No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Optimizing ABC Inventory Grouping Decisions
Abstract
Inventory managers often group inventory items into classes to manage and control them more efficiently. The well-known ABC inventory classification approach categorizes inventory items into A, B and C classes according to their sales and usage volume. In this paper, we present an optimization model to enhance the quality of inventory grouping. Our model simultaneously optimizes the number of inventory groups, their corresponding service levels and assignment of SKUs to groups, under limited inventory spending budget. Our methodology provides inventory and purchasing managers with a decision-support tool to optimally exploit the tradeoff among service level, inventory cost and net profit. The model and solution are applied for an inventory classification project of a real-life company, and outperform the traditional ABC method. Computational experiments are performed to obtain managerial insights on optimal inventory grouping decisions.
... Manufacturing company stores various of Raw Materials and components to meet production needs in a huge amount so that it is impossible to control the whole thing [4]. One way to handle a lot of SKU is to aggregate it into several groups [5]. ...
... Grouping the inventory with various service level can also shows the demand fulfillment strategy of the company. The determination of service level that is used will affect company's revenue [4]. Implementing Multiple Criteria ABC A simple classifier for multiple criteria ABC Analysis by W. L Ng, 2007 [6]. ...
... The method used is branch and cut. [4]; using matrix diagram and parameter of stock control policy based on classification in manufacturing company [8], [9]. A traditional ABC concept is known as Divides inventory into three classes based on annual dollar volume Class Ahigh annual dollar volume, Class Bmedium dollar volume, Class Clow annual dollar volume and used to establish policies that focus on the few critical parts and not the many trivial ones. ...
... As it suggests, the policy should be that only 20% of the inventory make up 80% of the total annual cost of the inventory system, and the remaining 80% account for only 20% of the costs. The result of such an analysis shows that class A should be very low, class B low, and class C the least controlled [35]. ...
... The method of grouping and inventory control available in traditional ABC has several disadvantages. First of all, there are no specific guidelines in the literature with which to specify the service level for each group [35]. Secondly, since grouping decisions are independent and are preceded by service level decisions, their interactions are not applied and neither of the two decisions can be optimal. ...
... The well-known ABC approach classifies inventory items to A, B, and C based on their usage and sales. Millstein et al. [35] presented an optimization formulation to improve the quality of inventory grouping under a limited budget. In the research by Kaabi et al. [25], TOPSIS was used to calculate the score of each inventory item, and a continuous-valued number system (CVNS) algorithm was used to create the weighting criterion. ...
In modern business today, organizations that hold large numbers of inventory items, do not find it economical to make policies for the management of individual inventory items. Managers, thus, need to classify these items according to their importance and fit each item to a certain asset class. The method of grouping and inventory control available in traditional ABC has several disadvantages. These shortcomings have led to the development of an optimization model in the present study to improve the grouping and inventory control decisions in ABC. Moreover, it simultaneously optimizes the existing business relationships among revenue, investment in inventory and customer satisfaction (through service levels) as well as a company's budget for inventory costs. In this paper, a mathematical model is presented to classify inventory items, taking into account significant profit and cost reduction indices. The model has an objective function to maximize the net profit of items in stock. Limitations such as budget even inventory shortages are taken into account too. The mathematical model is solved by the Benders decomposition and the Lagrange relaxation algorithms. Then, the results of the two solutions are compared. The TOPSIS technique and statistical tests are used to evaluate and compare the proposed solutions with one another and to choose the best one. Subsequently, several sensitivity analyses are performed on the model, which helps inventory control managers determine the effect of inventory management costs on optimal decision making and item grouping. Finally, according to the results of evaluating the efficiency of the proposed model and the solution method, a real-world case study is conducted on the ceramic tile industry. Based on the proposed approach, several managerial perspectives are gained on optimal inventory grouping and item control strategies.
... The inventory level of individual assortment items depends primarily on their movement, i.e., the extent and nature of consumption for the monitored period (day, month, year, consumption date, uniformity of consumption in the planned period, etc.) and the size of the production batch that is consumed in production at one time. The nature of consumption can be expressed by the continuity of consumption, which essentially means continuity in the need and subsequent consumption of the given items [5][6][7][8][9]. The choice of the method that will be used in determining the control levels of inventory of the given item may consider costs or may not consider costs. ...
... Inventory are divided into three groups (A, B and C) according to the share of the total volume of the given unit. It is based on the Pareto principle, which states that 20 % of the causes make up 80 % of the consequences [5]. In the study [18], the authors address the issue of safety inventory dimensioning at the strategy level. ...
... Inventory classification with limited inventory space Millstein et al. (2014) dealt with a multi groups inventory classification problem. Each product item was to be classified into a group with the same corresponding service level. ...
... A MILP model was developed to dynamically integrate and optimize the inventory classification and inventory control decisions to maximize the net present value of profit over a planning horizon. Ly & Raweewan (2021) refer to the mathematical model proposed by Millstein et al (2014) to deal with an inventory classification problem. However, Ly & Raweewan (2021) extend the mathematical model to consider the total number of pallets required as the constraint. ...
This research addresses an inventory classification problem in a company that manufactures plastic pallets. Classification of the inventory is difficult because it is subject to two restrictions: the number of changeovers and the size of inventory storage. A mathematical model is first proposed to maximize the fill rate by classifying all product items into four groups. Due to all items can be classified based on the monthly demand, in descending order. The present study then proposed a procedure to find the classification that is most efficient. According to the experimental results, the maximum fill rate in the current situation is 89.85%. The proposed methodology also tested different production batches and levels of demand. The proposed methodology was found to be appropriate for practical application.
... Inventory classification with limited inventory space Millstein et al. (2014) dealt with a multi groups inventory classification problem. Each product item was to be classified into a group with the same corresponding service level. ...
... A MILP model was developed to dynamically integrate and optimize the inventory classification and inventory control decisions to maximize the net present value of profit over a planning horizon. Ly & Raweewan (2021) refer to the mathematical model proposed by Millstein et al (2014) to deal with an inventory classification problem. However, Ly & Raweewan (2021) extend the mathematical model to consider the total number of pallets required as the constraint. ...
... Ramanathan used four criteria to solve multi-criteria and used a complex algorithm in ABC classifications [3]. Also, many methods deal with multi-criteria classification problem [4][5]. [6] designed a model based on the ABC classification and shared similarity of products to solve the storage problem for a new arrival. ...
... Mean Absolute Percent Error (MAPE) is the average of the absolute value of the difference resulting between the predicted and real values, represented as a percent of real value, as shown in equation (5). ...
... Manufacture, retailer, repair shop, and hospitals usually keep the components and raw material into stock-keeping units (SKUs) to meet the demand [19]. However, the number of these SKUs cannot be large due to difficult individual control [11]. ...
... To calculate the crowding distance, Eqs. (19) and (20) are used: ...
One of the most applicable techniques in the inventory management field is inventory classification based on ABC analysis, a well-known method to set the items in a different group, according to their importance and values. In this paper, a bi-objective mathematical model is proposed to improve the inventory grouping based on ABC analysis. The first objective function maximizes the total net profit of the items in the central stock, and the second objective function maximizes the total net profit of items in different wards. The proposed model simultaneously optimizes the service level, the number of inventory groups, and the number of assigned items. To solve the model in small and large dimensions, two exact methods (LP-metric and ε-constraint) and two meta-heuristic methods (NSGA-II and MOPSO) are used. Then, to compare those methods in terms of efficiency, the statistical analysis besides the AHP and VIKOR techniques is implemented. The results show the superiority of the ε-constraint among the exact methods and MOPSO among meta-heuristic methods. Finally, the proposed model has been implemented in two sets of numerical examples to demonstrate its applicability.
... Así, la gestión de cadenas de suministro involucra el diseño y gestión de todas las actividades de una cadena de suministro para garantizar la satisfacción del cliente y maximizar la rentabilidad de la cadena [2]. Para ello, se parte de la definición de estrategias, métodos, actividades y metodologías para el funcionamiento de la cadena de suministro; luego, el objetivo es lograr el funcionamiento eficiente y eficaz de los diferentes eslabones, en especial, reducir tiempos de espera y optimizar el uso de los recursos existentes para disminuir los costos de operación individuales y de la cadena de suministro [3][4][5][6]. ...
