Search

All intensively studied and widely applied inventory control policies satisfy demand in accordance with the First-Come-First-Served (FCFS) rule, whether this demand is in backorder or not. Interestingly, this rule is sub-optimal when the fill-rate is constrained or when the backorder cost structure includes fixed costs per backorder and costs per backorder per unit time. In this paper we study the degree of suboptimality of the FCFS rule for inventory systems controlled by the well-known base-stock policy. As an alternative to the FCFS rule, we propose and analyze a class of generalized base-stock policies that reserve some maximum number of items in stock for future demands, even if backorders exist. Our analytic results and numerical investigations show that such alternative stock reservation policies are indeed very simple and considerably improve either the fillrate or reduce the total cost, without having much effect on the backorder level. (C) 2017 Elsevier Ltd. All rights reserved.

International audience; Spare parts are often associated with intermittent demand patterns that render their forecasting a challenging task. Forecasting of spare parts demand has been researched through both parametric and non-parametric approaches. However, little has been contributed in this area from a Bayesian perspective, and most of such research is built around the Poisson demand distributional assumption. However, the Poisson distribution is known to have certain limitations and, further, empirical evidence on the inventory performance of Bayesian methods is lacking. In this paper, we propose a new Bayesian method based on compound Poisson distributions. The proposed method is compared to the Poisson-based Bayesian method with a Gamma prior distribution as well as to a parametric frequentist method and to a non-parametric one. A numerical investigation (on 7400 theoretically generated series) is complemented by an empirical assessment on demand data from about 3000 stock keeping units in the automotive sector to analyse the performance of the four forecasting methods. We find that both Bayesian methods outperform the other methods with a higher inventory efficiency reported for the Poisson Bayesian method with a Gamma prior. This outperformance increases for higher demand variability. From a practical perspective, the outperformance of the proposed method is associated with some added complexity. We also find that the performance of the non-parametric method improves for longer lead-times and higher demand variability when compared to the parametric one.

The demand for industrial plant spare parts is driven, at least in part, by maintenance requirements. It is therefore important to jointly optimise planned maintenance and the associated spare parts inventory using the most appropriate maintenance and replenishment policies. In this simulation-based study, we address this challenge in the context of the random failure of parts in service and the replacement of defective parts at inspections of period T. Inspections are modelled using the delay-time concept. A number of simultaneous periodic review and continuous review replenishment policies are compared. A paper making plant provides a real context for the presentation of our ideas. We survey practitioners working with such plant to collect real data that inform the values of parameters in the models. Our simulation results indicate that a periodic review policy with ordering that is twice as frequent as inspection is cost optimal in the context of the plant that we study. For the purpose of comparison, we also present and discuss the characteristics of the various policies considered.

The Repair Kit Problem (RKP) concerns the determination of a set of items taken by a service engineer to perform on-site product support. Such a set is called a kit. Models developed in the literature have always ignored the lead times associated with delivering items to replenish the kit, thereby limiting the practical relevance of the proposed solutions. Motivated by a real life case, we develop a model with positive lead times to control the replenishment quantities of the items in the kit, and study the performance of (s, S) policies under a service objective. The choice for (s, S) policies is made in order to accommodate fixed ordering costs. We present a method to calculate job fill rates with exact expressions, and discuss a heuristic approach to optimize the reorder level and order-up-to level for each item in the kit. The empirical utility of the model is assessed on real world data from an equipment manufacturer and useful insights are offered to after-sales managers.

Information sharing has been identified, in the academic literature, as one of the most important levers to mitigate the bullwhip effect in supply chains. A highly-cited article on the bullwhip effect has claimed that the percentage inventory reduction resulting from information sharing in a two level supply chain, when the downstream demand is autoregressive of order one, is an increasing function of the autoregressive parameter of the demand. In this paper we show that this is true only for a certain range of the autoregressive parameter and there is a maximum value beyond which the bullwhip ratio at the upstream stage is reduced and the percentage inventory reduction resulting from information sharing decreases towards zero. We also show that this maximum value of the autoregressive parameter can be as high as 0.7 which represents a common value that may be encountered in many practical contexts. This means that large benefits of information sharing cannot be assumed for those Stock Keeping Units (SKUs) with highly positively auto-correlated demand. Instead, equally careful analysis is needed for these items as for those SKUs with less strongly auto-correlated demand.

