No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Impact of Bias Magnification on Supply Chain Costs: The Mitigating Role of Forecast Sharing
Abstract
The impact of forecast error magnification on supply chain cost has been well documented. Unlike past studies that measure forecast error in terms of forecast standard deviation, our study extends research to consider the impact of forecast bias, and the complex interaction between these variables. Simulating a two-stage supply chain using realistic cost data we test the impact of bias magnification comparing two scenarios: one with forecast sharing between retailer and supplier, and one without. We then corroborate findings via survey data. Results show magnification of forecast bias to have a considerably greater impact on supply chain cost than magnification of forecast standard deviation. Particularly damaging is high bias in the presence of high forecast standard deviation. Forecast sharing is found to mitigate the impact of forecast error, however, primarily at higher levels of forecast standard deviation. At low levels of forecast standard deviation the benefits are not significant suggesting that engaging in such mitigation strategies may be less effective when there is little opportunity for improvement in accuracy. Furthermore, forecast sharing is found to be much less effective against high levels of bias. This is an important finding as managers often deliberately bias their forecasts and underscores the importance of exercising caution even with forecast sharing, particularly for forecasts that have inherently large errors. The findings provide a deeper understanding of the impact of forecast errors, suggest limitations of forecast sharing, and offer implications for research and practice alike.
... However, the prediction methods in this study were limited to moving average (MA), exponential smoothing (ES) and minimum mean square error (MMSE). Sanders and Graman (2016) studied the impact of amplified prediction error on supply chain costs and found that the amplification of prediction bias had a greater impact on supply chain costs than the amplification of prediction standard deviation, and that sharing demand prediction information could mitigate this impact. ...
... The calculation of replenishment decisions depends on the deviation between predicted and actual demand, making this an important gap in the field of research. Building on the findings of Sanders and Graman (2016), our study considers both forecasting bias and variance and directly examines their impact on inventory and firm profits. We compare the relative magnitude of these effects to aid decisionmaking. ...
... While some demand forecasting methods have improved accuracy and bias performance thanks to technologies such as machine learning (Spiliotis et al., 2022), demand forecast errors persist. Sanders and Graman (2016) have shown that amplifying forecasting bias and standard deviation can have a clear adverse impact on supply chain costs, with the effect of the forecasting standard deviation being greater. To address this, this paper develops an inventory model with stochastic production rates of suppliers and demand knowledge updates. ...
Purpose
This study examines the relationship between demand forecasting error and retail inventory management in an uncertain supplier yield context. Replenishment is segmented into off-season and peak-season, with the former characterized by longer lead times and higher supply uncertainty. In contrast, the latter incurs higher acquisition costs but ensures certain supply, with the retailer's purchase volume aligning with the acquired volume. Retailers can replenish in both phases, receiving goods before the sales season. This paper focuses on the impact of the retailer's demand forecasting bias on their sales period profits for both phases.
Design/methodology/approach
This study adopts a data-driven research approach by drawing inspiration from real data provided by a cooperating enterprise to address research problems. Mathematical modeling is employed to solve the problems, and the resulting optimal strategies are tested and validated in real-world scenarios. Furthermore, the applicability of the optimal strategies is enhanced by incorporating numerical simulations under other general distributions.
Findings
The study's findings reveal that a greater disparity between predicted and actual demand distributions can significantly reduce the profits that a retailer-supplier system can earn, with the optimal purchase volume also being affected. Moreover, the paper shows that the mean of the forecasting error has a more substantial impact on system revenue than the variance of the forecasting error. Specifically, the larger the absolute difference between the predicted and actual means, the lower the system revenue. As a result, managers should focus on improving the quality of demand forecasting, especially the accuracy of mean forecasting, when making replenishment decisions.
Practical implications
This study established a two-stage inventory optimization model that simultaneously considers random yield and demand forecast quality, and provides explicit expressions for optimal strategies under two specific demand distributions. Furthermore, the authors focused on how forecast error affects the optimal inventory strategy and obtained interesting properties of the optimal solution. In particular, the property that the optimal procurement quantity no longer changes with increasing forecast error under certain conditions is noteworthy, and has not been previously noted by scholars. Therefore, the study fills a gap in the literature.
