Inventory Optimization Research Articles

The influence of supplier competency on business performance through supplier integration, vendor-managed inventory, and supply chain collaboration in Fuel Station: An evidence from Timor Leste

Fuel availability is essential in supporting the sustainable economic growth of a country. The manufacturing industry, transportation activities, and shipping products between regions are the primary sectors that require a sustainable fuel supply. The fuel station contributes to distributing and delivering fuel in serving the demand for the fuel. This study investigates supplier competency's role in supporting fuel station business performance through supplier integration, vendor-managed inventory, and supply chain collaboration. The research surveyed 71 fuel stations in Timor Leste using a questionnaire designed with a five-point Likert scale. The questionnaires are distributed to supervisors or higher positions at fuel stations by distributing questionnaires by direct delivery and also through Google Forms for areas far away in downtown Timor Leste. Data from respondents were analyzed using smartPLS software version 4.0. The results found that supplier competency positively impacts supplier integration, vendor-managed inventory, and supply chain collaboration. Moreover, supplier integration positively impacts vendor-managed inventory, supply chain collaboration, and business performance. Vendor-managed inventory fuel station sites can have an impact on improving supply chain collaboration and business performance. In addition, supply chain collaboration between vendors and fuel stations in Timor Leste enables continuous business performance improvement. This research paves the way for supervisors, managers, and fuel station top management to collaborate with suppliers in maintaining inventory levels and forecasting the supply and demand for fuel procurement requirements. Finally, this research contributes to the theory of inventory optimization and supply chain performance.

Sustainable Inventory Optimisation: Balancing Demand Dynamics with Eco-Friendly Packaging and Carbon Emission Constraints

Sustainable Inventory Optimisation: Balancing Demand Dynamics with Eco-Friendly Packaging and Carbon Emission Constraints

Optimal inventory economic order quantity model for inventory system with imperfect inspection processes

Optimal inventory economic order quantity model for inventory system with imperfect inspection processes

Research on E-Commerce Commodity Demand Forecasting and Inventory Optimization Based on Time Series Forecasting Model

In this study, 1996 sets of time series data are extracted from the three dimensions of merchant, warehouse and commodity, and the outliers are removed using the 3σ criterion. Through visual analysis, it was found that home improvement building materials and food and beverages were popular commodities. Then ARIMA and LSTM models were used to forecast the demand. Through 1-wmape index evaluation, LSTM model was found to perform better. Finally, the K-Means cluster analysis is carried out based on the categories of goods, merchants and warehouses, and the cluster number is selected as 70. The cosine similarity method is used to match the newly added dimensions to the category of the cluster in problem 1, and the ARIMA model is used for prediction. The results show that the cosine similarity method can accurately predict the commodity demand, the 1-wmape index is 0.801, and the residual plot presents randomness. The data of November 2022 is added to the original data, and the missing data is processed by linear interpolation. The LSTM model was used to forecast the increase of the total demand during Double 11. By setting a periodic time series with a step size of 30, the model achieves a good accuracy in predicting the demand in June, with a 1-wmape index of 0.829. To sum up, this study comprehensively considers three dimensions of merchants, warehouses and commodities, and uses different models to make accurate predictions. The ARIMA and LSTM models are adopted, while the promotion characteristics are considered and the appropriate LSTM parameters are selected. The research results provide practical forecasting tools and methods for supply chain management.

Inventory Control for Eyeglass Supply Using the P Model Based on Sales Products Sales Forecasting (Case Study: Merry Optic Bandung)

Inventory is a resource owned by the company to be used in the production process to meet consumer demand. Companies must be able to control inventory appropriately in order to avoid excess or shortage of inventory by using inventory control. Inventory control is a necessary part of a company that requires an appropriate inventory policy to meet uncertain needs. Based on this background, this study discusses the single item inventory model in the form of photochromic glasses at Merry Optik to find the optimal total inventory cost. In meeting the uncertain needs of the company, the Additive Decomposition forecasting method is used in order to find out the forecast sales data pattern in the future. Uncertain demand causes the inventory system to be probabilistic, so it is necessary to carry out probabilistic inventory control. The P model of the case of back orders was chosen because the range of ordering periods is fixed and the company can buy inventory when it runs out before the time the inventory order is made so that buyers can wait until the inventory arrives. By using Model P for the case of back orders, the company can obtain the period between orders, the total cost of inventory, and the optimal level of service. Based on the results of this study, a pattern of sales forecast data is obtained which repeats every 12 months. Companies must order glasses within a period of 32 days between orders so that it is optimal and able to provide a reduction in the total inventory cost of IDR 21,828,771 with a service level of 95%. Companies can save on inventory costs if they use shorter periods between orders. The total cost of inventory can be more optimal if the company reduces the cost of storing inventory in the warehouse.

