Inventory Optimization Research Articles

Sustainable Production-Inventory Model with Multi-Material, Quality Degradation, and Probabilistic Demand: From Bibliometric Analysis to A Robust Model

An adequate sustainable production inventory model is expected to represent complex real-life cases involving fuel, emissions, and electricity costs as well as multi-materials, quality degradation, and probabilistic demand. Therefore, this study was conducted to develop this kind of model to determine the number of raw material shipments (), production cycle time (), and the number of finished goods delivered (n) to maximize the Expected Total Profit (ETP). The proposed model is based on a bibliometric literature analysis of the sustainable production-inventory problem which is visualized using the VOSviewer. Moreover, a sophisticated Harris-Hawks Optimization (HHO) algorithm was proposed to solve the problems identified in the sustainable production inventory model optimization. It is also important to note that three numerical cases were provided to evaluate the performance of the algorithm. The findings showed that the suggested HHO method outperforms the Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) in maximizing ETP and this means it is better for ETP optimization. It was also discovered from the sensitivity analysis that an increase in the rate of quality degradation (k) led to a reduction in both the ETP and T.

Optimizing inventory control through a data-driven and model-independent framework

Machine learning has shown great potential in various domains, but its appearance in inventory control optimization settings remains rather limited. We propose a novel inventory cost minimization framework that exploits advanced decision-tree based models to approximate inventory performance at an item level, considering demand patterns and key replenishment policy parameters as input. The suggested approach enables data-driven approximations that are faster to perform compared to standard inventory simulations, while being flexible in terms of the methods used for forecasting demand or estimating inventory level, lost sales, and number of orders, among others. Moreover, such approximations can be based on knowledge extracted from different sets of items than the ones being optimized, thus providing more accurate proposals in cases where historical data are scarce or highly affected by stock-outs. The framework was evaluated using part of the M5 competition’s data. Our results suggest that the proposed framework, and especially its transfer learning variant, can result in significant improvements, both in terms of total inventory cost and realized service level.

Joint Optimization of Maintenance and Spare Parts Inventory for Multi-Unit Systems With a Generalized Structure

Abstract Joint optimization of maintenance operations and spare parts inventory is promising for ensuring the reliable and efficient operation of industrial systems. Extensive studies have been conducted on joint optimization emphasizing various aspects. However, those studies still suffer two limitations. (1) The considered system structures are restricted to particular cases, and thus are unable to fully address the joint optimization needs of actual industrial systems possessing various structures, and (2) imperfect maintenance, as has been commonly adopted in industries, is not addressed in existing works, which compromises the economic efficiency of the joint policy. Targeted at these limitations, this paper investigates the joint optimization for multi-unit systems with a generalized structure, i.e., the systems consist of multiple identical units, and each unit possesses a complex subsystem structure. First, a total cost rate model is formulated, in which maintenance actions include both perfect replacement and imperfect maintenance, and the spare parts inventory policy consists of an (s, S) policy and the option to place emergency orders. Based on the formulated model, a simulation optimization method is proposed. The simulation module evaluates the total cost rate iteratively, and the optimization module utilizes a variable neighborhood search-based algorithm to obtain a high-quality joint policy with tractable computation times. Two numerical examples are provided for demonstration, and sensitivity analyses are conducted to study the effects of parameters.

Backorder Prediction in Inventory Management: Classification Techniques and Cost Considerations

This article introduces an advanced analytical approach for predicting backorders in inventory management. Backorder refers to an order that cannot fulfilled immediately due to stock depletion. Multiple classification techniques, including Balanced Bagging classifiers, Fuzzy Logic, Variational Autoencoder (VAE) - Generative Adversarial Networks, and Multilayer Perceptron classifiers, are assessed in this work using performance evaluation metrics such as ROC-AUC and PR-AUC. Moreover, this work incorporates a profit function and misclassification costs, considering the financial implications and costs associated with inventory management and backorder handling. The study suggests a hybrid modelling approach, which includes ensemble techniques and VAE, which effectively addresses imbalanced datasets in inventory management. This approach emphasizes interpretability and reduces false positives and false negatives. This research contributes to the advancement of predictive analytics and offers valuable insights for future investigations in backorder forecasting and inventory control optimization for decision-making.