... Usualmente, se usa la clasificación ABC, que se fundamenta en la teoría de Pareto. Millstein, Yang y Li [5] desarrollaron una herramienta informática con el fin de optimizar el número de agrupaciones de SKU y a su vez mejorar los niveles de desempeño, añadiéndole herramientas de experimentos computacionales y análisis de costos. Por otra parte, Yu, De Koster y Guo [23] desarrollan un análisis sobre la clasificación por clases en la que se muestra que no siempre es conveniente usar mayor cantidad de clases, dado que podría conllevar a una asignación no eficiente de los SKU y afectar el desempeño. ...
Supply Chain Management is based on formulating models and methodologies to improve and optimize operations and internal processes, in order to increase efficiency and response capacity and simultaneously reduce costs. In Supply Chain Management, activities carried out in warehouses and distribution centers are critical to ensure an optimum service level and to obtain significant savings in total logistics costs. Slotting and picking are two fundamental activities in the efficient warehouses operation and management. For this reason, we made in this article an exhaustive bibliographic review on models and methodologies used for optimizing slotting and picking, between 2000 and 2018, identifying indirect applications in other types of industries and research opportunities and trends, considering the factors that influence the flow of materials and stochastic components in inventory planning: dynamic accommodation, route analysis, cluster location methodologies and warehouse division according to the type of products.
... When it is required to manage a wide number of products, it is suggested the aggrupation and the elaboration of stock policies corresponding to each one of the resulting groups [5]. The ABC method is useful to get a better follow up of the stock, taking reference on the sales and the products volume [6]. The classification with the ABC inventory methodology is often applied in the industry [7,8], which was created by GE [8] in 1950. ...
... The ABC method helps us to have a better inventory tracking, based on the sales and the volume of the products [6]. Approximately, the 20% of inventory provides to the economy the 80% of sales and incomes within the company, this is well-known as the "80-20" Rule. ...
The lack of proper inventory control in a company engaged in the marketing of goods, which are supplied to the welding industry, is presented throughout this paper. The main objective of this work is to supply sufficient product to the client without saturating its warehouses. The paper describes an analysis of factors influencing the behavior of demand for products purchased in China. Once the inventory is identified, it will be possible to have more certainty about the required order size of foreign suppliers in China, meeting the demand requirements within the domestic market. Avoiding lost sales due to lack of inventory products or materials with slow movement that become discontinued products as the purchase is for a larger amount than expected by customers. The computational tool employed is ANFIS (Adaptive Neuro-Fuzzy Modeling), which includes fuzzy logic, allowing to deal with the uncertainty or lack of information and to calculate the demand level based on an analytical and a more accurate method. Because of this, an inventory policy which improves the distribution system of the company is created.
... All these studies consider a single-item inventory system. When factoring in real-world complexities such as multiple products, transportation costs, truck capacity, supplier capacity, inventory budget, and volume discounts, inventory replenishment problemseven without considering lost salesare generally NP-hard and require a mathematical programming approach to find optimal or near-optimal solutions (e.g., Hsu, 1983;Chan et al., 2002;Neale & Willems, 2009;Baki et al., 2014;Millstein et al., 2014;Skouri et al., 2014;Ö nal, 2016;Akbalik & Rapine, 2018;Duan & Ventura, 2021). ...
Pallets are widely used for bulk shipping in the United States and Europe. In response to the call for more comprehensive research on inventory management that incorporates practical freight rates, this study investigates optimal inventory replenishment decisions by explicitly considering palletized shipping rates and lost sales in multi-product multi-period inventory systems facing stochastic demand. We first introduce a stepwise transportation cost function that accurately captures real-world palletized less-than-truckload (LTL) and truckload (TL) shipment costs by accounting for both pallet quantity and truck capacity. We then formulate two novel inventory models that consider palletized freight transportation costs and the coexistence of LTL and TL shipments, with one model excluding lost sales and the other specifically incorporating lost sales. We apply both models to a wholesaler based in the Midwest, U.S., and analyze the effects of varying shipping rates and lost sales on inventory decisions. Our results show that the inclusion of lost sales in the inventory replenishment model can potentially reduce total costs for the company. Interestingly, our findings contradict prevailing industry practices of maximizing truck capacity, revealing that filling up the “free” space on a truck may increase total logistics costs. This holds even when shipping rates are relatively high and lost sales are considered. Furthermore, our results suggest that joint optimization of transportation and inventory decisions may not be necessary when shipping costs are small relative to inventory costs and lost sales are not considered. However, as shipping rates increase and lost sales are factored in, a joint optimization that accounts for all factors can yield much greater savings.
... In this topic, Millstein, Yang and Li (2014) developed a model to improve the quality and efficiency of the inventory grouping. The model optimized the number of groups and SKUs assignment according to service level. ...
This paper aims to develop an allocation model integrating SKUs physical variables, warehousing design and operation (dimensions, layout, material handling equipment), and heterogeneous product demand. The modeling methodology considers two phases. First, an integer linear programming model for warehousing spaces assignment for SKUs considering priority and required orders is developed. Then, the total operation times using different strategies are calculated. The results showed that the best performance in the total time of the slotting operation is achieved by using the ABC as a criterion for the classification of the SKUs and by sequentially assigning the row, level, column, and section.
... With the support of this method, logistics operators can make more rational and informed decisions that will yield positive results in their operations. However, the ABC method has several limitations, which are mitigated by various extensions and modifications (notably observed in Abdolazimi et al., 2021b andMillstein et al., 2014). One of these limitations, focused on in this article, is the fact that the ABC method relies on historical data, thus solely on information related to what has already happened. ...
... Te author in [9] was the frst to develop a multicriteria ABC classifcation model with linear programming. Furthermore, the authors in [17] propose a mixed integer linear programming model with multiple objectives: to optimize the number of inventory groups, their service levels, and the allocation of products to each group, under a limited inventory expense budget. Te model was tested in real life, obtaining better results than the traditional ABC classifcation. ...
Products’ classification according to their importance has been a topic addressed by academia and industry for many years, mainly due to the great importance of this process to obtain efficient inventory policies that reduce lost sales while reducing inventory maintenance costs. This research has to perform an ABC inventory classification in a medium-sized company that sells hardware goods and construction materials, considering multiple quantitative and qualitative criteria. AHP fuzzy TOPSIS multicriteria tool was used as a methodological approach which implies the definition and initial weighting of a set of relevant criteria for the study based on the AHP fuzzy methodology, to obtain an inventory products’ importance assessment according TOPSIS technique procedure. After applying the technique, it is possible to obtain that 0.26% of the inventory was classified as highly critical. Likewise, 5.45% represents products of medium relevance to the organization. Finally, it is observed that many of the products (approximately 94%) have little or almost no impact within the company under study. This methodology was used in a practical case where some criteria were taken from the reviewed literature. In addition, the criticality criterion was used from a financial perspective.
... Few studies have provided structured methodologies to exploit the results of an ABC classification to review spare parts SC configurations (thereby planning both stock deployment and supply policies in multiple DCs). Specifically, albeit multiple studies have investigated multi-criteria ABC criticality classifications of spare parts, most of them belong to two research streams (Millstein, Yang, and Li 2014). The first research stream comprises studies proposing brand-new ABC classifications or improvements to existing classifications (Lolli, Ishizaka, and Gamberini 2014). ...
Configuring supply chains (SCs) is critical to spare parts retailers' success, entailing two key aspects: stock deployment into distribution centres (DCs) (i.e. inventory centralisation or decentralisation) and stock supply in each DC (how many spare parts to supply and how often). Given the unpre-dictability of spare parts demand, stock deployment and supply policies should be regularly reviewed, adapting to fluctuations in customer needs. A viable way to do this is to adopt a multi-criteria ABC criticality classification. However, the multi-criteria ABC criticality classification has often been used to plan stock supply policies in a single DC, but only once to plan spare parts deployment. Nevertheless, the available literature methodology presents major limitations, being not applicable in real companies. Therefore, this paper provides a novel methodology, called SP-LACE, which first reviews the configuration of spare parts SCs based on a multi-criteria criticality classification. Then, allows, for the first time, to evaluate the economic benefits of the reviewed SC configuration. SP-LACE was tested on two case studies and compared with the literature methodology. The results indicate that it provides economic benefits (in terms of total SC cost), overcoming the limitations of the literature methodology and ensuring high service levels.