Originality/value
This study established a two-stage inventory optimization model that simultaneously considers random yield and demand forecast quality, and provides explicit expressions for optimal strategies under two specific demand distributions. Furthermore, the authors focused on how forecast error affects the optimal inventory strategy and obtained interesting properties of the optimal solution. In particular, the property that the optimal procurement quantity no longer changes with increasing forecast error under certain conditions is noteworthy, and has not been previously noted by scholars. Therefore, the study fills a gap in the literature.
... The evolution of forecasting practices within organisations, as highlighted by these studies, indicates a shift towards more sophisticated and data-driven approaches. For example, Sanders and Graman (2016) show that advanced forecasting models and technologies are being adopted to improve forecast accuracy. These models leverage large datasets and advanced analytics to produce more accurate and reliable forecasts, which are crucial for effective supply chain management. ...
Objective: This study investigates the development and relationships between the goodness of fit of demand forecasts and supply chain decision-making within organisations. Theoretical Framework: Emphasising both qualitative and quantitative perspectives, we explore how accurate demand forecasting is integrated into organisational practices and how it influences evidence-based cultures. Method: The study employs an empirical case study from a Chilean public health organisation to demonstrate the practical application of advanced forecasting models. Results and Discussion: Our analysis reveals that precise forecasting methods significantly enhance inventory management, resource allocation, and cost efficiency, while fostering a data-driven decision-making culture. Research Implications: The findings underscore the importance of integrating accurate demand forecasting into organisational practices to improve supply chain performance and decision-making. Originality/Value: This study contributes to the literature by illustrating the effectiveness of advanced forecasting models in optimising lot-sizing decisions and achieving substantial cost savings.
... The second contribution pertains to the new findings. Many researchers, such as Ali et al. (2017) and Sanders and Graman (2016), argued that demand factors directly impact supply chain performance. However, our study proves that demand updates must occur through members' decision-making behaviours, and that these behaviours are intermediary factors for achieving improvement in supply chain performance. ...
The performance of the logistics service supply chain (LSSC) is not only affected by external demand changes, but also by the decision-making behaviours of LSSC members, including logistics service integrators (LSI) and functional logistics service providers (FLSP). This paper establishes a structural equation model for assessing the relationships among demand updating, decision-making behaviours and supply chain performance. The model is validated by questionnaire data from China using the SmartPLS method. There are many important conclusions. Firstly, demand updating acting as an intermediary variable does not have a direct impact on supply chain performance. Secondly, demand updating has a more positive impact on LSI than FLSP. Meanwhile, LSI has a positive impact on FLSP’s behaviours. Thirdly, the contribution of LSI’s behaviours towards improving the supply chain performance is only slightly greater than that of FLSP. Therefore, LSI should focus on improving its own behaviours to avoid being overtaken by FLSP.
... An unbiased forecast will have a ME of zero due to cancellations of equal amounts of over and under forecasting, with an ME other than zero indicating a bias tendency. We include forecast bias as a measure of forecast accuracy as it has been found to be the most damaging and prevalent in practice (Fildes et al. 2009, Sanders andGraman 2016). ...
We examine the impact of increasing product variety on two measures of a firm’s forecast performance – forecast accuracy and forecast bias – and test whether shared information mitigates this impact. With companies under pressure to expand product variety yet maintain good forecast accuracy understanding this relationship is critical. We use data gathered pre and post a vertical integration event, where some information forecasted prior to the merger was now available. We show that increasing product variety, and thus the number of forecasts, indeed deteriorates both forecast accuracy and bias. The vertical integration event, providing information sharing, results in improved forecast performance. Further, different product variety attributes (e.g. brand variety and pack variety) are found to have differing impacts. Increasing brand variety is found to have a significantly greater impact on forecast accuracy than pack variety. Using the vertical integration event as a natural experiment we document that expanding product variety negatively impacts forecasts and that information can help mitigated the impact. This is an important contribution as it tests the value of ‘truthful’ information given the elimination of the firm boundary post merger. Further, we show that a firm’s decision to expand product variety should include product variety attributes given their differential impact.