Efficient computational strategies for a mathematical programming model for multi-echelon inventory optimization based on the guaranteed-service approach

This paper presents a Multi-Echelon Inventory Optimization (MEIO) framework, based on the Guaranteed-Service Model (GSM), to allocate safety stocks across a supply chain with several locations and products, minimizing costs while meeting service level objectives. Extending previous work by Achkar et al. (2023), this paper enhances the Mixed-Integer Quadratically Constrained Program (MIQCP) with a highly efficient solution approach. The model introduces a piecewise linear approximation, significantly improving computational efficiency and the accuracy of the approximation for the fill rate function. It also introduces a different and more efficient approach to account for stochastic lead times using a discrete function. Moreover, an extension of the approach to account for non-normally distributed demands is proposed. The model is applied to several instances of a real-world case study from a pharmaceutical company, with more than 7300 product-location combinations, showing that optimal solutions can be obtained within few seconds of computational time.

Optimizing the Hospital Blood Bank Stock in Korea: A Comparative Analysis of the Uniform 5-Day Stock Index and a Novel Blood Stock Index.

Maintaining optimal blood inventory levels in hospitals is important to prevent blood shortage and wastage. We aimed to provide an efficient blood inventory management strategy for hospital blood banks nation-wide by comparing the current use of 5-day issuable stock (IS) with Lim's IS as a novel target IS. The average and CV of daily usage (DU) were calculated from information entered into Korea's Blood Management System by 194 participating hospitals in 2019 and 2020. Using these data, Lim's IS was calculated by determining the simulated annual average blood shortage day nearest to 1 for each blood group in each hospital. The 5-day IS (5IS) was estimated by multiplying the average DU in 2018 by five to count the shortage days in 2019. The average DU (0.3-231.3 units) and corresponding CV (0.33-7.14) in the participating hospitals were inversely proportional (r=-0.699 to -0.695). The hypothetical averages of 5IS and Lim's IS were 27.0±41.2 and 24.7±20.8, respectively (P=0.006). The shortage days for 5IS and Lim's IS were 8.9±22.7 and 1.0±1.9, respectively (P<0.001). While 5IS was unacceptable for universal application, Lim's IS remained near one shortage day and is considered more efficient than 5IS. Hospitals should implement indicators that consider DU and its variations. This is the first study to introduce Lim's IS as an indicator of optimal blood inventory, and the data are expected to provide guidance for effective blood inventory management nationwide, particularly during blood shortages.

Towards inventory control excellence: An innovative approach based on a web-based platform.

Inventory management in educational institutions presents unique challenges due to the diverse sources of information and the need for improved team collaboration. This research aims to enhance inventory processes in educational institutions by leveraging information technology to optimize efficiency and ensure data integrity and reliability. The study employed a five-phase methodology to develop a web-based inventory optimization system. The initial phase involved a comprehensive analysis of inventory requirements, considering multiple data sources and team needs. Subsequently, in the planning phase, requirements were prioritized, and tasks with corresponding deadlines were established.The implementation phase adhered to the requirements outlined in the planning phase, utilizing appropriate information technologies to ensure efficient and reliable operation. A thorough system review was conducted to assess the achievement of each requirement's objectives, with necessary adjustments made as needed. Finally, following the completion of the previous phases, the developed software was deployed, and additional testing was conducted to ensure proper functionality. Following the implementation of the web-based system, significant improvements were observed: an 85.51% increase in efficiency for goods searches, streamlining the process and reducing location times; a 90.31% enhancement in goods registration, ensuring greater accuracy and data reliability; an 83.11% improvement in annual goods report generation, simplifying reporting and offering a clearer view of the inventory. Overall, the inventory process experienced an 86.31% improvement, leading to enhanced efficiency and collaboration among administrative and teaching staff. The utilization of information technology reduced inventory processing times and ensured the uniqueness and reliability of information. This research focuses specifically on optimizing inventory management in educational institutions through information technology. The study's uniqueness lies in its tailored web-based system designed to address the specific needs of educational institutions. The results demonstrate the effectiveness of this approach and its positive impact on inventory management.