Physical inventories constitute a significant proportion of companies’ investments in today's competitive environment. The trade-off between customer service levels and inventory reserves is addressed in practice by statistical inventory software solutions; given the tremendous number of Stock Keeping Units (SKUs) that contemporary organizations deal with, such solutions are fully automated. However, empirical evidence suggests that managers habitually judgementally adjust the output of such solutions, such as replenishment orders or re-order levels. This research is concerned with the value being added, or not, when statistically derived inventory related decisions (Order-Up-To, OUT, levels in particular) are judgementally adjusted. We aim at developing our current understanding on the effects of incorporating human judgement into inventory decisions; to our knowledge such effects do not appear to have been studied empirically before and this is the first endeavour to do so. A number of research questions are examined and a simulation experiment is performed, using an extended database of approximately 1,800 SKUs from the electronics industry, in order to evaluate human judgement effects. The linkage between adjustments and their justification is also evaluated; given the apparent lack of comprehensive empirical evidence in this area, including the field of demand forecasting, this is a contribution in its own right. Insights are offered to academics, to facilitate further research in this area, practitioners, to enable more constructive intervention into statistical inventory solutions, and software developers, to consider the interface with human decision makers.

Intermittent demand items dominate service and repair inventories in many industries and they are known to be the source of dramatic inefficiencies in the defence sector. However, research in forecasting such items has been limited. Previous work in this area has been developed upon the assumption of a Bernoulli or a Poisson demand arrival process. Nevertheless, intermittent demand patterns may often deviate from the memory-less assumption. In this work we extend analytically previous important results to model intermittent demand based on a compound Erlang process, and we provide a comprehensive categorisation scheme to be used for forecasting purposes. In a numerical investigation we assess the benefit of departing from the memory-less assumption and we provide insights into how the degree of determinism inherent in the process affects forecast accuracy. Operationalised suggestions are offered to managers and software manufacturers dealing with intermittent demand items.

International audience; One of the implicit assumptions considered in the majority of investigations performed in the area of inventory management is that the physical flow of products in an inventory system is free from defects. The same is hypothesized for the associated information flow. However, various factors may create a difference between the actual physical and information system (IS) flows and perturb their synchronized evolution. The implications of such a discrepancy are particularly prevalent in contemporary supply chains, where sales commitments are based on IS records only. In this paper we model and analyze the impact of inventory inaccuracies on supply chain performance. We first provide an overview of potential errors that may occur within an inventory system and we then propose a general framework to model the impact of inaccuracy errors. Potential errors in both the physical and/or the IS record inventories are considered and optimal analytical solutions are provided for both centralized and decentralized (coordinated and uncoordinated) supply chains for three plausible scenarios: inaccuracy errors are ignored; errors are estimated; the utilization of a Radio Frequency Identification (RFID) technology enables the reduction of the relevant errors. The performance improvements enabled by the availability of error related information and the RFID technology are assessed and managerial insights are provided. The paper concludes with the implications of our work for supply chain design as well as with an agenda for further research in this area.

Despite the evidence of benefits of information sharing, there are many supply chains that are unable to share information due to constraints such as compatibility of information systems, information quality, trust and confidentiality. Furthermore, a steady stream of papers has explored a phenomenon known as Downstream Demand Inference (DDI) where the upstream member in the supply chain can infer the downstream demand without the need of a formal information sharing mechanism. Recent research has shown that under a more practical setting, with less restrictive assumptions, DDI is not possible with optimal forecasting methods or Single Exponential Smoothing but is possible when supply chains use a Simple Moving Average (SMA) method. In this paper, we propose a simple DDI strategy based on SMA for supply chains where information cannot be shared. This strategy allows the upstream member in the supply chain to infer the consumer demand mathematically rather than sharing this. We compare the DDI strategy with the existing No Information Sharing (NIS) strategy. The comparison is made analytically which enables to show that using the DDI strategy reduces the MSE in the supply chains.