New product supply chain planning is challenging, primarily due to the lack of historical demand data. Rarely, however, do the academic literature or companies differentiate the demand forecasting process for new products from existing ones, despite their increased reliance on judgmental estimates. This research focuses on how judgmental errors lead to an under‐estimation of the difference between the highest‐ and lowest‐demand stock‐keeping units (SKUs), and consequently negatively impact supply chain planning for new product family introductions. A generalized empirical model and accompanying discrete event simulation are developed and applied to data from a major consumer packaged goods (CPG) firm during the launch of a new cosmetics product family. This application allows us to identify a focal type of judgmental error (identified as the SKU‐level spread bias) inherent to new product forecasting and to provide a new theoretical understanding of how this type of bias harms supply chain performance. Via an empirically driven theory‐building approach that iterates between the simulation outcomes and existing literature, SKU‐level spread bias is demonstrated to harm demand forecasts and, thereby, supply chain plans. Our unique theory‐building approach advances theory by identifying planner SKU‐level spread bias as a new source of bias that firms should seek to mitigate when introducing new product families.
Demand forecasts are the lifeblood of supply chains. Academic literature and common industry practices indicate that demand forecasts are often subject to human interventions. Judgmental forecasting or judgmental forecast adjustments can cause both positive and negative repercussions to the rest of the supply chain. This paper provides the first systematic literature review of judgmental forecasting and adjustments focusing on key features that impact various decisions in supply chains. A carefully assembled and shortlisted literature pool is analyzed for systematic mapping of the published works using bibliometric tools. The primary sub streams of research within the broader scope of the field are synthesized from a rigorous keyword cluster analysis and a thorough discussion is presented. Our review concludes by encapsulating the key learnings from four decades of academic research in judgmental forecasting and suggests future research avenues to expand our understanding of the role of humans in demand forecasting and supply chain decision-making.
This article proposes a unifying theory, or Golden Rule, of forecasting. The Golden Rule of Forecasting is to be conservative. A conservative forecast is consistent with cumulative knowledge about the present and the past. To be conservative, forecasters must seek out and use all knowledge relevant to the problem, including knowledge of methods validated for the situation. Twenty-eight guidelines are logically deduced from the Golden Rule. A review of evidence identified 105 papers with experimental comparisons; 102 support the guidelines. Ignoring a single guideline increased forecast error by more than two-fifths on average. Ignoring the Golden Rule is likely to harm accuracy most when the situation is uncertain and complex, and when bias is likely. Non-experts who use the Golden Rule can identify dubious forecasts quickly and inexpensively. To date, ignorance of research findings, bias, sophisticated statistical procedures, and the proliferation of big data, have led forecasters to violate the Golden Rule. As a result, despite major advances in evidence-based forecasting methods, forecasting practice in many fields has failed to improve over the past half-century.
Purpose
Logistics scholars, as well as strategic management scholars, have in recent years shown that capabilities in logistics and supply chain management may be the foundation for a company's sustainable competitive advantage. It can be argued that beside product‐, production‐, or market‐oriented companies, there are also flow‐oriented companies, in which the business models are based on superior logistics performance. The purpose of this study is to explore the characteristics of logistics‐based competition, i.e. how a logistics‐based business model is designed.
Design/methodology/approach
The research is based on a case study at a German do‐it‐yourself retailer. The case company can be considered as a best practice company when it comes to logistics‐based competition, where a committed top management team guarantees the importance of logistics in the strategic development of the company.
Findings
Logistics‐related characteristics of the three business model components – external environment, internal factors and offering – are elaborated.
Originality/value
This research adds to existing theory by developing the meaning of logistics‐based competition. The strategic role of logistics is described through a business model approach.