... With portfolio models, buyers can enhance purchasing performance (Gelderman and van Weele, 2005), the use of purchasing strategies (Nellore and Söderquist, 2000), the relationship development with suppliers (Ahtonen and Virolainen, 2009) and the resource allocation to selected suppliers (Olsen and Ellram, 1997). When compared to other portfolio models, such as ABC analysis that provides information only about how to allocate purchase spend (e.g., Flores and Whybark, 1986;Millstein et al., 2014), the Kraljic's purchasing portfolio does not focus only on the financial value of purchased goods, like the ABC model does by excluding all other important factors such as quality, performance and social risks (Gelderman and van Weele, 2005). Because of the uncertainty of the markets, companies need tools to protect their supply chains from disruptions (Wu et al., 2007), and for that, Kraljic suggested classification based on a portfolio model that, in addition to considering profit impact, also considers the supply risk. ...
Abstract Portfolio models are popular in purchasing and supply management to optimise strategies for supplier relationship management. Portfolio models, such as Kraljic’s purchasing portfolio, are based on subjective judgements and are qualitative in their nature. Portfolio models have been criticised because they lack guidelines on how the models could be applied in practice. The key to the application is the definition of appropriate key attributes that can be used for measuring and defining the dimensions. In this study, the factors which influence the supply risk and profit impact are studied by deriving the appropriate attributes from the empirical data of a multinational electrical manufacturer. This study contributes by identifying the key attributes for the dimensions of profit impact and supply risk and by scaling these with numerical values for the purposes of Kraljic’s matrix. As a result, this study provides a practical model, explaining how companies can apply Kraljic’s matrix.
... Una forma de administrar una gran cantidad de skus es clasificarlos en diferentes grupos y establecer políticas de control comunes en cada grupo. La clasificación permite que los administradores puedan tener un mejor desempeño en el control del inventario (Millstein, Yang y Li, 2014). El análisis ABC basado en el principio de proponen que el intervalo medio entre la demanda distinta de cero debe ser 1.25 mayor al periodo de revisión del intervalo. ...
Purpose: To classify the type of product demand placed on the market by auto parts companies in Mexico focusing on the assembly and sale of auto parts at national and international level, which is the basis for the adequate provision of materials in the studied supply chain. Methodologyical design: From a total of 14,895 products, 326 components were selected through the ABC method to perform the demand pattern analysis which was carried out according to the average demand interval and the square coefficient of variation using the monthly demands of each product. Results: The probabilistic analysis of the demand for the 14,895 products shows smoothed (63.80%), erratic (19.94%), lumpy (11.35%) and intermittent (4.91%) demand patterns from which it is concluded that the demand patterns for these companies are mainly of the smoothed type. Research limitations: The probabilistic analysis conducted is based on the data provided by three autoparts companies in México, of which, after the ABC analysis, only the articles of category A were considered for the results obtained. Proposing a different technique other than ABC analysis is limited by the type of data provided by companies. Findings: Due to the number of factors involved in demand variability, it is vital to rely on tools that aid in reaching trustworthy demand forecasts, maintaining companies competitive in customer service quality. Further, the complexity of forecasting automotive spare parts is a challenge which the automotive industry is currently facing. The classification of demand patterns resulting from the study allows for the selection of an appropriate forecasting method for each pattern and improvement of supply conditions of the different companies. This type of study and data analysis permits better decision-making by those responsible for the supply components.
... (Tavassoli et al., 2014) used data envelopment analysis (DEA) to classify inventory items into three groups with weight restrictions in order to allow managerial preferences. Another model simultaneously optimises the number of inventory groups, corresponding service levels and assignment of SKUs within the group (Millstein et al., 2014). (Narkhede & Rajhans, 2022) discusses an integrated approach where they use rank order clustering (ROC) technique to redesign inventory management strategies for small and medium-sized enterprises. ...
Item clustering has become one of the most important topics in terms of effective inventory management in supply chains. Classification of items in terms of their features, sales or consumption volume and variation is a prerequisite to determine differentiated inventory policies as well as parameters, most common of which is service levels. Volume classification is easily obtained by well-known Pareto approach while coefficient of variance is usually used for variation dimension. Hence, it is not always applicable to classify items under different product families with different demand patterns in terms of variation. In this paper, we propose two algorithms, one based on statistical analysis and the other an unsupervised machine learning algorithm using K-means clustering, both of which differentiate seasonal and non-seasonal products where an item’s variation is evaluated with respect to seasonality of the product group it belongs to.
... The advantage of this policy is that fast moving products can be stored close to the depot while the flexibility and high storage space utilisation of random storage are applicable. Generally, there are two kinds of class-based storage, 1 dedicated purposes (Brynzér and Johansson, 1996;Liu, 1999) 2 ABC classification (Montulet et al., 1998;Li et al., 2015;Balaji and Kumar, 2014;Millstein et al., 2014). ...
... There are numerous segmentation applications in various areas; however, literature is sparse in formulating a generic framework to segment the spare parts based on compatibility with AM. The segmentation framework also facilitates groupings of the spares for better inventory management (Chakravarty, 1981;Millstein et al., 2014;Mohammaditabar et al., 2012). ...
Organizations strive to find new ways to manage the production of strategic spare parts with unanticipated demand and high delivery time. Additive Manufacturing (AM) is a revolutionary technology that effectively serves such needs by producing compatible spare parts in a shorter period without holding inventories. Although the promising benefits of spare parts production through AM, research is scarce in this domain. This study is developed to demonstrate the applicability of AM in spare part manufacturing. We have proposed a novel generic multi-criteria framework using Delphi, analytical hierarchy process (AHP), and segmentation approaches to identify the most compatible spares producible through AM. The applicability of the proposed framework is illustrated through a real-life case study. Delphi is used to determine and validate relevant criteria considered for spare part classification. This results in determining 11 criteria belonging to two group criteria, namely – Business Impact (BI) and Technical Compatibility (TC). AHP is used to compute the relative weights of criteria for prioritizing them. A normalization (objective criteria) and rating (subjective criteria) approach is used to evaluate the total score of each spare part for BI and TC. Spare parts are clustered into four quadrants (Type A, B, C, and D) using the segmentation approach according to the total scores of BI and TC. This generic framework benefits practitioners in identifying technically compatible spares for AM that improve business competitiveness.
... Hadad and Keren [12] employed the statistical methods for classifying inventory items. Millstein and Yang [13] developed a new approach to optimize the number of inventory groups. Their model optimizes the number of inventory groups and allocation of SKUs to groups based on a limited inventory budget. ...
One of the common methods for classifying inventory items is ABC classification approach. In many cases, the data might be stochastic. In the current study, using stochastic data envelopment analysis model, we present a new approach to categorize inventory items given stochastic data and nature of criteria. Then, a new stochastic mixed integer programming model is proposed to forecast classes of the new inventory items. The proposed stochastic mixed integer programming model does not impose subjective judgment on the classification of inventory items and can be used for multi-group classification. The developed approach can classify inventory items and forecast the class of new items with both qualitative and quantitative criteria. The applicability of developed stochastic data envelopment analysis and stochastic mixed integer programming models is demonstrated by a case study.
... They demonstrate that, when a criteria-based classification is applied, the best result is delivered by the approach considering level of importance of criteria used. Millstein et al. (2014) found optimal grouping, maximising super-criterion, combining target indicators such as logistic service level, inventory cost, and enterprise net profit. Optimisation was implemented using the data on monthly average observed demand. ...
ABC-XYZ analysis algorithm classifies commodities and inventory depending on their significance for the company and demand stability. Based on the classification results, the optimal strategies for materials flow management are suggested. If there are commodities with a seasonal or rapidly changing demand in the inventory, then current classification is seriously influenced by the values observed before the change point emergence, which leads to increased significance for commodities already less significant, and the other way around, lower significance of the commodities with the recently increased profit or revenue. This work suggests a modification to ABC-XYZ analysis, which takes into account change point influences, allows finding better fitting groupings and decreases demand variability level by splitting sales series into sections with steady demand. Demand significance is recalculated once change point is detected as a product of a new average demand level for the period and a number of periods observed.
