Supply Chain Analytics最新文献

Forecasting demand and determining safety stocks are key aspects of supply chain planning. Demand forecasting involves predicting future demand for a product or service using historical data and other external and internal drivers. Stockouts and excess production can be reduced by accurately forecasting demand. This allows companies to plan production, inventory, and logistics more effectively. Companies maintain safety stocks in their inventory to protect against unexpected changes in demand or supply. A company must find the appropriate safety stock level to meet customer demands while avoiding excess inventory and carrying costs. Forecasting demand and determining safety stocks work together to help companies reduce costs, improve customer service, and optimize inventory levels. Key Performance Indicators (KPIs) are commonly used to measure model performance. Classical forecasting models mostly concern themselves with minimizing forecast errors. However, the impact on inventory costs is not directly considered. In this paper, we introduce a Key Performance Indicator to be used in the demand forecasting process that produces more efficient results in terms of inventory costs. We also propose a novel approach to determining the best level for safety stock. This approach considers logistic network supply reliability and seasonality indices identified within historical demand patterns. We use real-life data and show that the proposed method can improve efficiency in forecasting and safety stock levels by reducing the risk of stockouts and excess inventory.

This study proposes a mathematical optimization model for a two-echelon location-routing problem in the last-mile delivery e-commerce environment. The e-commerce firm delivers each customer’s demand at home or through delivery points. Customers could be unavailable when the vehicle arrives at their homes. In this case, the vehicle must visit the allocated delivery points for the unavailable customer. There are several scenarios from all-present to all-absent customers. A mathematical model is proposed with six inequalities to reduce the model’s complexity. In addition, two scenario reduction methods are introduced to deal with the exponential growth of the number of scenarios. We generate twelve numerical instances to evaluate the performance of the model, the scenario reduction methods, and the proposed inequalities. The model produces valid solutions. Also, the scenario reduction methods are helpful for decision-makers in the e-commerce context by reducing the number of scenarios and decreasing the complexity of managing unavailable customer scenarios.

Green Supply Chain Management (GSCM) has emerged as a paramount issue in modern business organizations striving to become environmentally sustainable. Suppliers are pivotal in building a green supply chain. Green supplier selection (GSS) is a complex task involving several steps, from evaluation to final selection. This research aims to select spare parts suppliers of an automotive company based on their GSCM practices. Fourteen critical criteria are extracted from extant literature and refined through a Delphi study. The data was collected through interviews with industry experts using structured questionnaires. This study proposes integrated multi-criteria decision-making (MCDM) and multivariate analysis method with internal consistency checks. The Principal Component Analysis (PCA) is used to calculate criteria weights. A Simple Additive Weighting (SAW) method ranks the suppliers based on weighted criteria. The result shows that “collaboration with suppliers for green purchasing” is the most influential parameter for GSS. The outcome of this research may aid managers in selecting the most suitable green suppliers in the automotive industry by attaining sustainability. The proposed framework can be replicated to select suppliers in other industries.

Inventory control aims to meet customer demands at a given service level while minimizing cost. As a result of market volatility, customer demand is generally changing, and ignoring this uncertainty could lead to under or over-estimation of inventories resulting in shortages or inefficiencies. Inventory managers need batch ordering such that the ordered items arrive before the depletion of stocks due to the lead time between the ordering point and delivery. Therefore, to meet demand while optimizing the cost of the inventory system, firms must forecast future demands to address ordering uncertainties. Traditionally, it was challenging to predict such uncertainties with high accuracy. The availability of high volumes of historical data and big data analytics have made it easier to overcome such a challenge. This study aims to predict future demand in the case of an online retail industry using ensemble deep learning-based forecasting methods with a comparison of their performance. Compared to single-model learning, ensemble learning could improve the accuracy of predictions by combining the best performance of each model. Also, the advantages of deep learning and ensemble learning are combined in ensemble deep learning models, allowing the final model to be more generalizable. Finally, safety stocks are estimated using the forecasted demand distribution, optimizing the inventory system under a cycle service level objective.

This paper presents a systematic review of the literature on Supply Chain Risk (SCR) research, focusing on content-based analysis. The study comprehensively examines the general factors associated with key themes and trends in supply chain risk management, encompassing the identification and assessment of risks, risk mitigation strategies, and the influence of emerging technologies on Supply Chain Risk Management (SCRM). The review provides an overview of current and emerging topics in SCRM, while also introducing categorization frameworks to address research gaps and provide a roadmap for future studies, thereby generating valuable insights in this field. The review highlights the significance of effective SCRM in ensuring business continuity and resilience, emphasizing the need for organizations to adopt a proactive approach to risk management. The paper concludes by identifying areas for future research, including the development of novel risk management frameworks and the integration of emerging technologies into supply chain risk management practices. Additionally, a comprehensive evaluation of each classification is presented, highlighting overlooked aspects and unexplored domains, and offering recommendations for potential next steps in SCRM research.