This article proposes a unifying theory, or the Golden Rule, of forecasting. The Golden Rule of Forecasting is to be conservative. A conservative forecast is consistent with cumulative knowledge about the present and the past. To be conservative, forecasters must seek out and use all knowledge relevant to the problem, including knowledge of methods validated for the situation. Twenty-eight guidelines are logically deduced from the Golden Rule. A review of evidence identified 105 papers with experimental comparisons; 102 support the guidelines. Ignoring a single guideline increased forecast error by more than two-fifths on average. Ignoring the Golden Rule is likely to harm accuracy most when the situation is uncertain and complex, and when bias is likely. Non-experts who use the Golden Rule can identify dubious forecasts quickly and inexpensively. To date, ignorance of research findings, bias, sophisticated statistical procedures, and the proliferation of big data, have led forecasters to violate the Golden Rule. As a result, despite major advances in evidence-based forecasting methods, forecasting practice in many fields has failed to improve over the past half-century.
Many telephone call centers that experience cyclic and random customer demand adjust their staffing over the day in an attempt to provide a consistent target level of customer service. The standard and widely used staffing method, which we call the stationary independent period by period (SIPP) approach, divides the workday into planning periods and uses a series of stationary independent Erlang-c queuing models—one for each planning period—to estimate minimum staffing needs. Our research evaluates and improves upon this commonly used heuristic for those telephone call centers with limited hours of operation during the workday. We show that the SIPP approach often suggests staffing that is substantially too low to achieve the targeted customer service levels (probability of customer delay) during critical periods. The major reasons for SIPP‘ s shortfall are as follows: (1) SIPP's failure to account for the time lag between the peak in customer demand and when system congestion actually peaks; and (2) SIPP’ s use of the planning period average arrival rate, thereby assuming that the arrival rate is constant during the period. We identify specific domains for which SIPP tends to suggest inadequate staffing. Based on an analysis of the factors that influence the magnitude of the lag in infinite server systems that start empty and idle, we propose and test two simple “lagged” SIPP modifications that, in most situations, consistently achieve the service target with only modest increases in staffing.
This paper proposes simple methods for sta-ng a single-class call center with uncertain arrival rate and uncertain sta-ng due to employee absenteeism. The arrival rate and the proportion of servers present are treated as random variables. The basic model is a multi-server queue with customer abandonment, allowing non-exponential service-time and time-to-abandon dis- tributions. The goal is to maximize the expected net return, given throughput beneflt and server, customer-abandonment and customer-waiting costs, but attention is also given to the standard deviation of the return. The approach is to approximate the performance and the net return, conditional on the random model-parameter vector, and then uncondition to get the desired results. Two recently-developed approximations are used for the conditional perfor- mance measures: flrst, a deterministic ∞uid approximation and, second, a numerical algorithm based on a purely Markovian birth-and-death model, having state-dependent death rates.
Using a real-life data set, we investigate the benefit of sharing market sales information in a setting where a theoretical model argues there is no benefit from such a collaboration scheme. The set of real Electronic Point Of Sales (EPOS) data and the orders that were placed by a retailer to a suppler was used. We have focused on products that operate under an every day low price strategy. To measure the benefit of the second echelon player the Standard Deviation of the Prediction Errors (SDPE) is used as this is linearly related to inventory costs. It is revealed that the second echelon player can reduce its SDPE by between 8% and 19% by exploiting the shared EPOS data, suggesting that there is a benefit to information sharing. Furthermore, it is proposed that the noise element that is originally contained in the EPOS series is the major source of the information sharing benefit.
Forecasts of demand are crucial to drive supply chains and enterprise resource planning systems. Usually, well-known univariate methods that work automatically such as exponential smoothing are employed to accomplish such forecasts. The traditional Supply Chain relies on a decentralised system where each member feeds its own Forecasting Support System (FSS) with incoming orders from direct customers. Nevertheless, other collaboration schemes are also possible, for instance, the Information Exchange framework allows demand information to be shared between the supplier and the retailer. Current theoretical models have shown the limited circumstances where retailer information is valuable to the supplier. However, there has been very little empirical work carried out. Considering a serially linked two-level supply chain, this work assesses the role of sharing market sales information obtained by the retailer on the supplier forecasting accuracy. Weekly data from a manufacturer and a major UK grocery retailer have been analysed to show the circumstances where information sharing leads to improved forecasting accuracy. Without resorting to unrealistic assumptions, we find significant evidence of benefits through information sharing with substantial improvements in forecast accuracy.