... With portfolio models, buyers can enhance purchasing performance (Gelderman and van Weele, 2005), the use of purchasing strategies (Nellore and Söderquist, 2000), the relationship development with suppliers (Ahtonen and Virolainen, 2009) and the resource allocation to selected suppliers (Olsen and Ellram, 1997). When compared to other portfolio models, such as ABC analysis that provides information only about how to allocate purchase spend (e.g., Flores and Whybark, 1986;Millstein et al., 2014), the Kraljic's purchasing portfolio does not focus only on the financial value of purchased goods, like the ABC model does by excluding all other important factors such as quality, performance and social risks (Gelderman and van Weele, 2005). Because of the uncertainty of the markets, companies need tools to protect their supply chains from disruptions (Wu et al., 2007), and for that, Kraljic suggested classification based on a portfolio model that, in addition to considering profit impact, also considers the supply risk. ...
Abstract Portfolio models are popular in purchasing and supply management to optimise strategies for supplier relationship management. Portfolio models, such as Kraljic’s purchasing portfolio, are based on subjective judgements and are qualitative in their nature. Portfolio models have been criticised because they lack guidelines on how the models could be applied in practice. The key to the application is the definition of appropriate key attributes that can be used for measuring and defining the dimensions. In this study, the factors which influence the supply risk and profit impact are studied by deriving the appropriate attributes from the empirical data of a multinational electrical manufacturer. This study contributes by identifying the key attributes for the dimensions of profit impact and supply risk and by scaling these with numerical values for the purposes of Kraljic’s matrix. As a result, this study provides a practical model, explaining how companies can apply Kraljic’s matrix.
... Table 1 explained the existing modules within the thirty-eight modules with BaaN and SAP/R3, 38% of the modules was suitable and 62% was unsuitable. In this research, module adjustments that will be evaluated is the Precom Chemicals case in Process Planning (PP). the forecasting improvement from sampling of one chosen product is done with ABC classification approach [6] [7]. ...
This study evaluates the SAP R/3 System Implementation through optimization of modules in resin chemicals industry. The company has implemented SAP R/3 software since 2013, but 62% of it has not been adjusted and need to be evaluated for implementation performance, therefore it is unknown whether SAP already reached its optimum point. Therefore, SAP R/3 evaluation is needed through SY Check List, improvement of forecasting, and Material Requirement Planning (MRP). The chosen product that was calculated was the A category product by ABC analysis. The 6 periods (months) forecasting will be used as a base of Master Production Schedule (MPS) to calculate the raw material requirement. The MRP calculation method used Lot-For-Lot because it does not need price information. SY Check List was used to identify in-optimum modules which SAP provided beforehand. The suggestion made based on the best forecasting calculation was used as other A category products forecasting calculation method. Therefore, SY Check List optimized SAP modules not only as a book data, but also logistic as integrated system which have to be maximized. As actual demand fluctuation forecasting method should be changed. More accurate forecasting will define MRP parameters accuracy.
... However, as we have gotten from different article literatures traditional ABC analysis is based on only single measurement (criteria) such as annual dollar usage. Some journals used multi criteria to classify the items based on annual usage dollar, average unit cost and lead time [6], [7], [2] and [8] Service level, Annual sales of stock keeping units(SKUs) [9], annual usage value (AUV), profit margin (PM), the annual number of orders (NO) and the number of clients (NC) [5], for Fertilizer Classification ABC used as an input to forecast the demand depending on lead time and sales price [10]. ...
... According to ABC analysis methodology SKUs are classified into three groups: A, B and C according to their importance. In a typical approach, one can classify inventory items according to their transaction volume or value (Millstein et al, 2014). The conventional ABC classification, based on Pareto principle (80%-20%), was developed at General Electric during the 50's (Flores and Whybark, 1986;Pareto and Page, 1971). ...
... Phase 1: ABC analysis Main products must be identified, which is done through ABC analysis, which is a technique for prioritizing the management of inventories. It divides inventories into three classes, A, B and C, using the total revenues as the segmentation element as for example in [34,35]. ...
Some people may be disadvantaged on the labor market because of their lower productivity; still, they have the same right to be employed as any other citizen. Social cooperatives employ disabled workers who are trained and supported in developing their abilities through individualized paths and targeted techniques. For the cooperatives to survive on the labor market, an improvement of management procedures and internal organization is required. To achieve this result, an optimal arrangement of activities must be determined to streamline the production processes, which is why Systematic Layout Planning (SLP) has been modified and adapted to fit disabled workers contexts. The factors of social cooperatives influencing the layout study have been determined and introduced into the classic SLP; the new methodology has been applied at L’Iride, a social cooperative developed through the years. The new layout has shown an improvement in space saturation of 219.2% and 197.5% considering the years 2019 and 2020. This paper provides social cooperatives with a revised SLP, including social factors, to enhance the disabled workers situation.
... They demonstrate that, when a criteria-based classification is applied, the best result is delivered by the approach considering level of importance of criteria used. Millstein et al. (2014) found optimal grouping, maximising super-criterion, combining target indicators such as logistic service level, inventory cost, and enterprise net profit. Optimisation was implemented using the data on monthly average observed demand. ...
ABC-XYZ analysis algorithm classifies commodities and inventory depending on their significance for the company and demand stability. Based on the classification results, the optimal strategies for materials flow management are suggested. If there are commodities with a seasonal or rapidly changing demand in the inventory, then current classification is seriously influenced by the values observed before the change point emergence, which leads to increased significance for commodities already less significant, and the other way around, lower significance of the commodities with the recently increased profit or revenue. This work suggests a modification to ABC-XYZ analysis, which takes into account change point influences, allows finding better fitting groupings and decreases demand variability level by splitting sales series into sections with steady demand. Demand significance is recalculated once change point is detected as a product of a new average demand level for the period and a number of periods observed
... Traditional ABC classification, which uses annual dollar volume to grouping items, is considered an easy way to use yet can create inefficiencies in inventory management. Simply considering total value as criteria can lead to inappropriate decisions on inventory items classification (Millstein, et al. 2014). ...
This research aims to observe current inventory management applied by one of the medical equipment distributors specializing in eye health devices, and provide recommendations for an optimal inventory management system to achieve cost efficiency afterward. The method used in this research is quantitative, focusing on processing and analyzing numerical data obtained from the company to calculate safety stock and the number of orders. In addition, ABC classification is also used in data processing to group items based on their value. Items belonging to class A (having a value of 80% for the company) will be used in the data processing. The next step is to conduct forecasting simulations for demand forecasts. The results of the forecast will be used for calculating the safety stock and order quantity. The output from the results of data processing and analysis in this study shows 67 items included in class A, which will then be processed using Minitab software for forecasting. Based on comparing the four forecasting methods, the one with the lowest error value is Trend Analysis. If the company can apply the storage method according to the fixed-time period model calculation, there is a potential savings of US $ 717,133 or 63% of the total overstock
... These works usually cross into the category of inventory management. Millstein et al. (2014) for example, enhance an often-used "ABC method" of inventory grouping, which categorizes items into three classes based on sales and usage. They propose an improved mixed-integer linear programming (MILP) formulation for such grouping, based on demand, profit, budget, and several other cost factors. ...
This paper presents customer selection and incentivization methodologies necessary for the implementation of many SKU rationalization schemes. Our work accounts for the problem of business demand loss, which is undesirably associated with the benefits of rationalized product offerings. We apply our methodologies to a particularly complex instance of SKU rationalization established in the literature, namely a case of demand substitution within a packaged gas supply chain planning problem. This is done both to display the value of our contributions, and to provide a business setting for the workflow process we prescribe for decision makers. In our first contribution, we develop a customer selection heuristic which pre-processes targets for demand substitution, subject to demand characteristics and the supply chain features. The heuristic is shown to outperform objectives utilizing random customer selection by 10–20%, dependent on the desired amount of substitution required of the demand-base. Further, we show that the heuristic outperforms an MILP extension, which explicitly includes customer selection as a decision in the underlying supply chain problem's model, by 7% across a variety of cases. Our second contribution regards development of prescriptive incentivization methodologies for a business, in order to secure shifts in demand profiles across the selected customers. We present multiple strategies for both determining offerings and analyzing system implications, while recognizing stochastic and diverse customer behaviors. In addition to providing useful methodologies around SKU rationalization, trade-offs and business implications throughout the execution of such ideas in practice are heavily considered throughout this work.
... Annual dollar usage, average unit cost, critical factor, and lead time are considered to be categorization criteria in this study. Millstein et al. (2014) developed an optimization model to optimize the number of inventory groups, their commensurate service levels, and allotment of SKUs to groups when the inventory budget is constrained. The criteria used in their example are annual demand, gross profit per unit of SKU, inventory holding cost, fixed overhead management cost, and service level. ...