ANALISIS PENGENDALIAN BAHAN BAKU TEPUNG TAPIOKA MENGGUNAKAN METODE ECONOMIC ORDER QUANTITY (EOQ) PADA PT. BUDI STARCH & SWEETENER, TBK

The purpose of this study is to find the optimal raw material inventory of a company if it is calculated using the EOQ method. (case study at Pt. Budi Strach & Sweetener, Tbk). The data used in this study were taken from the company's books and from interviews with the HRD personnel of Pt. Budi Strach & Sweetener, Tbk in 2021. The data used in this study are: purchase data, usage data, purchase frequency, raw material inventory data, cassava raw material ordering data, raw material storage cost data. The analysis was carried out using the EOQ formula, safety stock, reorder point, total cost, purchase frequency. The problem in this research is Pt. Budi Strach & Sweetener, Tbk in its production experience a shortage of raw materials every year because the supply of raw materials in the field is uncertain, so here the author tries to apply the Economic Order Quantity (EOQ) method to minimize various aspects in the procurement of raw material supplies. The results of this study indicate that: Control of raw materials Economic Order Quantity (EOQ) method is considered more efficient and optimal, it is proven that there is a decrease in inventory costs of Rp. 3,219,502. Judging from the company's policy, the optimal purchase of raw materials according to company policy is 1,353,378 Kg with a purchase frequency of 24 times, while according to the policy of the EOQ Method, the purchase of raw materials is 1,813,140 Kg with a purchase frequency of 18 times a year. Total Safety Stock according to EOQ policy is 15,954 Kg. Re-Order Point (Re-Order Point) according to the policy of the EOQ Method is 376,854,444 Kg. The analysis shows that the use of the EOQ method in controlling cassava raw materials at Pt. Budi Strach & Sweetener, Tbk is considered effective and efficient

Large-Scale Inventory Optimization: A Recurrent Neural Networks–Inspired Simulation Approach

Many large-scale production networks include thousands of types of final products and tens to hundreds of thousands of types of raw materials and intermediate products. These networks face complicated inventory management decisions, which are often too complicated for inventory models and too large for simulation models. In this paper, by combining efficient computational tools of recurrent neural networks (RNNs) and the structural information of production networks, we propose an RNN-inspired simulation approach that may be thousands of times faster than the existing simulation approach and is capable of solving large-scale inventory optimization problems in a reasonable amount of time. History: Accepted by Bruno Tuffin, Area Editor for Simulation. Funding: This work was supported by the National Natural Science Foundation of China [Grant 72091211].

Trading safety stock for service response time in inventory positioning

We study an inventory placement optimization problem where demand is sensitive to service response time, under the online retailing setting. The main challenge is to achieve the optimal trade‐off between revenue benefits from shorter delivery time and the increase in inventory cost associated with placing inventory closer to market demand. To predict the effects of modified demand under service response time variations, we introduce a demand prediction and elasticity model to quantify the sensitivity in demand for particular product categories. Of course, shortening response time by positioning products close to market demand may increase inventory costs. Hence, the team developed a novel data‐driven two‐stage stochastic programming approach complementing the demand prediction and elasticity model, which optimally trades safety stock with service response time and hence revenue increase. We then illustrate the impact of our approach through data provided by an e‐commerce retailer in North America. Our approach offers supply chain managers a general‐purpose decision support tool that optimizes the inventory network to generate recommended stocking levels for stores, distribution centers, and warehouses on a daily basis.

Simultaneous optimization of inventory, maintenance, and quality for production systems subject to multiple mean and variance shifts

This article presents a general, integrated production, quality, and condition-based maintenance model for imperfect processes with multiple out-of-control operating states. The production system is subject to multiple quality disruptions, which affect both the process mean and variance, and failures. The quality of the production process output is monitored by a fully adaptive control scheme, and the state of deterioration is estimated through periodic sampling inspection. The proposed control scheme’s operation is modeled through a Markov chain, and the optimal quality control, maintenance, and inventory policy are defined based on an expected total cost minimization criterion. Finally, an illustrative example is employed to demonstrate the operation of the proposed model, sensitivity analysis is conducted to generate insights into how the process parameters misspecification affects the economic performance, and a comparative study is performed to evaluate the model’s superiority against the respective single quality shift model.