The impact of e-commerce on the business environment is often praised but seldom analyzed with scrutiny. In this paper we try to depict the underlying logistically relevant aspects of e-commerce and their impacts on logistics service providers. This seems to be of considerable importance, as logistics is seen as the back-bone of e-commerce operations. However, the firms specializing in this field are commonly neglected. We argue that the logistical implications of e-commerce can be differentiated into two main categories: the rise of e-marketplaces; and the elimination of supply chain elements (disintermediation). By analyzing these two categories and their major logistical implications in detail we deduct strategic consequences for logistics service providers.
This paper develops a framework for examining the effect of demand uncertainty and forecast error on unit costs and customer service levels in the supply chain, including Material Requirements Planning (MRP) type manufacturing systems. The aim is to overcome the methodological limitations and confusion that has arisen in much earlier research. To illustrate the issues, the problem of estimating the value of improving forecasting accuracy for a manufacturer was simulated. The topic is of practical importance because manufacturers spend large sums of money in purchasing and staffing forecasting support systems to achieve more accurate forecasts. In order to estimate the value a two-level MRP system with lot sizing where the product is manufactured for stock was simulated. Final product demand was generated by two commonly occurring stochastic processes and with different variances. Different levels of forecasting error were then introduced to arrive at corresponding values for improving forecasting accuracy. The quantitative estimates of improved accuracy were found to depend on both the demand generating process and the forecasting method. Within this more complete framework, the substantive results confirm earlier research that the best lot sizing rules for the deterministic situation are the worst whenever there is uncertainty in demand. However, size matters, both in the demand uncertainty and forecasting errors. The quantitative differences depend on service level and also the form of demand uncertainty. Unit costs for a given service level increase exponentially as the uncertainty in the demand data increases. The paper also estimates the effects of mis-specification of different sizes of forecast error in addition to demand uncertainty. In those manufacturing problems with high demand uncertainty and high forecast error, improved forecast accuracy should lead to substantial percentage improvements in unit costs. Methodologically, the results demonstrate the need to simulate demand uncertainty and the forecasting process separately.
The Internet has increased the level of importance of the end-consumer market to transportation carriers. In two between subject experiments, carrier disclosure on retail merchant websites is examined as a strategic differentiation strategy. Predictions are offered concerning effects of carrier disclosure strategies on product delivery-related expectations, consumer attitudes, and intentions to purchase a product online. Results from Study 1 reveal significant differences between disclosure and nondisclosure of the carrier for numerous product delivery-related variables, as well as many differences between the six carriers examined in this first study. Study 2 extends these findings by showing that providing consumers with a choice of carrier leads to increased levels of satisfaction with the online experience and greater willingness to buy, relative to nondisclosure and disclosure strategies.
Whether and how trust and trustworthiness differ between a collectivist society, e.g., China, and an individualistic one, e.g., the United States, generates much ongoing scientific debate and bears significant practical values for managing cross-country transactions. We experimentally investigate how supply chain members' countries of origin—China versus the United States—affect trust, trustworthiness, and strategic information sharing behavior in a cross-country supply chain. We consider a two-tier supply chain in which the upstream supplier solicits demand forecast information from the retailer to plan production; but the retailer has an incentive to manipulate her forecast to ensure abundant supply. The levels of trust and trustworthiness in the supply chain and supplier's capability to determine the optimal production quantity affect the efficacy of forecast sharing and the resulting profits. We develop an experimental design to disentangle these three aspects and to allow for real-time interactions between geographically distant and culturally heterogeneous participants. We observe that, when there is no prospect for long-term interactions, our Chinese participants consistently exhibit lower spontaneous trust and trustworthiness than their U.S. counterparts do. We quantify the differences in trust and trustworthiness between the two countries, and the resulting impact on supply chain efficiency. We also show that Chinese individuals exhibit higher spontaneous trust toward U.S. partners than Chinese ones, primarily because they perceive that individuals from the United States are more trusting and trustworthy in general. This positive perception toward U.S. people is indeed consistent with the U.S. participants' behavior in forecast sharing. In addition, we quantify that a Chinese supply chain enjoys a larger efficiency gain from repeated interactions than a U.S. one does, as the prospect of building a long-term relationship successfully sustains trust and trustworthiness by Chinese partners. We advocate that companies can reinforce the positive perception of westerners held by the Chinese population and commit to long-term relationships to encourage trust by Chinese partners. Finally, we also observe that both populations exhibit similar pull-to-center bias when solving a decision problem under uncertainty (i.e., the newsvendor problem).