The importance of replication has been recognised across many scientific disciplines. Reproducibility is a necessary condition for replicability, because an inability to reproduce results implies that the methods have not been specified sufficiently, thus precluding replication. This paper describes how two independent teams of researchers attempted to reproduce the empirical findings of an important paper, ‘‘Shrinkage estimators of time series seasonal factors and their effect on forecasting accuracy’’ (Miller & Williams, 2003). The two teams proceeded systematically, reporting results both before and after receiving clarifications from the authors of the original study. The teams were able to approximately reproduce each other’s results, but not those of Miller and Williams. These discrepancies led to differences in the conclusions as to the conditions under which seasonal damping outperforms classical decomposition. The paper specifies the forecasting methods employed using a flowchart. It is argued that this approach to method documentation is complementary to the provision of computer code, as it is accessible to a broader audience of forecasting\ud practitioners and researchers. The significance of this research lies not only in its lessons for seasonal forecasting but also, more generally, in its approach to the reproduction of\ud forecasting research.

International audience; This paper is concerned with analysing and modelling the effects of judgmental adjustments to replenishment order quantities. Judgmentally adjusting replenishment quantities suggested by specialized (statistical) software packages is the norm in industry. Yet, to date, no studies have attempted to either analytically model this situation or practically characterize its implications in terms of ‘learning’. We consider a newsvendor setting where information available to managers is reflected in the form of a signal that may or may not be correct, and which may or may not be trusted. We show the analytical equivalence of adjusting an order quantity and deriving an entirely new one in light of a necessary update of the estimated demand distribution. Further, we assess the system's behaviour through a simulation experiment on theoretically generated data and we study how to foster learning to efficiently utilize managerial information. Judgmental adjustments are found to be beneficial even when the probability of a correct signal is not known. More generally, some interesting insights emerge into the practice of judgmentally adjusting order quantities. © 2017 Elsevier B.V.

The fill rate is the most widely applied service level measure in industry and yet there is minimal advice available on how it should be differentiated on an individual Stock Keeping Unit (SKU) basis given that there is an overall system target service level. The typical approach utilized in practice, and suggested in academic textbooks, is to set the individual service levels equal to the targeted performance required across an entire stock base or a certain class of SKUs (e.g., in ABC classification). In this paper it is argued that this approach is far from optimal and a simple methodology is proposed that is shown (on real life datasets) to be associated with reductions in stock investments. In addition, the new approach is intuitive, very easy to implement and thus highly likely to be positively received by practitioners and software manufacturers. (C)2016 Elsevier B.V. All rights reserved.

Earlier research on the effects of nonoverlapping temporal aggregation on demand forecasting showed the benefits associated with such an approach under a stationary AR(1) or MA(1) processes for decision making conducted at the disaggregate level. The first objective of this note is to extend those important results by considering a more general underlying demand process. The second objective is to assess the conditions under which aggregation may be a preferable approach for improving decision making at the aggregate level as well. We confirm the validity of previous results under more general conditions, and we show the increased benefit resulting from forecasting by temporal aggregation at lower frequency time units.

Demand forecasting performance is subject to the uncertainty underlying the time series an organization is dealing with. There are many approaches that may be used to reduce uncertainty and thus to improve forecasting performance. One intuitively appealing such approach is to aggregate demand in lower-frequency “time buckets.” The approach under concern is termed to as temporal aggregation, and in this article, we investigate its impact on forecasting performance. We assume that the nonaggregated demand follows either a moving average process of order one or a first-order autoregressive process and a single exponential smoothing (SES) procedure is used to forecast demand. These demand processes are often encountered in practice and SES is one of the standard estimators used in industry. Theoretical mean-squared error expressions are derived for the aggregated and nonaggregated demand to contrast the relevant forecasting performances. The theoretical analysis is supported by an extensive numerical investigation and experimentation with an empirical dataset. The results indicate that performance improvements achieved through the aggregation approach are a function of the aggregation level, the smoothing constant, and the process parameters. Valuable insights are offered to practitioners and the article closes with an agenda for further research in this area.

