determining optimal request quantities, yielding a technique that is shown experimentally to outperform a standard technique from the literature The implementation of our entry in the Trading Agent Competition-Supply Chain Management game is also discussed.