Data, as supplemental material, are available at http://dx.doi.org/10.1287/mnsc.2014.1905 .
This paper was accepted by Yossi Aviv, operations management.
In this commentary, we trace back how we pursued research on the bullwhip effect, which resulted in the article published in Management Science. We reflect on the evolution of this concept, the impact that our work has had on industry, the way our work has been used in the teaching of supply chain management, and the key directions of research that have taken place since then.
We consider a production stage that produces a single item in a make-to-stock manner. Demand for finished goods is stationary. In each time period, an updated vector of demand forecasts over the forecast horizon becomes available for use in production decisions. We model the sequence of forecast update vectors using the Martingale model of forecast evolution developed by Graves et al. (1986, 1998) and Heath and Jackson (1994). The production stage is modeled as a single-server, discrete-time, continuous-state queue. We focus on a modified base-stock policy incorporating forecast information and use an approximate analysis rooted in heavy traffic theory and random walk theory to obtain a closed-form expression for the (forecast-corrected) base-stock level that minimizes the expected steady-state inventory holding and backorder costs. This expression, which is shown to be accurate under certain conditions in a simulation study, sheds some light on the interrelationships among safety stock, stochastic correlated demand, inaccurate forecasts, and random and capacitated production in forecasting-production-inventory systems.
Many companies have embarked on initiatives that enable more demand information sharing between retailers and their upstream suppliers. While the literature on such initiatives in the business press is proliferating, it is not clear how one can quantify the benefits of these initiatives and how one can identify the drivers of the magnitudes of these benefits. Using analytical models, this paper aims at addressing these questions for a simple two-level supply chain with nonstationary end demands. Our analysis suggests that the value of demand information sharing can be quite high, especially when demands are significantly correlated over time.
We study the demand forecast-sharing process between a buyer of customized production equipment and a set of equipment suppliers. Based on a large data collection we undertook in the semiconductor equipment supply chain, we empirically investigate the relationship between the buyer's forecasting behavior and the supplier's delivery performance. The buyer's forecasting behavior is characterized by the frequency and magnitude of forecast revisions it requests (forecast volatility) as well as by the fraction of orders that were forecasted but never actually purchased (forecast inflation). The supplier's delivery performance is measured by its ability to meet delivery dates requested by the customers. Based on a duration analysis, we are able to show that suppliers penalize buyers for unreliable forecasts by providing lower service levels. Vice versa, we also show that buyers penalize suppliers that have a history of poor service by providing them with overly inflated forecasts.
Principles of Forecasting: A Handbook for Researchers and Practitioners summarizes knowledge from experts and from empirical studies. It provides guidelines that can be applied in fields such as economics, sociology, and psychology. It applies to problems such as those in finance (How much is this company worth?), marketing (Will a new product be successful?), personnel (How can we identify the best job candidates?), and production (What level of inventories should be kept?).
The book is edited by Professor J. Scott Armstrong of the Wharton School, University of Pennsylvania. Contributions were written by 40 leading experts in forecasting, and the 30 chapters cover all types of forecasting methods. There are judgmental methods such as Delphi, role-playing, and intentions studies. Quantitative methods include econometric methods, expert systems, and extrapolation. Some methods, such as conjoint analysis, analogies, and rule-based forecasting, integrate quantitative and judgmental procedures. In each area, the authors identify what is known in the form of `if-then principles', and they summarize evidence on these principles.
The project, developed over a four-year period, represents the first book to summarize all that is known about forecasting and to present it so that it can be used by researchers and practitioners. To ensure that the principles are correct, the authors reviewed one another's papers. In addition, external reviews were provided by more than 120 experts, some of whom reviewed many of the papers. The book includes the first comprehensive forecasting dictionary.