A data‐driven optimization approach to plan smart waste collection operations

AbstractWaste collection is an important logistic operation that is often inefficient due to the high uncertainty associated with bin fill levels, resulting either in routes that visit empty bins or in bins overflowing due to lack of routes. To reduce such uncertainty, sensors installed in the bins can provide real‐time information on waste levels. However, this is not enough, and the management of this information needs to be combined with dynamic optimization approaches to effectively design smart collection routes. This paper investigates this challenge and uses real‐time information on waste levels, treated through machine learning techniques, to feed a dynamic reverse inventory routing optimization model. The resulting data‐driven optimization approach allows the definition of a medium‐term collection route plan that can be updated daily as new information becomes available. To demonstrate the applicability of such an approach, a real‐world case is solved, and the results show significant improvements in operational efficiency and service levels.

A Study on Optimal Location Selection and Semi-Finished Product Inventory Allocation in the Steel Industry

With the development of industrial production technologies and market economy, Postponement is increasingly being adopted by continuous production enterprise as a method that enables multi-product, mass customization production. In order to make use of the Postponement in manufacturing production enterprises need to achieve customized production and reduce enterprise costs. A modeling is conducted in the production process of Postponement in iron and steel enterprises in this paper. With the goal of minimizing total costs on a specific customer service level, mixed integer nonlinear programming and particle swarm algorithms are adopted for modeling and solving, to determine the optimal location and optimal semi-finished product inventory of PDP and CODP. Finally, taking an iron and steel enterprise as an example, the feasibility and effectiveness of the model and algorithm are verified. The study shows that the change of the optimal locations of PDP and CODP is affected by the change of customer service level and delay penalty coefficient, but the speed of change of the optimal location of PDP shows longer delays. In addition, the size of the capacity of semi-finished product inventory corresponding to CODP has a direct influence on whether the semi-finished product inventory corresponding to PDP participates in production, which in turn affects the optimal semi-finished product inventory on all levels. Through the analysis, it is found that the model constructed in this paper can better describe the overall situation and the influence relationship of the Postponement, and the study supplements the deficiency of the research on Postponement in the continuous manufacturing enterprises and enriches the content of the quantitative research on the Postponement.

RETRACTED: Application of blockchain technology based on big data analysis in sustainable agriculture

AbstractTo improve the effect of sustainable agricultural development, this paper reports on sustainable agricultural development with the support of big data technology, combines the Internet of Things technology to apply blockchain in sustainable agricultural development, and analyzes the economic effect model. Moreover, this paper proves that the introduction of third‐party logistics in the vendor‐managed inventory strategy can effectively reduce the total cost of the supply chain. Through model analysis and model transformation, the inventory transportation integration optimization problem model is decomposed into two sub‐models: the transportation scheduling model and the replenishment delivery model. In addition, this paper designs a new solution algorithm based on the genetic algorithm and builds an intelligent blockchain model. The experimental research shows that the blockchain technology based on big data analysis proposed in this paper has certain effects.

Inventory pooling and pricing decisions in multiple markets with strategic customers

This study considers the pricing and inventory decisions for the retailer selling in multiple markets with strategic customers. The impact of strategic customer behavior on inventory pooling is examined. The equilibrium decisions, in which strategic customers tend to purchase early, are subsequently characterized in the pooled/non-pooled systems. Our results highlight the role of the strategic customer in each market. Compared with myopic customers, the retailer is prone to reduce its inventory for strategic customers. The retailer’s optimal inventory for high-profit products is lower in the pooled system than in the non-pooled system. However, the result is reversed for low-profit products. The analytical and numerical results simultaneously demonstrate that, in the high-profit condition, the retailers’ inventory in the pooled system increases with the correlation coefficient of different markets, while the retailers’ profit decreases with the correlation coefficient. There is an opposite relationship in the low-profit condition. When the markets are less correlated, the retailer owns low inventory but high profit. Moreover, the retailers’ profit is always higher in the pooled system than in the non-pooled system.