The COVID-19 pandemic has had an immense economic, social, and environmental impact on Supply Chains (SCs) worldwide. Despite the importance of the impact of the pandemic on SCs, very little research has been conducted on a comprehensive systematic literature review on the COVID-19 pandemic and SCs. This study presents this comprehensive analysis and includes a summary and classification of 393 papers published between 2019 and 2022. We show four broad themes in the literature: (1) the impacts of the COVID-19 pandemic on SCs, (2) SC resilience strategies for managing impacts, (3) SC sustainability issues, and (4) SC disruptions and mitigation techniques. We analyzed each theme based on the research aim, findings, methodology, specific methods, context, and study scale. We also present the open research questions and suggestions for further investigation. These suggestions can provide extensive insights for scholars and practitioners in designing and conducting impactful and insightful research.

Suppliers often prefer to offer their retailers a delay period in payment to attract more sales and promote revenue in a supply chain. The retailers usually ask their customers to pay a portion of purchasing cost when receiving the product (i.e., a downstream partial trade credit) to reduce the default risk. On the other hand, the suppliers provide discounts for bulk purchases, and the retailer has enough capital to purchase more goods than can be stored in its warehouse. The retailer must store the excess quantities in a rented warehouse if the storage capacity is limited. A two-warehouse inventory system is needed to model this problem. In reality, the demand rate fluctuates with time, and the relevant cost is usually affected by the present value of time. This study focuses on the limited storage capacity inventory model for deteriorating items with fluctuating demand, downstream partial trade credit transactions, and discounted cash-flow considerations. The aim is to find the optimal replenishment cycle and order quantity and keep the present value of the total relevant cost per unit of time as low as possible. We further present numerical examples to demonstrate the applicability and develop managerial insights.

Fault detection and identification are critical for the accurate maintenance and management of industrial machinery. In this regard, data-driven condition monitoring models play an important role in machinery fault diagnosis and management. This study investigates the applicability of various statistical machine learning systems in modeling large data in the condition monitoring of electric drive trains in supply chains. Large data is used to train linear discriminant analysis, K-nearest neighbor algorithm, naïve Bayes, kernel naïve Bayes, decision trees, and support vector machine to distinguish between eleven fault states. The experimental results from the testing data set show that the decision trees achieved 93.8% accuracy, followed by kernel naïve Bayes (91.9%), radial basis function (Gaussian) support vector machine (89.3%), linear discriminant analysis (84.5%), k-NN algorithm (80.5%), and Gaussian naïve Bayes (71.3%). Accordingly, the choice of statistical machine learning algorithm influences classification accuracy related to electric drive fault diagnosis. In addition, decision trees take only few seconds to learn and classify new instances from big data. This makes the selection of decision trees trivial for condition monitoring and management of electric drive trains.

Robust and resilient agri-food supply chain management (AFSCM) is paramount to agribusinesses, given the many challenges and risks that this increased demand will bring in the coming decades. Interruptions caused by various risks to this crucial supply chain network, particularly in emerging economies, can put the lives of millions in danger, not to mention creating devastating impacts on the economy and the environment. Even so, there are only a limited number of quantitative risk management studies in the AFSCM literature. In this study, an integrated modified risk mitigation matrix (M-RMM) is developed to analyze the mitigation strategies for dealing with various risks in the context of the agri-food supply chain. The M-RMM is integrated with the grey multi-objective binary linear programming (GMOBLP) model to obtain the optimal risk mitigation strategies related to the three objective functions of risk, cost, and time minimization. The proposed model is a useful tool for formulating sustainable business policies and reducing food waste, and acquiring a context-specific (i.e., a developing economy), sector-specific (i.e., the agri-food processing sector), and multi-product (i.e., fresh and non-perishable) approach. The findings reveal that continuous training and development and vulnerability analysis of IT systems are the most effective risk mitigation strategies to lessen the impacts of lack of skilled personnel, sub-standard leadership, failure in IT systems, insufficient capacity to produce quality products, and poor customer relationships. The findings assist practitioners in managing risks in supply chains.

Managing information flow has always been a challenging and critical driver of performance increase in manufacturing companies. Each bit of information related to the manufacturing process has an information flow value that can impact the process. Recent studies have focused on the traditional classification algorithms methods to analyze the value of information flow. In this research paper, we use regression algorithms to develop an analytics model for the value of information flow in manufacturing shop floors of developing countries. The analysis shows that the Artificial Neural Network (ANN) has the best regression coefficient score of 0.775 with a prediction error of 0.0125. The lowest regression coefficient score of 0.323 was for the Multi-Linear Regression (MLR) with a prediction error of 0.0556. These results help companies use regression algorithms effectively to analyze the value of information flows on the manufacturing chains.