The production-smoothing model of inventories implies that inventories, labor inputs, sales, and factor input prices are cointegrated if sales and factor prices are I(1) with one cointegrating vector for each state variable held. These propositions are tested in six nondurable-goods industries. All industries provide evidence of cointegration. Fewer quasi-fixed factors are found than previous research often assumed. Estimates of cointegrating vectors provide implausible parameter estimates. Rank stability tests, with fixed or seqentially chosen breakpoints, indicate that the cointegrating matrix has unstable rank. Parameter estimates of cointegrating vectors do not provide much support for the production-smoothing model of inventories.
Many decisions are based on beliefs concerning the likelihood of uncertain events such as the outcome of an election, the guilt of a defendant, or the future value of the dollar. Occasionally, beliefs concerning uncertain events are expressed in numerical form as odds or subjective probabilities. In general, the heuristics are quite useful, but sometimes they lead to severe and systematic errors. The subjective assessment of probability resembles the subjective assessment of physical quantities such as distance or size. These judgments are all based on data of limited validity, which are processed according to heuristic rules. However, the reliance on this rule leads to systematic errors in the estimation of distance. This chapter describes three heuristics that are employed in making judgments under uncertainty. The first is representativeness, which is usually employed when people are asked to judge the probability that an object or event belongs to a class or event. The second is the availability of instances or scenarios, which is often employed when people are asked to assess the frequency of a class or the plausibility of a particular development, and the third is adjustment from an anchor, which is usually employed in numerical prediction when a relevant value is available.
This publication contains reprint articles for which IEEE does not hold copyright. Full text is not available on IEEE Xplore for these articles.
Drawing on behavioral research, we construct a multi‐period model with which to examine the role of trust and other social characteristics in a supply chain. Specifically, we focus on trust building in the context of a salesperson who acts as a representative of a manufacturer and shares demand forecast information with a retailer. The actions of the salesperson affect both her immediate economic gain and her future credibility as determined by retailer's trust. Our analysis reveals that, in such environments, although salespersons of widely varying types (e.g., honest, self‐serving, benevolent, loyal) lie some extent about their forecast information, they tend to be trusted in long relationships, provided their forecasting accuracy is higher than that of the retailer. Furthermore, while the presence of a salesperson can improve the profits of both the retailer and manufacturer, there are cost structures under which the manufacturer is better off without a salesperson. Finally, we make the general observation that the appropriate salesperson compensation scheme depends on her social characteristics, and the specific observation that when the salesperson cares for the retailer, the linear compensation scheme commonly suggested in the literature as the optimal compensation scheme for the salesperson is no longer optimal.
This paper studies supply chain demand variability in a model with one supplier and N retailers that face stochastic demand. Retailers implement scheduled ordering policies: Orders occur at fixed intervals and are equal to some multiple of a fixed batch size. A method is presented that exactly evaluates costs. Previous research demonstrates that the supplier's demand variance declines as the retailers' order intervals are balanced, i.e., the same number of retailers order each period. This research shows that the supplier's demand variance will (generally) decline as the retailers' order interval is lengthened or as their batch size is increased. Lower supplier demand variance can certainly lead to lower inventory at the supplier. This paper finds that reducing supplier demand variance with scheduled ordering policies can also lower total supply chain costs.
This paper presents a hierarchical model framework for the analysis of the stabilizing effect of inventories in multiechelon manufacturing/distribution supply chains. This framework is used to compare the variance of demand to the variance of replenishment orders at different echelons of the system (e.g., retailer, wholesaler). Empirical data and experience with management games suggest that, in most industries, inventory management policies can have a destabilizing effect by increasing the volatility of demand as it passes up through the chain (the "bullwhip" effect). Our model helps to explain these observations and indicates mechanisms that can promote stabilization. The analysis results also define sufficient conditions for the existence of stabilization and relate these conditions to the optimality of myopic control policies.