Optimization of Lateral Transfer Inventory of Auto Spare Parts Based on Neural Network Forecasting

Creating a fair replenishment strategy is one of the most significant instruments in the inventory management for automotive spare parts. It is also crucial to controlling the enterprise's inventory level. This study considers the significance of retailers' demand forecasting at the conclusion of the sales period to build a lateral transfer inventory optimization scheme with high scientific rigor, aiming to ensure the correctness and logic of the replenishment strategy. To provide a more scientific direction for the inventory management of an automotive spare parts company, this research constructs an upgraded particle swarm optimization (PSO)-backpropagation (BP) neural network prediction model, and a lateral transfer inventory optimization method based on demand forecasting. Finally, 26 retailers of Company B in Central China's Hunan Province were taken as examples to confirm the model's efficacy. The outcomes demonstrate an improvement in the lateral transfer's applicability in Company B.

Editorial to the Inaugural Issue

Dear editors, reviewers, authors, readers, and other members of the whole scientific and professional community, Welcome to this inaugural issue of Journal of Intelligent Systems and Control (JISC)! On behalf of the editorial office, I am writing with great pleasure and sincere privilege to present the first issue of the journal JISC. The past few years has witnessed a growing necessity for advanced intelligent systems, as artificial intelligence penetrate virtually all fields of science, industry, and life. There are many indicators of nature and social systems, some of which conflict with each other. Intelligent systems and smart control methods are urgently needed to resolve the potential conflicts. However, it is very challenging to develop such systems and methods, facing the uncertainties of the environment, the limited time, and the lack of financial resources. Against this backdrop, it is necessary to design intelligent systems based on intelligent and automatic control strategies. Such intelligent systems would save personnel costs, make our society more efficient, and enable proper decision-making. This first issue aims to answer many important questions related to the scope of the journal. Seven very interesting high-quality papers are selected for publication. These papers apply decision models in various fields: in the lateral transfer inventory optimization technique for auto spare parts, in the wind-solar hydrogen storage coupled power generation system, in the automatic car pedal pressing system, and in the cargo transportation of cranes. Additionally, the micro-positioning stage, the data sharing of multi-cloud storage server, and the power system voltage stability, are also discussed in this issue, providing important insights into various intelligent systems. Journal of Intelligent Systems and Control (JISC) (ISSN 2957-9805) is an international open access scholarly journal addressing the theories, methods, and applications underlying intelligent systems and system control. The mission of the journal is to foster new thinking and research, and facilitate the understanding of operating and control mechanisms of economic, engineering, management, and technological systems. We welcome original submissions in various forms, including review articles, regular articles, short communications, as well as Special Issues on particular subjects. The journal encourages contributions related to the new developments in theory and practice that can improve the performance and control of various systems. We follow principle of international diversity regarding the editorial board, reviewers and authors. Therefore, we invite and welcome submissions from around the world. All information related to JISC journal are available in our website: https://www.acadlore.com/journals/JISC.

The optimization of typical species inventory of habitat types of a NATURA 2000 site using a phytosociological approach

The definition of typical species inventories of the 92/43/EEC Directive habitat types is a valuable information for the optimization of the conservation status assessment. Habitat-specific assessment protocols and predefined local inventories of typical species provide a method for a relatively fast and accurate assessment of the criterion “structures and functions”. Habitat types are often defined and described on the basis of a phytosociological description of vegetation units, mainly at the syntaxonomical level of alliance. Therefore, the definition of typical species inventories can be based on phytosociological approaches. Within this concept we surveyed the vegetation of a NATURA 2000 Special Area of Conservation in northern Greece in order to optimize and downscale the existing region-wide inventories of typical species. In total, we sampled 164 relevés in beech and in thermophilous deciduous broadleaved forests. The relevés were assigned to vegetation units and habitat types using numerical approaches and their differential and constant taxa were defined. We used these taxa to draw up the optimized, site-specific inventories of typical species for seven habitat types of community interest and one habitat type of national interest.

Application of intelligent logistics inventory optimization algorithm based on digital supply chain

Abstract Inventory is the core link of enterprise operation and an essential resource for enterprises to occupy the market. Therefore, optimizing the control and management of inventory is a necessary measure for enterprises to maintain their core competitiveness. However, at present, the optimization of the enterprise’s inventory is basically still at the single inventory level, which seriously shortens the life cycle of the enterprise’s products and reduces the speed of the enterprise’s capital flow. Digital supply chain is the digitization of traditional supply chain services, which can change the traditional thinking of inventory control and management, break down the barriers between enterprises and modern logistics, and build a complete management system for enterprises. Smart logistics is a product of the new era, and it is also a product of the development of the digital supply chain. To this end, this paper proposes an inventory optimization algorithm based on digital supply chain and smart logistics. The algorithm is optimized on the basis of the original inventory optimization scheme, so that the improved algorithm can be more suitable for actual inventory management needs. The experimental results of this paper show that the improved new inventory optimization algorithm improves the comprehensive benefit by 39.1% on the original basis, which can effectively reduce the error in the actual use process.