Different spare parts are associated with different underlying demand patterns, which in turn require different forecasting methods. Consequently, there is a need to categorise stock keeping units (SKUs) and apply the most appropriate methods in each category. For intermittent demands, Croston's method (CRO) is currently regarded as the standard method used in industry to forecast the relevant inventory requirements; this is despite the bias associated with Croston's estimates. A bias adjusted modification to CRO (Syntetos–Boylan Approximation, SBA) has been shown in a number of empirical studies to perform very well and be associated with a very ‘robust’ behaviour. In a 2005 article, entitled ‘On the categorisation of demand patterns’ published by the Journal of the Operational Research Society, Syntetos et al. (2005) suggested a categorisation scheme, which establishes regions of superior forecasting performance between CRO and SBA. The results led to the development of an approximate rule that is expressed in terms of fixed cut-off values for the following two classification criteria: the squared coefficient of variation of the demand sizes and the average inter-demand interval. Kostenko and Hyndman (2006) revisited this issue and suggested an alternative scheme to distinguish between CRO and SBA in order to improve overall forecasting accuracy. Claims were made in terms of the superiority of the proposed approach to the original solution but this issue has never been assessed empirically. This constitutes the main objective of our work. In this paper the above discussed classification solutions are compared by means of experimentation on more than 10,000 SKUs from three different industries. The results enable insights to be gained into the comparative benefits of these approaches. The trade-offs between forecast accuracy and other implementation related considerations are also addressed.

Demand forecasting performance will be challenged by demand dispersion underlying the time series related to the Stock Keeping Units (SKUs). Among the strategies that may be used to reduce the demand dispersion, an intuitively appealing approach is to aggregate demand in lower-frequency 'time buckets'. This paper focuses on the impact of non-overlapping temporal aggregation on the performance of demand forecasting by investigating the mean square error (MSE) before and after aggregation. We assume that the non-aggregated demand follows a first-order autoregressive moving average process [ARMA(1,1)] and a Single Exponential Smoothing (SES) procedure is used to estimate the level of demand. The theoretical analysis shows that the temporal aggregation approach has a great potential to improve the forecasting accuracy. The improvement is a function of process parameters, the aggregation level, and the smoothing constant values. We present some insights into the impact of different control parameters on the performance of each approach. The paper concludes with an agenda for further research in this area.

Practical experience and scientific research show that there is scope for improving the performance of inventory control systems by delaying a replenishment order that is otherwise triggered by generalised and all too often inappropriate assumptions. This paper presents the first analysis of the most commonly used continuous (s, S) policies with delayed ordering for inventory systems with compound demand. We analyse policies with a constant delay for all orders as well as more flexible policies where the delay depends on the order size. For both classes of policies and general demand processes, we derive optimality conditions for the corresponding delays. In a numerical study with Erlang distributed customer inter-arrival times, we compare the cost performance of the optimal policies with no delay, a constant delay and flexible delays. Sensitivity results provide insights into when the benefit of delaying orders is most pronounced, and when applying flexible delays is essential. (C) 2015 Elsevier B.V. and Association of European Operational Research Societies (EURO) within the International Federation of Operational Research Societies (IFORS). All rights reserved.

Demand for spare parts is typically intermittent and forecasting the relevant requirements constitutes a very challenging exercise. Why is the demand for spare parts intermittent and how can we use models developed in maintenance research to forecast such demand? We attempt to answer these questions; we present a novel idea to forecast demand that relies upon the very sources of the demand generation process and we compare it with a well-known time-series method. We conclude that maintenance driven models are associated with a better performance under certain conditions. We also outline an inter-disciplinary agenda for further research in this area.

Intermittent demand patterns are characterised by infrequent demand arrivals coupled with variable demand sizes. Such patterns prevail in many industrial applications, including IT, automotive, aerospace and military. An intuitively appealing strategy to deal with such patterns from a forecasting perspective is to aggregate demand in lower-frequency ‘time buckets’ thereby reducing the presence of zero observations. However, such aggregation may result in losing useful information, as the frequency of observations is reduced. In this paper, we explore the effects of aggregation by investigating 5000 stock keeping units from the Royal Air Force (UK). We are also concerned with the empirical determination of an optimum aggregation level as well as the effects of aggregating demand in time buckets that equal the lead-time length (plus review period). This part of the analysis is of direct relevance to a (periodic) inventory management setting where such cumulative lead-time demand estimates are required. Our study allows insights to be gained into the value of aggregation in an intermittent demand context. The paper concludes with an agenda for further research.