Enhancing supply chain management in the physical internet: a hybrid SAGA approach

This paper introduces an advanced inventory replenishment optimization approach tailored for the Physical Internet (PI), addressing the dynamic and complex nature of this environment. We propose a hybrid Simulated Annealing–Genetic Algorithm (SA–GA), engineered to optimize the balance between exploration and exploitation, ensuring adaptability and efficiency in a variety of PI contexts. The study also presents an enriched mathematical model integrating dynamic demand, and multi-objective optimization. The SA–GA algorithm emerges as a novel contribution, characterized by its computational efficiency and adaptability, marking an advancement in PI inventory management. The incorporation of real-time data analytics in our dynamic inventory replenishment strategy enhances adaptability and responsiveness, while the robust mathematical model offers a versatile tool for both theoretical analysis and practical application. Collectively, these innovations help bridge existing gaps in PI inventory management and serve as a reference for other similar studies.

Fully dynamic reorder policies with deep reinforcement learning for multi-echelon inventory management

The operation of inventory systems plays an important role in the success of manufacturing companies, making it a highly relevant domain for optimization. In particular, the domain lends itself to being approached via Deep Reinforcement Learning (DRL) models due to it requiring sequential reorder decisions based on uncertainty to minimize cost. In this paper, we evaluate state-of-the-art optimization approaches to determine whether Deep Reinforcement Learning can be applied to the multi-echelon inventory optimization (MEIO) framework in a practically feasible manner to generate fully dynamic reorder policies. We investigate how it performs in comparison to an optimized static reorder policy, how robust it is when it comes to structural changes in the environment, and whether the use of DRL is safe in terms of risk in real-world applications. Our results show promising performance for DRL with potential for improvement in terms of minimizing risky behavior.

Advancements in AI-Enhanced Just-In-Time Inventory: Elevating Demand Forecasting Accuracy

The landscape of global supply chains is undergoing a transformation characterized by increasing complexity and the need for agile response to demand fluctuations. At the forefront of addressing these challenges is the strategic alignment of inventory levels with volatile demand, a task that has become more sophisticated within the Just-In-Time (JIT) inventory management paradigm. This paper explores the integration of Artificial Intelligence (AI) into JIT systems, with a focus on enhancing the accuracy of demand forecasting—a critical component for inventory optimization. We present a groundbreaking hybrid AI model that combines the forward-thinking capabilities of neural networks with the reliability of classical statistical forecasting methods. This innovative approach seeks to elevate forecasting reliability and reduce errors that lead to either inventory shortfalls or surpluses. Through a series of case studies spanning various industries, the versatility and effectiveness of the hybrid model are demonstrated, highlighting improvements in forecasting accuracy and the resulting operational benefits.

Inventory Control for Eyeglass Supply Using the P Model Based on Sales Products Sales Forecasting (Case Study: Merry Optic Bandung)

Inventory is a resource owned by the company to be used in the production process to meet consumer demand. Companies must be able to control inventory appropriately in order to avoid excess or shortage of inventory by using inventory control. Inventory control is a necessary part of a company that requires an appropriate inventory policy to meet uncertain needs. Based on this background, this study discusses the single item inventory model in the form of photochromic glasses at Merry Optik to find the optimal total inventory cost. In meeting the uncertain needs of the company, the Additive Decomposition forecasting method is used in order to find out the forecast sales data pattern in the future. Uncertain demand causes the inventory system to be probabilistic, so it is necessary to carry out probabilistic inventory control. The P model of the case of back orders was chosen because the range of ordering periods is fixed and the company can buy inventory when it runs out before the time the inventory order is made so that buyers can wait until the inventory arrives. By using Model P for the case of back orders, the company can obtain the period between orders, the total cost of inventory, and the optimal level of service. Based on the results of this study, a pattern of sales forecast data is obtained which repeats every 12 months. Companies must order glasses within a period of 32 days between orders so that it is optimal and able to provide a reduction in the total inventory cost of IDR 21,828,771 with a service level of 95%. Companies can save on inventory costs if they use shorter periods between orders. The total cost of inventory can be more optimal if the company reduces the cost of storing inventory in the warehouse.