Inventory classification is a fundamental issue in the development of inventory policy that assigns each inventory item to several classes with different levels of importance. This classification is the main determinant of a suitable inventory control policy of inventory classes. Therefore, a great deal of research is done on solving this problem. Usually, the problem of inventory classification is considered in a multi-criteria and uncertain environment. The proposed method in this paper inspired by the notion of heterogeneous decision-making problems in which decision-makers deal with different types of data. To this aim, a mathematical modeling-based approach is proposed considering different types of uncertainty in classification information. Demand information is considered to be stochastic due to its time-varying nature and cost information is considered to be fuzzy due to its cognitive ambiguity. A hybrid algorithm based on chance-constrained and possibilistic programming is proposed to solve the problems. Considering the stochastic nature of demand information, solving the proposed model using the hybrid algorithm, the classification of items to three classes of extremely important, class A, moderately important, class B, and relatively unimportant, class C, items are determined along with a minimum inventory level required to deal with the stochasticity of demands information. The proposed approach is applied to a case study of classifying 51 inventory items. The obtained results assigned 22%, 39%, and 39% of the items to A, B, and C classes, respectively.
... In previous researches, product classification has mainly been addressed through analytical models to create optimal ABC classifications (Ding & Sun, 2011;Flores, Olson, & Dorai, 1992;Jeddou, 2014;Ramanathan, 2006;Teunter, Babai, & Syntetos, 2010;Touping & Zhixue, 2008; the list is not exhaustive). Even though the classification is widely used in practice (Millstein, Yang, & Li, 2014), no past studies were found on practical implications and impacts in a supply chain context. In particular, no previous research has been found in which product classification was assessed through simulation. ...
... The advantage of this policy is that fast moving products can be stored close to the depot while the flexibility and high storage space utilisation of random storage are applicable. Generally, there are two kinds of class-based storage, 1 dedicated purposes (Brynzér and Johansson, 1996;Liu, 1999) 2 ABC classification (Montulet et al., 1998;Li et al., 2015;Balaji and Kumar, 2014;Millstein et al., 2014). ...
Purpose The article addresses the optimization of safety stock service levels for parts in a repair kit. The work was undertaken to assist a public transit entity that stores thousands of parts used to repair equipment acquired over many decades. Demand is intermittent, procurement lead times are long, and the total inventory investment is significant. Design/methodology/approach Demand exists for repair kits, and a repair cannot start until all required parts are available. The cost model includes holding cost to carry the part being modeled as well as shortage cost that consists of the holding cost to carry all other repair kit parts for the duration of the part’s lead time. The model combines deterministic and stochastic approaches by assuming a fixed ordering cycle with Poisson demand. Findings The results show that optimal service levels vary as a function of repair demand rate, part lead time, and cost of the part as a percentage of the total part cost for the repair kit. Optimal service levels are higher for inexpensive parts and lower for expensive parts, although the precise levels are impacted by repair demand and part lead time. Social implications The proposed model can impact society by improving the operational performance and efficiency of public transit systems, by ensuring that home repair technicians will be prepared for repair tasks, and by reducing the environmental impact of electronic waste consistent with the right-to-repair movement. Originality/value The optimization model is unique because (1) it quantifies shortage cost as the cost of unnecessary holding other parts in the repair kit during the shortage time, and (2) it determines a unique service level for each part in a repair kit bases on its lead time, its unit cost, and the total cost of all parts in the repair kit. Results will be counter-intuitive for many inventory managers who would assume that more critical parts should have higher service levels.
One advantage of online retail is that a large number of products can be displayed at low cost. However, online retailers must decide which of these products to carry in inventory (stock items) and which to order from suppliers when a customer places an order (nonstock items). In this paper, we empirically investigate how carrying a product in inventory affects its online sales. We use data from a European furniture and interior design retailer consisting of daily sales transactions and inventory data covering 18 months. We use a quasi-natural experiment—random transitions of products in and out of inventory at the retailer’s central warehouse—to estimate the causal effect of carrying inventory on sales. Our results show a strong and statistically significant increase in sales of, on average, 65% associated with having the product available in stock. More interestingly, this effect differs between products and is moderated by the price of the product: sales of more expensive products are less sensitive to the product being in stock. We use these results to draw insights on which types of items to carry in inventory. This paper was accepted by Victor Martínez-de-Albéniz, operations management. Supplemental Material: Data are available at https://doi.org/10.1287/mnsc.2023.4777 .
Larger product assortments have been found to have both positive and negative impacts on firms that offer them. More product variety allows firms to increase sales by either selling to a larger customer base or by encouraging current customers to purchase more frequently and in greater quantities. However, more product variety is also associated with lower operational performance. In this research, we investigate the impact of product variety on firm performance in a retail setting. Using data gathered from a large retailer over a 32‐week period for 12 product categories, we develop a multiple stage regression model and find that the effects of product variety on inventory levels, stockout rates and sales differ across more hedonic and more utilitarian product categories. Furthermore, we find that the product variety decision itself is moderated by the hedonic or utilitarian nature of the product category. Implications of the findings for theory and retail management are discussed.
In this paper, we propose a robust ABC classification for inventories using a hybrid technique for order of preference by similarity to ideal solution-alternative factor extraction approach (TOPSIS-AFEA) as the cornerstone method to calculate and rank importance scores for each item in stock. This is done to mitigate multicollinearity that may exist among different inventory criteria, which artificially inflates total data variance. Besides, and differently from previous research, information reliability techniques such as information entropy and gray relational analysis (GRA) are used as an auxiliary tool to differentiate alternative ABC methods proposed in the literature in terms of the principle of maximal entropy. This principle states that the probability distribution that best represents the current state of knowledge given prior data is the one with largest entropy. Results suggest that the proposed robust TOPSIS-AFEA provides an adequate representation of score ranks that may be computed on different datasets by using existing alternative ABC inventory classification models.
Companies worldwide are interested in inventory policies as essential components of the value chain. Inventories of raw materials are required to meet the given demand fluctuations and to support the delivery times of suppliers (lead time). This paper proposes a model for determining an inventory management system for raw materials by using multicriteria methods and fuzzy parameters. The raw materials are classified, and inventory policies are determined, with optimal levels for a company, which are required to have with effective methodologies leading better management of these aspects and better control of their standards. The proposed approach generates an ABC classification by using a multicriteria scoring method, and then inventory policies are defined by using a fuzzy strategy. The proposed approach has been tested in a real company producing items for personal hygiene absorbents and cosmetics. The obtained results are promising for multinational companies.
This paper proposes a group decision making model with individual preferences to investigate the multicriteria ABC inventory classification problem. We first propose a preliminary group decision matrix by means of identifying the individual preference among the classification criteria as a typical decision maker; then analyze the endogenous individual preference structure in terms of exploring the preferential difference and preferential priority, a revised group decision matrix is therefore presented; thirdly, make the use of SMAA-2 to derive the holistic acceptability index for classifying the SKUs. A satisfaction index is developed to manifest the merits of proposed method. A numerical illustration using the data drawn from previous studies is performed to indicate the applicability and feasibility of our method.
Supply chain segmentation and inventory classification, specifically, are considered a competitive advantage in many industries. Approaches like the ABC-XYZ analysis are commonly used in practice to classify SKUs based on simple rules for ranking even though simplified rules-of-thumb may lead to sub-optimal decisions and higher costs. We thus propose a cost-based, multi-dimensional inventory classification scheme for assigning SKUs to classes of replenishment policies that prescribe a group service level, a demand distribution, and an inventory control rule. We further provide an extension for classification under an overall service constraint. Our methodological approach is based on machine learning classifiers and we employ a genetic algorithm to train cost-minimising decision trees which allow for easy understanding and reproduction of classification decisions. Cost- and operational focus, simple application, and interpretability are our main contributions to the inventory classification literature. We evaluate the approach on three industry data sets and show that the classification trees result in an average cost increase of only 1.01% (3.70% with an overall service constraint) over the cost-optimal classification, where no tree structure is enforced. Once trees are constructed, unseen data can be classified out-of-sample with an average cost increase of 1.85% (7.68%) over the optimal cost of classification.