The effect of using estimated (forecast) demand parameters on the performance of an inventory control system is an intriguing and important subject. Recent research has been undertaken on this phenomenon assuming stationary demand data. In this paper we extend the research to non-stationary demands, by means of simulation. The case of a periodic order-up-to-level inventory system is considered and the experimental structure allows us to evaluate in a progressive manner the accumulated effect of using the optimal forecasting method, optimal forecast parameters and correct variance expression procedures. The results allow insights to be gained into operational issues and demonstrate the scope for improving stock control systems.

Intermittent demand occurs at random with many time periods showing no demand at all. Forecasting such demand patterns constitutes a challenging exercise because of the associated dual source of variation (demand intervals and demand sizes). Research in this area has developed rapidly in recent years with new results implemented into supply chain software solutions because of its practical\ud implications. In an inventory context, both the accuracy of the forecasts and their variability (sampling error of the mean) have equal importance in terms of service level achievement and/or inventory cost minimisation. Although the former issue has been studied extensively (mainly building upon Croston’s model, 1972) the latter has been largely ignored. The purpose of this paper is to analyse the most well cited intermittent demand estimation procedures in terms of the variance of their estimates. Detailed derivations are offered along with a discussion of the underlying assumptions. As such, we hope that our contribution may constitute a point of reference for further analytical work in this area as well as\ud facilitate a better understanding of issues related to modelling intermittent demands.

Wholesalers add value to the products they deal with by essentially bringing them closer to the end consumers. In that respect, the effective control of stock levels becomes an important measure of operational performance especially in the context of achieving high customer service levels. In this paper, we address issues pertinent to forecasting and inventory management in a wholesaling environment and discuss the recommendations proposed in such a context in a case study organization. Our findings demonstrate the considerable scope that exists for improving current practices and offers insights into possible managerial issues.

PurposeThis paper aims to substantiate the need for additional research into a more holistic and multidisciplinary approach to managing the supporting supply chains that may also capture contextual information, also pointing out emerging avenues for further scholarly contributions.Design/methodology/approachThe supply chain is viewed from a spare part consumer as well as from a supplier perspective. Key to the discussion is an accurate description of the maintenance demand pattern (MDP) known at the consumer's side as a valuable information source for the entire supply chain.FindingsSolving the spare parts supply chain puzzle exceeds the realms of a single scientific discipline and involves hard and soft sciences. Besides, extending on the quantitative modelling aspects of MDPs, soft modelling and analysis is needed to define cooperative settings in which the supply chain parties can operate effectively.Practical implicationsIn this paper, the authors argue for the sharing of the appropriately balanced combination of quantitative and qualitative information that is currently hidden, or exists in isolation, within supply chains. Debatably, such information sharing may potentially generate substantial benefits for all “players” within a given supply chain.Originality/valueThis contribution is unique in the sense that it provides a most accurate characterization of MDPs based on the proven maintenance concept design theory. In addition, the supply chain problem is analysed in a realistic context, with an open and broad mindset rather than approaching this issue from a single hard science perspective.

A number of research projects have demonstrated that the efficiency of inventory systems does not relate directly to demand forecasting performance, as measured by standard forecasting accuracy measures. When a forecasting method is used as an input to an inventory system, it should therefore always be evaluated with respect to its consequences for stock control through accuracy implications metrics, in addition to its performance on the standard accuracy measures. In this paper we address the issue of judgementally adjusting statistical forecasts for ‘fast’ demand items, and the implications of such interventions in terms of both forecast accuracy and stock control, with the latter being measured through inventory volumes and service levels achieved. We do so using an empirical dataset from the pharmaceutical industry. Our study allows insights to be gained into the combined forecasting and inventory performance of judgemental estimates. It also aims to advance the practice of forecasting competitions by arguing for the consideration of additional (stock control) metrics when such exercises take place in an inventory context.

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.