A two-stage Genetic Algorithm for joint coordination of spare parts inventory and planned maintenance under uncertain failures

The main problem of spare parts management is to maintain the minimal requirement of stock keeping units kept. This research proposes a joint optimization model of multi-item multi-period spare parts inventory management and planned maintenance under uncertain failures in order to balance inventory cost and spare parts availability. This paper presents a Mixed Integer Non-linear Programming formulation of the inventory optimization model under a minimum and maximum inventory policy with stock review intervals. Some studies in the literature have considered aggregating spare parts inventory management as they assume that it will reduce the ordering cost. We consider both independent and aggregate spare parts inventory policies and then combine the formulation with the predictive maintenance interval, which is a replacement action due to uncertain failures under predefined distribution. Furthermore, a novel two-stage Genetic Algorithm is proposed as a sim-heuristic approach to deal with the non-linearity, combinations, and stochasticity of the problem and solve large-scale instances. In the end, we perform a computational study on some instances and a real-world case study to demonstrate the proposed approach’s effectiveness and efficiency. The computational study shows that the independent policy results in lower cost than the aggregate policy, and the proposed Genetic Algorithm performs efficiently for large-scale problems.

Optimizing the inventory and fulfillment of an omnichannel retailer: a stochastic approach with scenario clustering

We study an inventory optimization problem for a retailer that faces stochastic online and in-store demand in a selling season of fixed length. The retailer has to decide the initial inventory levels and an order fulfillment policy such that the expected total costs are minimized. We approximate the problem by a two-stage stochastic optimization on a reduced number of scenarios. For deciding the representative scenarios, we propose a new similarity measure and a novel technique that combines the framework of Good–Turing sampling and Linear Programming. On randomly generated instances, the proposed algorithm obtains an average cost reduction of 7.56% compared to a state-of-the-art algorithm in the literature. The proposed algorithm works considerably better for short time horizons and a relatively large proportion of in-store customers.

Many-objective optimization of a three-echelon supply chain: A case study in the pharmaceutical industry

This paper proposes an order-up-to (OUT) replenishment policy integrated with inventory routing optimization, formulated as a three-echelon supply chain. The OUT policy is used for raw material purchasing and transportation from the suppliers to support warehouses. Inventory routing optimization is applied to transport the raw materials to the main warehouse when required, where manufacturing operations take place. The optimization problem is solved using a many-objective genetic algorithm. The proposed optimization framework can be applied to the pharmaceutical industry and to any other highly dynamic industry with large product portfolios. This paper presents a real-world case in the pharmaceutical industry from Hovione Farmaciência SA. The performance of the many-objective optimization is compared with a summed single-objective simplification, showing that while the total cost reduces by using single-objective optimization, the optimal scenarios offered by the many-objective optimization may provide additional insight to decision-makers and act as a decision support system, being more inline with the human–machine cooperation trends of the industry.

Optimalisasi Persediaan Bahan Baku Kemas dengan Metode Program Dinamis Algoritma Wagner Within

Inventory is a very important role for a company especially manufacturing industry. Good inventory control is needed to manage inventory to be effective and efficient. This research held at PT XYZ because there are some problems such as overload warehouse and overstock inventory. The purpose of this research is to analyze packaging material inventory to get the optimal inventory with warehouse capacity constraint. Primary data were obtained through observation at Pulogadung warehouse, interview with related divisions, and secondary data were obtained from company documents. Data were analyzed by Material Requirement Planning with Wagner Within Algorithm Dynamic Program Method. The result of this research show that Wagner Within Algorithm dynamic program can decrease the expand of the company beside the exist method the company used. Some implementation impacts of silver meal dynamic program are the availability of materials when they needed and warehouse is not overloaded.