Inventory managers are responsible for the trade-off between inventory holding costs and customer service. In this paper we consider a periodic review multi-item inventory system with exogenous lot-sizes and backordering. The objective is to minimise the total inventory holding costs subject to the constraint that the aggregate fill rate should be at least equal to a target level. The aggregate fill rate is a weighted average of the fill rates of all items in the assortment. We consider three ways of defining this aggregate fill rate: using generic weights, weights based on the average demand (volume) or weights based on the average (monetary) turnover. We show that the definition of the aggregate service can have huge effects on the performance of the system. So, inventory managers should be very careful on which definition to apply. We also derive four heuristics to determine the reorder levels for all items. One heuristic is very generic and can be applied to many problems including multi-item multi-echelon inventory systems and systems with a constrained aggregate ready rate. Since multiple assumptions made to derive the heuristics are common assumptions made in the literature, we first test the accuracy of these approximations using simulation. Next, we evaluate the heuristics based on data from a large international reseller. The heuristic based on the most accurate approximation performs best, is close to optimal and very efficient. Savings compared to no service level differentiation are large (up to 28.7%) and depend on the definition of the aggregate service.
The paper analyzes a multi-item inventory system, using independent (R,Q) policies. The aim is to minimize the average stock level while keeping a weighted (across items) fill rate service level at a given target. The paper explores whether the optimal order sizes and the optimal safety factors are aligned with the ABC classification. Our results show that A items should be ordered more frequently followed by B items and C items. Concerning the optimal safety factors, our results depend on the weights applied in the specification of the weighted service level. If all items have equal weight, A items should have the lowest safety factors followed by B and C items. If the weights are the demand rates, the ranking of the safety factors follows the ratios between the demand rate and the unit purchase price, and the higher this ratio is, the higher is the optimal safety factor. However, this ranking is completely aligned with the ABC classification given that the demands are transformed into monetary units.
Following the guaranteed service approach (GSA), several studies have investigated the interaction between production and inventory decisions in multistage supply systems and developed efficient algorithms to solve the large-scale optimization problems that emerge. These works have largely ignored limited inventory budgets and their effect on production and inventory decisions. In reality, however, firms tend to limit the amount of capital tied-up in inventories, and there is usually a limited amount of storage space at a warehouse or a retailer. This study investigates the problem of production capacity and safety stock placement with both limited capacity and inventory budgets in general acyclic supply chains. This problem allocates capacity to production stages and sets inventory targets at logistics stages, with the objective to minimize the expected total supply chain cost while meeting a target customer service level. The present paper contributes to the GSA literature in several ways. First, we compare guaranteed and chance-constraint approaches to model limited inventory budgets and analyze their effect on safety stock placement. Second, we present two new equivalent formulations of the production capacity and safety stock placement problem. Solving these new models using a successive piecewise linear approximation algorithm outperforms existing solution procedures in terms of solution quality and time, in both cases of infinite and finite inventory budgets. Third, taking advantage of the structure of these formulations, we develop a two-phase heuristic, which finds optimal or near-optimal solutions and greatly improves CPU times. Finally, our numerical experiments show that inventory budgets affect production capacity and safety stock placement decisions, increasing both work in process (WIP) and safety stock levels.
Inventory control can be broadly defined as "the activity of checking a shop’s stock." However, a more focused definition takes into account the more science-based, methodical practice of not only verifying a business' inventory but also focusing on the many related facets of inventory management "within an organisation to meet the demand placed upon that business economically. “Other facets of inventory control include supply chain management, production control, financial flexibility, and customer satisfaction. Chapter Outline: After going through this chapter students will be able to understand about • Cost Factors In Inventory Control • Inventory Carrying Cost • Ordering Cost • EOQ, Lead Time • Safety Stock • Reorder Level • Minimum Level, Max. Level • Types of Inventory Control Systems • Perpetual Inventory Control System • ABC Method Etc. • Valuation Of Materials Issued From Store • FIFO, LIFO, etc.
Inventory classification is a managerial method utilized to group items that share predetermined characteristics, with the intent of assigning group-specific controls and monitoring mechanisms to each established item group. In this paper, we develop a performance-based inventory classification (PBIC) method that finds a grouping solution for a multi-item, multi-echelon inventory system controlled by continuous review. We argue that instead of grouping items based on similarities in unit cost, demand rate, or leadtime, the most effective strategy is to group items based on the information contained in their control policy values and their performance-related parameter values. We introduce a new policy-driven approach for establishing the classification criteria used to group items. We also adopt a ranking method to control the multi-dimensionality of multi-echelon systems in order to determine a one-dimension score. To group items, we improve the Pareto-based (ABC) solution by developing a search-based partitioning solution, utilizing a novel aggregation process. Our findings indicate that the PBIC method significantly outperforms alternative classification methods. Also, the empirical results show that there is a negligible gap between the performance of the PBIC and the optimal (complete enumeration) grouping solution. Finally, we discuss our work in the context of managerial implications highlighting the use of classification for problem aggregation and size reduction, when managers need to perform efficient, yet extensive, and dependable what-if analyses related to inventory management.
In order to efficiently reduce the high inventory cost of discrete manufacturing firms, which is caused by the large production scale, complex processes, and varieties of materials, this article presents a two-stage decision framework integrating multi-index material classification and inventory control policy. In the first stage, a multi-index material classification method based on analytic hierarchy process-information entropy is implemented to categorize materials in production process into three classes: class A (i.e., strategic materials), class B (i.e., bottleneck materials), and class C (i.e., general materials). In the following stage, based on the results of material classification, an order quantity forecasting model for strategic materials based on ( Q , s ) is constructed with the objective to minimize the total inventory cost over a planning horizon. Then, a hybrid Artificial Bee Colony-Chaos (ABC-Chaos) algorithm is employed to solve the proposed model. To be specific, the chaotic local search strategy is introduced to help local extreme point escape from bondage in the random search phase of scout bee. Finally, a real-world case study from a typical foundry enterprise is illustrated to demonstrate the applicability and feasibility of the proposed decision framework. The experimental results show that the proposed hybrid ABC-chaos algorithm performs better than the other algorithms.
This book presents the proceedings of The EAI International Conference on Computer Science: Applications in Engineering and Health Services (COMPSE 2019). The conference highlighted the latest research innovations and applications of algorithms designed for optimization applications within the fields of Science, Computer Science, Engineering, Information Technology, Management, Finance and Economics and Health Systems. Focusing on a variety of methods and systems as well as practical examples, this conference is a significant resource for post graduate-level students, decision makers, and researchers in both public and private sectors who are seeking research-based methods for modelling uncertain and unpredictable real-world problems.
Healthcare inventory management is a complex task which contains critical decision phases. One of the efficient ways of healthcare inventory management is to classify inventory items into predefined categories in terms of their significant features. This chapter proposes a guideline to healthcare decision makers to implement appropriate inventory control methods. The proposed method combines Fuzzy AHP (Analytical Hierarchy Process), TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) and ABC (Always Better Control) analysis methods to determine the priority of inventory items. The corresponding method, which takes into account multiple criteria in the classification of inventory items, cope with the limits of the classical ABC method. It also helps to reduce the uncertainty in the inventory classification problem as the proposed method is based on the fuzzy logic approach. A real-life case study is conducted in a hospital laboratory to test the proposed method.
DPP (direct product profitability) has been heralded as one of the more important advances in supermarket shelf management, yet its acceptance by managers in the industry has been slow. Not only is DPP complex and expensive to calculate, but some question exists about whether decisions based on DPP are different from those based on traditional criteria such as gross margin and movement. A data base of nine dry-grocery categories is used here to compare DPP with other SKU indices. DPP is shown to lead to significantly different rankings in some categories, but not all. A Merchandising Attractiveness Index (MAl) is devised, based on a linear regression of gross margin, dollar sales, unit sales, and shelf area occupied, which yields predicted values of DPP that are virtually identical to DPP in the nine categories studied. This MAl may be a far less expensive way to implement the basic concept of DPP. It may also be more transparent to managers for basic merchandising decisions (price, space allocation, promotions).
The problem of grouping the many items in stock into a few groups with the provision of a common order cycle or common order quantity per group is modelled as a dynamic program. It is shown that bY a simple reorganization of the stock items, the computation time of the dynamic program can be reduced to a manageable size. Further the order cycle grouping is shown to be, usually, superior to the order quantity grouping scheme. Also, the composition of the order cycle grouping is found to be remarkably close to that of the well known A/B/C system of stock control therby giving theoretical credence to that system.