Forecasting and planning for inventory management has received considerable attention from the Operational Research (OR) community over the last 50 years because of its implications for decision making, both at the strategic level of an organization and at the operational level. Many influential contributions have been made in this area, reflecting different perspectives that have evolved in divergent strands of the literature, namely: system dynamics, control theory and forecasting theory (both statistical and judgemental). Although this pluralism is healthy in terms of knowledge advancement, it also signifies the fragmentation of the OR discipline and the lack of cross-fertilization of ideas to develop more comprehensive approaches towards the resolution of the same issues. In this paper, the relevant literature is reviewed and synthesized to promote some convergence between these different approaches to inventory forecasting and planning. The review concludes with an inter-disciplinary agenda for further research.

Empirical research suggests that quantitatively derived forecasts are very frequently judgementally adjusted. Nevertheless, little work has been conducted to evaluate the performance of these judgemental adjustments in a practical demand/sales context. In addition, the relevant analysis does not distinguish between slow and fast moving items. Currently, there are neither conceptual developments nor empirical evidence on the issue of integrating judgements and statistical forecasts for slow/intermittent demand items. Moreover, no results have ever been reported on the stock control implications of these human judgements. Our work analyses monthly intermittent demand forecasts for the UK branch of a major international pharmaceutical company. The company relies upon a commercially available statistical forecasting system to produce forecasts that are subsequently judgementally adjusted based on marketing intelligence gathered by the company forecasters. The benefits of the intervention are evaluated by comparing the actual sales to system and final forecasts using both forecast accuracy and inventory control (accuracy implication) metrics. Our study allows insights to be gained on potential improvements to intermittent demand forecasting processes and, subsequently, the design effectiveness of forecasting support systems.

PurposeSpare parts have become ubiquitous in modern societies and managing their requirements is an important and challenging task with tremendous cost implications for the organisations that are holding relevant inventories. An important operational issue involved in the management of spare parts is that of categorising the relevant stock keeping units (SKUs) in order to facilitate decision‐making with respect to forecasting and stock control and to enable managers to focus their attention on the most “important” SKUs. This issue has been overlooked in the academic literature although it constitutes a significant opportunity for increasing spare parts availability and/or reducing inventory costs. Moreover, and despite the huge literature developed since the 1970s on issues related to stock control for spare parts, very few studies actually consider empirical solution implementation and with few exceptions, case studies are lacking. Such a case study is described in this paper, the purpose of which is to offer insight into relevant business practices.Design/methodology/approachThe issue of demand categorisation (including forecasting and stock control) for spare parts management is addressed and details reported of a project undertaken by an international business machine manufacturer for the purpose of improving its European spare parts logistics operations. The paper describes the actual intervention within the organisation in question, as well as the empirical benefits and the lessons learned from such a project.FindingsThis paper demonstrates the considerable scope that exists for improving relevant real word practices. It shows that simple well‐informed solutions result in substantial organisational savings.Originality/valueThis paper provides insight into the empirical utilisation of demand categorisation theory for forecasting and stock control and provides some very much needed empirical evidence on pertinent issues. In that respect, it should be of interest to both academics and practitioners.

Demand forecasting and stock control are traditionally examined as independent of each other. Even though this weakness has been highlighted in the academic literature, little empirical work has been conducted on forecasting adjustments addressing the interaction between forecasting and stock control. In this paper, the relevant literature is critically reviewed. Subsequently, the empirical performance of some modifications and adjustments, on slow-moving items, is examined in detail. The data set consists of the individual demand histories of 753 intermittent line items from the Royal Air Force (UK). Overall, the results indicate that there is a scope for improving the performance of parametric stock control systems, and adjustments are indeed required in order to account for the interaction between forecasting and stock control.

A modified Croston procedure to forecast intermittent demand is reviewed. The modified procedure, published in this journal in 2004, consists of a new method for estimating the mean demand and a smoothing method for estimating the variance of the forecasted demand rate. It is found that the smoothed variance estimate is based on an invalid measure of forecast accuracy. Moreover, it is shown that the method of forecasting mean demand produces biased forecasts. The accuracy of this method is assessed, using simulated data and the mean square error measure, and compared with Croston's method and single exponential smoothing. It is found that Croston's method is generally more accurate than its modification, particularly for strongly intermittent series.