Association Between Concerns About COVID-19 Infection and Blood Donation Intention: Cross-Sectional Survey Study Through a Mobile Communication Platform.

The ongoing COVID-19 pandemic has had an unprecedented impact on blood transfusion and collection. At the beginning of the pandemic, most blood transfusion services had a tough challenge in maintaining an optimal blood inventory. This study aims to understand the public's psychological cognition and intention toward blood donation as well as the factors influencing their worries. We aimed to find a solution for increasing blood donations and provide a scientific reference for policy formulation regarding blood donation during the COVID-19 pandemic and in the future. A random survey with a 14-item scale on worries related to blood donation was conducted from December 31, 2022, to January 3, 2023, among residents aged 18-60 years in Zhejiang province via SMS text messaging. The results of 8 worry items in this study were compared with the survey results of March 2022, during which COVID-19 was not considered as an epidemic in Zhejiang province. Chi-square test and logistic regression analysis were performed to analyze the factors affecting respondents' blood donation intention and concerns. The degree of worry about blood donation was assigned from 1 (completely disagree) to 5 (completely agree), and 2-sided t tests were performed to analyze the differences in blood donation intention and worries about blood donation. In total, 1254 valid questionnaire responses were obtained. Males accounted for 62.36% (782/1254) of the sample, 78.39% (983/1254) were 18-45 years old, 60.61% (760/1254) had a university education, and 69.06% (866/1254) had no previous blood donation experience. Approximately 36.52% (458/1254) of the public clearly expressed that they had blood donation worries regarding COVID-19. The main concerns of the respondents were temporary physical weakness caused by blood donation, their own physical conditions not meeting the requirements of blood donation, inconvenient location and working hours for blood donation, and family (or friends) worrying about blood donation. Compared with the results in 2022, the results in 2023 regarding the harmful effects of blood donation on health, temporary physical weakness, infection in donated blood, and family (friends) worrying increased significantly (P<.001). The factors influencing blood donation worries regarding COVID-19 were COVID-19 infection status, adverse reactions to the donated blood, family (or friends) worrying, and unsatisfactory blood donation experience. The factors influencing blood donation intention were gender, age, previous blood donation times, blood donation worries regarding COVID-19, harmful effects of blood donation on health, and blood donation anxiety. Blood transfusion services should make full use of the recovery phase of COVID-19 infection as an important time point, publicize the blood donation process and operation standardization, reduce the public's concerns about blood donation, correct negative evaluations, and increase perceived behavioral control and subjective norms.

Optimal control policies for dynamic inventory systems with service level dependent demand

Empirical studies have shown that stockouts may adversely affect future demand. However, much of the literature on inventory optimization has ignored this effect. In this paper, we investigate the effect of stockouts on a firm’s operational policy and total discounted profit. We show that compared with classic periodic review inventory models with no stockout effect, the optimal inventory control policies for inventory systems with stockout-dependent demand have different but interesting structures. Specifically, the optimal perceived stock-out service levels exhibit a mean-reverting pattern. These results shed lights on operational decisions and customer services to effectively manage inventory systems. Numerical studies show that neglecting stockout-dependent demand can lead to significant drop in the firm’s performance when compared with the optimum. This paper deepens our understanding on inventory systems when customer demand is discouraged by stockouts, and it helps inventory managers develop effective inventory control mechanisms that incorporate stockout effect.

ANALYSIS OF RICE INVENTORY CONTROL AT PT. DAYA TANI SEMBADA NGAWI DISTRICT

The demand for rice fluctuates significantly along with the increase in population every year, making PT. Daya Tani Sembada, as a premium rice-producing company, must do planning to deal with changes in demand that will occur. This research aims to analyze rice demand forecasting and the optimal rice inventory. The method of determining the sample is purposive sampling, where the Director and Administrative Staff are vital informants. Demand forecasting was analyzed using the Double Exponential Smoothing (Holts) method and inventory control using Economic Order Quantity. The results showed that: 1) forecasting calculations show that the demand for rice in the next period is 33,367.38 tons; 2) inventory control calculations show that the company can prepare premium rice inventory of 29.89 tons, safety stock of 336.03 tons, ROP when rice inventory is at 779.47 tons, and TIC that must prepare amounting to IDR. 5,357,082,020, -, overall, demand for rice has increased by 8,662.58 tons from the previous period so that the company can increase production for the next period by the draft inventory control calculation