A distance-based multi-criteria consensus framework on the concepts of ideal and negative-ideal solutions is presented for the ABC analysis of inventory items. This article demonstrates a way of classifying inventory items using the TOPSIS (‘Technique for Order Preference by Similarity to Ideal Solution’) model. The methodology has been applied in a pharmaceutical company located in the heart of Kolkata, India. The technique takes into account various conflicting criteria having incommensurable units of measurement. Unit cost, lead time, consumption rate, perishability of items and cost of storing of raw materials have been considered for the case study. By using TOPSIS, the items are ranked in categories A, B and C. The suitability, practicability and effectiveness of the TOPSIS method used in ABC classification have been judged using the analysis of variance (ANOVA) technique. A simulation model has been used to compare the proposed model with that of the traditional ABC classification technique.
Many production/inventory systems contain thousands of stock keeping units (SKUs). In general, it is not computationally (or conceptually) feasible to consider every one of these items individually in the development of control polices and strategies. Our objective here is to develop a methodology for defining groups to support strategic planning for the operations function. Accordingly, such groups should take into consideration all product characteristics which have a significant impact on the particular operations management problem of interest. These characteristics can include many of the attributes which are used in other functional groupings and will most certainly go beyond the cost and volume attributes used in ABC analysis. The ORG methodology is based on statistical clustering and can utilize a full range of operationally significant item attributes. It considers both statistical measures of discrimination and the operational consequences associated with implementing policies derived on the basis of group membership. The main departure of this analysis from earlier work is: 1) the approach can handle any combination of item attribute information that is important for strategy purposes, 2) management's interest in defining groups on the basis of operational factors can be accommodated, 3) statistical discrimination is considered directly, 4) group definition reflects the performance of management policies which are based (in part) on group membership, and 5) the method can be applied successfully to systems with a large number of SKUs. The specific application which motivated development of the ORG methodology was an analysis of distribution strategy for the service parts division of a major automobile manufacturer. The manufacturer was interested in developing optimal inventory stocking policies, which took into account the complexities of its multiechelon distribution network, supplier relationships and customer service targets for each market segment. This manufacturer stocked over 300,000 part numbers in an extensive network with approximately 50 distribution centers and thousands of dealer locations (i.e., 1.5 million SKU/ location combinations). The results of this application indicated that the advantage of using operationally relevant data for grouping and for defining generic, group‐based policies for controlling inventory can be substantial. The ORG methodology can be of value to operations managers in industries with a large number of diverse items.
At various intervals during the years 1952-1953, the author, as a Fellow of the American Management Association, served as leader of those units of AMA's Management Course which are devoted to Planning and Controlling. During this period he was in close contact with several hundred industrial executives, all studying the problems of planning and controlling. In preparation for these meetings an annotated outline of the subject was developed, as well as an assortment of "case" material. However, as the series of meetings progressed, the discussions began to generate a list of "universals" of Planning and Controlling. These ''universals," which are set forth and discussed in this paper, appear to be applicable to any problem in Management Planning and Controlling, irrespective of the particular product, process, or function involved. Their universal character appears to hold without exception. Thereby they represent truly transferable skills of management. FIRST LET US CLARIFY what we mean by a "universal" of planning and controlling. As used in the AMA Management Course, and for the purposes of this discussion, the term may be defined as "any principle which is valid in planning or controlling – no matter what the company, the product, the process or the function.
Many production/inventory systems contain thousands of stock keeping units (SKUs). In general, it is not computationally (or conceptually) feasible to consider every one of these items individually in the development of control polices and strategies. Our objective here is to develop a methodology for defining groups to support strategic planning for the operations function. Accordingly, such groups should take into consideration all product characteristics which have a significant impact on the particular operations management problem of interest. These characteristics can include many of the attributes which are used in other functional groupings and will most certainly go beyond the cost and volume attributes used in ABC analysis. The ORG methodology is based on statistical clustering and can utilize a full range of operationally significant item attributes. It considers both statistical measures of discrimination and the operational consequences associated with implementing policies derived on the basis of group membership. The main departure of this analysis from earlier work is: 1) the approach can handle any combination of item attribute information that is important for strategy purposes, 2) management's interest in defining groups on the basis of operational factors can be accommodated, 3) statistical discrimination is considered directly, 4) group definition reflects the performance of management policies which are based (in part) on group membership, and 5) the method can be applied successfully to systems with a large number of SKUs. The specific application which motivated development of the ORG methodology was an analysis of distribution strategy for the service parts division of a major automobile manufacturer. The manufacturer was interested in developing optimal inventory stocking policies, which took into account the complexities of its multiechelon distribution network, supplier relationships and customer service targets for each market segment. This manufacturer stocked over 300,000 part numbers in an extensive network with approximately 50 distribution centers and thousands of dealer locations (i.e., 1.5 million SKU/ location combinations). The results of this application indicated that the advantage of using operationally relevant data for grouping and for defining generic, group‐based policies for controlling inventory can be substantial. The ORG methodology can be of value to operations managers in industries with a large number of diverse items.
Prioritising items for management attention has been advocated in operations management for a long time, normally using ABC analysis (inventory control). This focuses attention on the “A” category items to maximise managerial effectiveness. Empirical evidence shows that this is a reasonable rule for allocating scarce resource-management time but presents difficulties when the manager has to take more than one important dimension of a situation into account. A joint criteria matrix is put forward within the ABC framework and an industrial application given. The joint criteria matrix has practical utility provided ranking on some scale of measurement is realistic. The appropriate number of categories must be defined by the user. Combining criteria will probably require different analytical approaches, e.g. goal programming or heuristic approaches. Utilisation of the matrix by managers can provide an explicit method for taking a range of criteria into account in the development of inventory policies.
Presents a multicriteria approach to the ABC classification problem in inventory control. The proposed method, based on Saaty's Analytic Hierarchy Process, rates items on both qualitative and quantitative criteria. Demonstrates the model through an example, using real data from the maintenance department stock room of a pharmaceutical company. A series of simulation experiments show how the resulting classification can benefit inventory control in this company.
Purpose The article offers a radically different and truly strategic approach to SKU optimization. Design/methodology/approach The author has put together an innovative approached base on recycling and reapplying tested methodology – such as customer preferences and customer switching behavior – to achieve the removal of unneeded products from the portfolio. Findings This new methodology holds the prospect for a portfolio transformation, brand enhancement and significant cost reduction Practical implications Designed to eliminate high‐volume but unnecessary SKUs, this approach is based on three principles: Only products that score well with consumers are keepers; and those that don't score highly can be targeted for elimination. Identify which SKUs serve unique channels. Conduct a failed‐product elimination process. Originality/value This is the first truly strategic approach to ending SKU proliferation, a cause of substantial wasted resources.
Purpose For many firms the problems of manufacturing, marketing and distributing a complex product line persist, and it is driving up costs in an economy where cutting costs is essential to survival. This paper aims to promote the innovative concept of “Smart Complexity.” Design/methodology/approach This paper explains how a firm can adopt this new complexity management concept. It is an approach that challenges the notion that every new product variant drives growth. Findings Recently, a company that adopted this approach increased margins by 1 to 3 percent and set the foundation for ongoing improvements in profitability. Practical implications This four‐pronged approach to complexity management starts with consumer research to find the right level of variety. It adds richer SKU‐based data on costs across each step of a newly transparent value chain. It brings this data to a cross‐functional, integrated decision process. Finally, it implements process changes to ensure complexity is governed and managed over time. Originality/value The leadership lesson: desirable complexity drives consumer buying decisions. Undesirable complexity unduly complicates internal processes without making a whit of difference to the consumer. The new concept of Smart Complexity distinguishes between the two.
The problem of optimally coordinating the replenishments of the many items in stock with one another is dealt with in this article. Specifically, it considers this coordination based on classifying the items into a few groups with common order cycles for all the items in a particular group. Assuming that the cumulative distribution by value of the inventory can be characterized by a Pareto function of the type f(n) = n/(an + b), (a, b > 0), it establishes that the optimal boundaries of the groups can be obtained as closed-form expressions by solving a system of simultaneous equations. The composition of the successive groups thus obtained is found to equipartition the total cost and to follow geometric sequences in relation to the number of items, the value of items, and the lengths of the order cycles. Graphs have been proposed to aid the implementation of the grouping scheme. Simple iterative schemes are outlined within the framework of the Pareto function to handle other relevant costs.