A research project recently undertaken by the authors focused on supplier management related issues and the extent to which they are shaped by the organizational culture and structure. The project was conducted in the Hospitality industry and employed an inductive methodological approach in order to collect rich information from six organizations. The organizations represent different structuring models as well as distinct underlying culture-related principles. The findings challenge the assumption regarding beneficial universal applicability of many practices such as ‘Purchasing Consortia’, ‘Service Level Agreements’ and the establishment of long-term relationships. Our analysis also suggests that organizational culture and structure are reflected on the supplier management approaches adopted by the organizations under consideration.

Although intermittent demand items dominate service and repair parts inventories in many industries, research in forecasting such items has been limited. A critical research question is whether one should make point forecasts of the mean and variance of intermittent demand with a simple parametric method such as simple exponential smoothing or else employ some form of bootstrapping to simulate an entire distribution of demand during lead time. The aim of this work is to answer that question by evaluating the effects of forecasting on stock control performance in more than 7,000 demand series. Tradeoffs between inventory investment and customer service show that simple parametric methods perform well, and it is questionable whether bootstrapping is worth the added complexity.

The purpose of this paper is to assess the empirical stock control performance of intermittent demand estimation procedures. The forecasting methods considered are the simple moving average, single exponential smoothing, Croston's method and a new method recently developed by the authors of this paper. We first discuss the nature of the empirical demand data set (3000 stock keeping units) and we specify the stock control model to be used for experimentation purposes. Performance measures are then selected to report customer service level and stock volume differences. The out-of-sample empirical comparison results demonstrate the superior stock control performance of the new intermittent demand forecasting method and enable insights to be gained into the empirical utility of the other estimators.

Intermittent demand appears sporadically, with some time periods showing no demand at all. In this paper, four forecasting methods, Simple Moving Average (SMA, 13 periods), Single Exponential Smoothing (SES), Croston's method, and a new method (based on Croston's approach) recently developed by the authors, are compared on 3000 real intermittent demand data series from the automotive industry. The mean signed and relative geometric root-mean-square errors are shown to meet the theoretical and practical requirements of intermittent demand, as do the Percentage Better and Percentage Best summary statistics based on these measures. These measures are subsequently applied in a simulation experiment. The out-of-sample comparison results indicate superior performance of the new method. In addition, the results show that the mean signed error is not strongly scale dependent and the relative geometric root-mean-square error is a well-behaved accuracy measure for intermittent demand.

Spare parts are known to be associated with intermittent demand patterns and such patterns cause considerable problems with regards to forecasting and stock control due to their compound nature that renders the normality assumption invalid. Compound distributions have been used to model intermittent demand patterns; there is however a lack of theoretical analysis and little relevant empirical evidence in support of these distributions. In this paper, we conduct a detailed empirical investigation on the goodness of fit of various compound Poisson distributions and we develop a distribution-based demand classification scheme the validity of which is also assessed in empirical terms. Our empirical investigation provides evidence in support of certain demand distributions and the work described in this paper should facilitate the task of selecting such distributions in a real world spare parts inventory context. An extensive discussion on parameter estimation related difficulties in this area is also provided.

Intermittent demand items account collectively for considerable proportions of the total stock value of any organization. Forecasting the relevant inventory requirements constitutes a very difficult task and most work in this area is based on Croston's estimator that relies upon exponentially smoothed demand sizes and inter-demand intervals. This method has been shown to be biased and a number of variants have been introduced in the literature, including the recently proposed TSB method that updates the demand probability instead of the demand interval and in doing so reacts faster to decreasing demand. The TSB has been shown theoretically to be unbiased (for all points in time), but its empirical performance has not been investigated yet and this constitutes one of the objectives of our work. More generally, we explore the empirical performance of forecasting methods used in an intermittent demand context, paying particular attention to the effects and implications of the smoothing constant values employed for updating purposes. We do so by means of experimentation on large empirical datasets from the military sector and automotive industry. The results enable insights to be gained into the sensitivity of the various methods' forecasting and stock control performance to the smoothing constant values used. The paper concludes with an agenda for further research.