Generative AI in Supply Chain Management

A new age of creativity and efficiency is ushered in by the integration of Generative Artificial Intelligence (AI) into supply chain management. This in-depth study examines the diverse effects of generative artificial intelligence on supply chain operations, including risk management, inventory optimization, procurement, logistics, and more. Given the predictive capacity of generative AI, traditional methods have been completely modified, enabling companies to anticipate demand, maximize inventory, and expedite procurement procedures with previously unheard-of accuracy. Real-time adaptation is made possible by its dynamic decision-making skills, which also help to promote resilience against interruptions and enable proactive reactions to changing market conditions. However, there are some challenges in implementing generative AI in supply chains. Obstacles requiring strategic navigation and organizational preparedness include skill gaps, ethical considerations, scalability issues, and data integration complexity. Future directions for generative artificial intelligence in supply networks are extremely promising. Substantial improvements are expected to be driven by advances in explainable AI, predictive analytics, seamless integration, and ethical frameworks. Redefining supply chain models could be facilitated by autonomous supply chains, adaptive resilience to disturbances, and increased transparency in decision-making.

WAYS OF INCREASING THE COMPETITIVENESS OF FOOD INDUSTRY ENTERPRISES

&#x0D; &#x0D; &#x0D; &#x0D; Purpose. The purpose of this study is to provide food industry professionals, entrepreneurs, and stakeholders with valuable insights and actionable strategies to enhance the competitiveness of their enterprises. By exploring various approaches and methods, we aim to empower individuals and organizations within the food industry to thrive in a highly dynamic and competitive environment. Through this study, readers will gain a deeper understanding of the critical factors influencing competitiveness and learn practical ways to stay ahead, adapt to consumer trends, optimize operations, and foster innovation within their food businesses. Ultimately, our goal is to facilitate the growth and sustainability of food industry enterprises in an ever-evolving market landscape.&#x0D; Results. In the dynamic food industry, competitiveness is pivotal for survival and success. It goes beyond mere participation; it's about thriving amidst intense competition, meeting consumer expectations, and outperforming rivals. Competitiveness is defined as a food enterprise's ability to strategically position itself, surpass competitors, and consistently exceed consumer expectations. Key factors in competitiveness include maintaining stringent quality and safety standards, ensuring operational efficiency and cost management throughout the supply chain, continuous innovation and product development, understanding evolving consumer preferences through market research, and fostering efficient supply chain management through strong supplier relationships, inventory optimization, and logistics. To bolster competitiveness, companies invest in improving product quality and safety through Quality Assurance programs and adherence to regulatory requirements. They also prioritize cost efficiency strategies such as lean manufacturing, supply chain optimization, and sustainability initiatives. Additionally, innovation and product development efforts focus on consumer-centric design, R&amp;D investments, and strategic new product launches.&#x0D; Scientific novelty. The scientific novelty of this study lies in the comprehensive synthesis and application of multidisciplinary strategies for increasing the competitiveness of food industry enterprises. While previous research has explored individual aspects of competitiveness, such as quality control, cost efficiency, or market analysis, this article uniquely integrates these facets into a holistic framework. By doing so, it offers a novel perspective on how food businesses can thrive in a complex and ever-changing environment.&#x0D; Practical value. The practical value of this study is twofold: it empowers food industry professionals with actionable strategies to enhance competitiveness, helping them stay ahead in a rapidly changing market. Additionally, it provides insights into risk mitigation and resource optimization, enabling businesses to navigate challenges effectively and maximize profitability.&#x0D; &#x0D; &#x0D; &#x0D;

Deep learning based emulator for simulating CMAQ surface NO2 levels over the CONUS