ABC inventory classifications are widely used in practice, with demand value and demand volume as the most common ranking criteria. The standard approach in ABC applications is to set the same service level for all stock keeping units (SKUs) in a class. In this paper, we show (for three large real life datasets) that the application of both demand value and demand volume as ABC ranking criteria, with fixed service levels per class, leads to solutions that are far from cost optimal. An alternative criterion proposed by Zhang et al. performs much better, but is still considerably outperformed by a new criterion proposed in this paper. The new criterion is also more general in that it can take criticality of SKUs into account. Managerial insights are obtained into what class should have the highest/lowest service level, a topic that has been disputed in the literature.
The work described in the literature on inventory and supply chain management has advanced greatly over the last few decades and now covers many aspects and challenges of applied supply chain management. In this paper we describe an approach that combines many of these academic aspects in a practical way to manage the spare parts logistics at a German automobile manufacturer. The basic problem is a single-echelon inventory problem with a system-wide service-level requirement and the possibility of issuing emergency orders. There exist two related optimization problems: One is to maximize the system-wide service level under the constraint of a given budget; the other is to minimize the budget for a given system-wide service level. The most important requirements and constraints considered are a detailed cost structure, different packaging sizes, capacity constraints, several storage zones, the decision whether or not to stock a product, stochastic lead times, highly sporadic demands, and the stability of the optimization result over time. Our approach has been implemented successfully in an automotive spare parts planning environment. The complete solution package integrates into the mySAP ERP®, the SAP Enterprise Resource Planning system, and APO 4.0, the SAP Advanced Planning and Optimization system. A detailed description of the model is given and results are presented.
In this paper we presented an extended version of the Ng-modelg [W.L. Ng, A simple classifier for multiple criteria ABC analysis, European Journal of Operational Research 177 (2007) 344–353] for multi-criteria inventory classification. The proposed model is a nonlinear programming model which determines a common set of weights for all the items. Our model not only incorporates multiple criteria for ABC classification, but also maintains the effects of weights in the final solution, an improvement over the model proposed by Ng. An illustrative example is presented to compare our model and the Ng-model.
This paper presents artificial neural networks (ANNs) for ABC classification of stock keeping units (SKUs) in a pharmaceutical company. Two learning methods were utilized in the ANNs, namely back propagation (BP) and genetic algorithms (GA). The reliability of the models was tested by comparing their classification ability with two data sets (a hold-out sample and an external data set). Furthermore, the ANN models were compared with the multiple discriminate analysis (MDA) technique. The results showed that both ANN models had higher predictive accuracy than MDA. The results also indicate that there was no significant difference between the two learning methods used to develop the ANN.
In ABC analysis, a well-known inventory planning and control technique, stock-keeping units (SKUs) are sorted into three categories. Traditionally, the sorting is based solely on annual dollar usage. The aim of this paper is to introduce a case-based multiple-criteria ABC analysis that improves on this approach by accounting for additional criteria, such as lead time and criticality of SKUs, thereby providing more managerial flexibility. Using decisions from cases as input, preferences over alternatives are represented intuitively using weighted Euclidean distances which can be easily understood by a decision maker. Then a quadratic optimization program finds optimal classification thresholds. This system of multiple criteria decision aid is demonstrated using an illustrative case study.
One of the application areas of genetic algorithms is parameter optimization. This paper addresses the problem of optimizing a set of parameters that represent the weights of criteria, where the sum of all weights is 1. A chromosome represents the values of the weights, possibly along with some cut-off points. A new crossover operation, called continuous uniform crossover, is proposed, such that it produces valid chromosomes given that the parent chromosomes are valid. The new crossover technique is applied to the problem of multicriteria inventory classification. The results are compared with the classical inventory classification technique using the Analytical Hierarchy Process.
This article presents the results of applying multicriteria ABC analysis to maintenance inventories. A large service organization and a consumer goods manufacturer participated in the study. The managers in both organizations used cost and noncost criteria for developing the ABC categories for inventory management. The study shows that managers can develop noncost criteria and classify the inventory items in ways that combine the criteria types. Specific policies were defined for managing the items in the industrial firm. Once the benefits of the methodology were demonstrated, a year-long program for implementing the system was developed. The project is estimated to cost less than 10 to 15% of the available storeroom clerk manhours and provide substantially greater benefits.
Inventory classification using ABC analysis is one of the most widely employed techniques in organizations. The need to consider multiple criteria for inventory classification has been stressed in the literature. A simple classification scheme is proposed in this paper using weighed linear optimization. The methodology is illustrated using an example.
Inventory classification is an effective way to manage a large number of items. As a basic methodology, ABC analysis is widely used for classification. The traditional ABC classification is based on only a single criterion. However, it is generally recognized that multiple criteria should be considered in practice. A peer-estimation approach is proposed in this paper for multi-criteria inventory classification (MCIC). The proposed approach determines two common sets of criteria weights and aggregates the resulting two performance scores in the most favorable and least favorable senses for each item without any subjectivity. Comparisons of the proposed approach with some previous methods are illustrated based on a classical MCIC problem. It is shown that our proposed approach can provide a more reasonable and comprehensive performance index for MCIC.
In order to efficiently control the inventory items and determine the suitable ordering policies for them, multi-criteria ABC inventory classification, which is one of the most common techniques of production and inventory control, is used. In this classification, other criteria in addition to annual dollar usage are taken into account and then the items are classified in three classes with different ordering policies, based on their priority. In this paper, we propose an integrated fuzzy analytic hierarchy process-data envelopment analysis (FAHP-DEA) for multiple criteria ABC inventory classification. The proposed FAHP–DEA methodology uses the FAHP to determine the weights of criteria, linguistic terms such as Very High, High, Medium, Low and Very Low to assess each item under each criterion, the data envelopment analysis (DEA) method to determine the values of the linguistic terms, and the simple additive weighting (SAW) method to aggregate item scores under different criteria into an overall score for each item. The integrated FAHP–DEA methodology is illustrated using a real case study.
In some stockholding situations, only a small number of lot sizes is feasible or even desirable. Rules are defined for obtaining the optimal ratios between the lot sizes and for determining the range of requirements appropriate to each lot size. In particular, results have been tabulated for a log-normal distribution of requirements. It is found that with only a small number of lot sizes there is a very small increase in cost above the theoretical minimum. It is shown how the results can be simplified in the design of re-ordering systems with negligible increase in cost. An example is given which shows how the grouped items can also be ordered with simple frequencies.
This paper presents a particle swarm optimization approach for inventory classification problems where inventory items are classified based on a specific objective or multiple objectives, such as minimizing costs, maximizing inventory turnover ratios, and maximizing inventory correlation. In addition, this approach determines the best number of inventory classes and how items should be categorized for the desired objectives at the same time. Experiments are employed to determine the best combination of algorithm parameter values. Extensive numerical studies are conducted and results are compared to other known classification methods. The performance of the algorithm on a practical case is also presented.
To have an efficient control of a huge amount of inventory items, traditional approach is to classify the inventory into different groups. Different inventory control policies can then applied to different groups. The well-known ABC classification is simple-to-understand and easy-to-use. However, ABC analysis is based on only single measurement such as annual dollar usage. It has been recognized that other criteria are also important in inventory classification.In the paper, we propose a simple model for multiple criteria inventory classification. The model converts all criteria measures of an inventory item into a scalar score. The classification based on the calculated scores using ABC principle is then applied. With proper transformation, we can obtain the scores of inventory items without a linear optimizer. The model can be widely applied to inventory managers with minimal backgrounds in optimization.
Business Logistics/Supply Chain Management. Pearson Education
- R Ballou
Ballou, R., 2004. Business Logistics/Supply Chain Management. Pearson Education, Upper Saddle River, NJ, pp. 349-355.
Universals in Management Planning and Control. Management Review. 1954. American Management Association
- J Juran
Juran, J., 1954. Universals in Management Planning and Control. Management Review. 1954. American Management Association, New York, NY, pp. 748-761 (November).
English Translation) Manual of Political Economy
- V Pareto
Pareto, V., 1971. (English Translation) Manual of Political Economy. AM Kelley, New York.