Forecasting and inventory control for intermittent demand items has been a major problem in the manufacturing and supply environment. Croston (Operational Research Quarterly 23 (1972) 289), proposed a method according to which intermittent demand estimates can be built from constituent events. Croston's method has been reported to be a robust method but has shown more modest benefits in forecasting accuracy than expected. In this research, one of the causes of this unexpected performance has been identified, as a first step towards improving Croston's method. Certain limitations are identified in Croston's approach and a correction in his derivation of the expected estimate of demand per time period is presented. In addition, a modification to his method that gives approximately unbiased demand per period estimates is introduced. All the conclusions are confirmed by means of an extended simulation experiment where Croston's and Revised Croston's methods are compared. The forecasting accuracy comparison corresponds to a situation of an inventory control system employing a re-order interval or product group review.

This paper proposes a hierarchical multi-criteria classification method developed for inventory management purposes and applied in a case study of the spare parts business of a household appliance manufacturer. The classification method is built on the basis of SIX dimensions, resulting in 12 different classes of spare parts, for which differentiated forecasting and inventory policies are proposed and tested. The results of our simulation study demonstrate the reduction of the total logistics costs by about 20% whilst still achieving the specified target service level for each class. Even more importantly, the proposed approach is simple enough to be understood and applied by company managers, thus increasing the probability of its adoption (in the same or similar fashion) in other real world settings.

The standard method to forecast intermittent demand is that by Croston. This method is available in ERP-type solutions such as SAP and specialised forecasting software packages (e.g. Forecast Pro), and often applied in practice. It uses exponential smoothing to separately update the estimated demand size and demand interval whenever a positive demand occurs, and their ratio provides the forecast of demand per period. The Croston method has two important disadvantages. First and foremost, not updating after (many) periods with zero demand renders the method unsuitable for dealing with obsolescence issues. Second, the method is positively biased and this is true for all points in time (i.e. considering the forecasts made at an arbitrary time period) and issue points only (i.e. considering the forecasts following a positive demand occurrence only). The second issue has been addressed in the literature by the proposal of an estimator (Syntetos-Boylan Approximation, SBA) that is approximately unbiased. In this paper, we propose a new method that overcomes both these shortcomings while not adding complexity. Different from the Croston method, the new method is unbiased (for all points in time) and it updates the demand probability instead of the demand interval, doing so in every period. The comparative merits of the new estimator are assessed by means of an extensive simulation experiment. The results indicate its superior performance and enable insights to be gained into the linkage between demand forecasting and obsolescence. (C) 2011 Elsevier B.V. All rights reserved.

We propose a new method for determining order-up-to levels for intermittent demand items in a periodic review system. Contrary to existing methods, we exploit the intermittent character of demand by modelling lead time demand as a compound binomial process. in an extensive numerical study using Royal Air Force (RAF) data, we show that the proposed method is much better than existing methods at approximating target service levels and also improves inventory-service efficiency. Furthermore, the proposed method can be applied for both cost and service oriented systems, and is easy to implement. (C) 2009 Elsevier B.V. All rights reserved.

The periodic (T,s,S) policies have received considerable attention from the academic literature. Determination of the optimal parameters is computationally prohibitive, and a number of heuristic procedures have been put forward. However, these heuristics have never been compared in an extensive empirical study. Such an investigation on 3055 SKUs is carried out in this paper. Our study provides insights into the performance of (T, s, S) heuristics, also in relation to demand forecasting. The results show that Naddor's heuristic is best able to minimize the total cost. However, the normal and power approximations achieve more efficient solutions in that backorder volumes are smaller at the same inventory levels, indicating the potentially superior performance of these methods if the balancing of holding and backorder costs can be improved. The results also show that, for all heuristics, the SBA variant of the Croston forecasting method significantly outperforms Croston as well as Single Exponential Smoothing (SES). (C) 2009 Elsevier B.V. All rights reserved.

In this paper we propose a modification to the standard forecasting, periodic order-up-to-level inventory control\ud approach to dealing with intermittent demand items, when the lead-time length is shorter than the average interdemand\ud interval. In particular, we develop an approach that relies upon the employment of separate estimates of the inter-demand intervals and demand sizes, when demand occurs, directly for stock control purposes rather than first estimating mean demand and then feeding the results in the stock control procedure. The empirical performance of our approach is assessed by means of analysis on a large demand data set from the Royal Air Force (RAF, UK). Our work allows insights to be gained on the interactions between forecasting and stock control as well as on demand categorization-related issues for forecasting and inventory management purposes.