This study details the development and evaluation of an emulator model of the Community Multiscale Air Quality (CMAQ) model, utilizing a U-Net deep learning architecture to accelerate the simulation of surface NO2 concentrations across the Contiguous United States (CONUS). The emulator employs a subset of meteorological, land cover, and emission input variables identical to those in CMAQ. An initial assessment of the model based on 3-fold monthly cross-validation during the summer (JJA) demonstrates excellent accuracy for 1-h NO2 concentration, with a correlation coefficient (R) of 0.979 and an Index of Agreement (IOA) of 0.989. Subsequently, the model's robustness is examined by training it with NEI 2011 and 2014 data and then evaluating it using NEI 2017 data. This yields an R of 0.949 and an IOA of 0.974. We utilize the emulator to investigate the semi-normalized sensitivity of NO2 concentrations to NOx emissions, which exhibits a satisfactory alignment with CMAQ Decoupled Direct Method (DDM) sensitivities, with an MAE of 0.271 ppb for 1-h sensitivity coefficients. Diurnal cycle analysis of NOx sensitivity coefficients spatially averaged in 15 major urban environments indicates slight over- and underestimations of the morning and evening peaks, respectively, with the MAE varying from 0.27 (Dallas) to 0.92 ppb (Los Angeles). Remarkably, the emulator's computational efficiency significantly surpasses CMAQ's, providing more than 400 times the simulation speed on a single CPU and over 600 times when utilizing both CPU and GPU. As such, the emulator represents a promising tool for efficient CMAQ modeling, with potential applications in health impact assessments, emission reduction strategies, and emission inventory optimization.

Machine Learning-Based Sales Prediction and Inventory Management for Grocery Stores

In today's competitive grocery retail environment, effective inventory management coupled with precise sales prediction is pivotal for success. This research undertakes an in-depth exploration into a machine learning framework tailored for "Sales Forecasting and Inventory Optimization in Grocery Retail." Utilizing historical sales records, meteorological data, and consumer behavior metrics, the proposed model endeavors to predict nuanced seasonal demand fluctuations. The primary value proposition of this approach lies in its capacity to curtail wastage, ensuring the balance between overstocking and inventory stockouts. By recognizing and adjusting for seasonal dynamics, the system offers enhanced demand fulfillment during high-demand periods. The subsequent refinement of the replenishment cycle fosters superior operational efficacy. As an outcome, businesses witness cost reductions, augmented profit margins, and elevated consumer contentment due to consistent product availability. As the broader grocery sector undergoes transformation, embedding sophisticated machine learning strategies can be a linchpin for sustained adaptability and competitiveness. This research further underscores the role of emergent technologies, such as machine learning within the IoT spectrum, in reshaping supply chain and communication paradigms. The endeavor here is to curtail lifecycle expenses in the supply chain by refining inventory practices. The research introduces a Deep Inventory Management (DIM) technique, employing the GradientBoostingRegressor paradigm of machine learning. Through DIM's innovative approach, time-series challenges are reimagined as supervised learning tasks, enabling efficient model training. Preliminary tests indicate DIM's prediction accuracy hovers around 85%, translating to an impressive 15% reduction in inventory expenses when juxtaposed with prevailing methods, alongside rapid anomaly detection in inventory activities

Optimization of multi-echelon spare parts inventory systems using multi-agent deep reinforcement learning

Multi-echelon inventory systems are commonly used in practice to satisfy widely distributed random demands of spare parts in an efficient and cost-effective manner. Optimization of a multi-echelon inventory system is a decision-making problem under uncertainties. Classic inventory policies (e.g. (s, S) and (R, Q)) that do not consider the inventory positions of other warehouses become suboptimal due to interrelationships among different warehouses caused by transshipment. The Markov decision process (MDP) is an effective tool for inventory optimization, which does not require a predetermined parameterized policy structure. Unfortunately, both the state and action spaces of MDP suffer from the curse of dimensionality when the number of warehouses increases. This paper optimizes the inventory of a large-scale multi-echelon inventory system using a new multi-agent deep reinforcement learning (MADRL) algorithm named EM-VDTD3 that is developed by introducing value decomposition and experience buffer modification into the twin delayed deep deterministic policy gradient (TD3) algorithm. Each agent in EM-VDTD3 manages a subsystem in the multi-echelon inventory system. Because different agents share the same network parameters, networks are customized to process subsystems with different parameters. Domain knowledge of inventory control is embedded in the learning process of EM-VDTD3 by adding expert experiences to the experience buffer. An efficient approximate method is developed to identify a teacher policy that generates expert experiences. Numerical studies about a spare part inventory system in the wind energy industry show that the proposed EM-VDTD3 outperforms benchmark methods.