Purpose
In general, demand for functional products is dependent on a range of promotions offered in various retail outlets. To improve promotional sales many retailers collaborate with manufacturers for planning, forecasting and replenishment. The purpose of this paper is to hypothesize that collaborative forecasting will improve the forecast accuracy if all the partners can relate their demand forecast with underlying demand factors.
Design/methodology/approach
In this paper, the author uses a case study approach to study various demand factors of soft drink products of the UK based company which offers frequent promotions in retail outlets. The paper represents the case study findings in a conceptual framework called Reference Demand Model (RDM). Further, the case study findings are validated empirically by means of multiple linear regression analysis using actual sales data of the case company.
Findings
Surprisingly, some of the demand factors specified as very important by the case company are not found to be highly significant for actual sales. The paper uses the identified demand factors to suggest levels of collaboration.
Practical implications
Understanding the importance of product specific demand factors through regression models and incorporating the same in managerial decision making will aid managers to identify the necessary information to make accurate demand forecasts.
Originality/value
This approach unveils the presence of three levels of collaboration namely preparatory, progressive and futuristic levels among supply chain partners based on the information exchange. The proposed method will aid decision making on information sharing and collaborative planning among manufacturer and retailers for future promotional sales.
Motivated by an oilfield services industry case study, we investigate the dynamic behavior of customized service supply chains by developing a two-stage serial staffing model. Each stage holds no finished goods inventory, but rather only backlogs that can be managed by adjusting staffing levels. We develop optimal control policies to balance backlog costs against hiring and firing personnel costs'assuming shared backlog information—under both centralized and decentralized control. We examine when there is sufficient economic incentive for two completely decentralized stages to begin: (1) to share backlog information without centralizing control, or (2) to completely centralize control. These switching points are determined by the relative service and personnel costs of the two stages. From these results, we show that decentralizing control in many cases does not materially worsen performance, so long as information is shared. Moreover, in some cases, even sharing information is of only marginal benefit.
Service managers often find that available worker capacity does not match with actual demand during a given day. They then must attempt to modify the planned work schedule to improve service and increase profitability. This study, which defines such a setting as the real-time work schedule adjustment decision, proposes mathematical formulations of the real-time adjustment and develops efficient heuristic approaches for this decision. The study evaluates the relative effectiveness of these heuristics versus experienced service managers, investigates the effect of the degree of schedule adjustment on profitability, and assesses the effect of demand forecast update errors on the performance of the schedule adjustment efforts. First, the results indicate that the computer based heuristics achieve higher profit improvement than experienced managers. Second, there is a trade-off between schedule stability and profitability so that more extensive schedule revisions (efficiency first heuristics) generally result in higher profitability. However, the incremental return on schedule changes is diminishing. Third, we find that active adjustments of work schedules are beneficial as long as the direction of demand change is accurately identified.
This is a case study of workforce scheduling in the U.S. postal system. We use it to analyze the benefits of scheduling flexibility at postal distribution systems, which can come from several sources. We focus on the additional flexibility deriving from increasing the proportion of part-time employees, as well as from increasing the cross-training of part-time employees. These two dimensions of scheduling flexibility are decision points of particular interest to the postal management.
We used a large-scale simulation model of the dynamic functioning of the postal distribution system in conjunction with a staff-scheduling model to obtain insights into policy issues of interest. Our results show that the operating environment at a distribution station affects cost and customer service performance, and that gains from greater scheduling flexibility are situationally dependent. The benefit of cross-training part-time workers is modest over the range of levels considered realistic for distribution stations.
Our overall recommendation is for postal managers to increase the proportion of part-time employees, allowing more efficient matching of resources with the varying demands for mail delivery on different routes. For the range of conditions we modeled, cost reductions from more part-time workers average over six percent when capacity utilization is low. Customer service improvements are even larger, and range between 20 and 43% when capacity utilization is high. Improvements at the upper end of the range are achieved when demand variability is also at its highest.
We examine the effects of product variety and inventory levels on store sales. Using 4 years of data from stores of a large retailer, we show that increases in product variety and inventory levels are both associated with higher sales. We also show that increasing product variety and inventory levels has an indirect negative effect on store sales through their impact on phantom products—products that are physically present at the store, but only in storage areas where customers cannot find or purchase them. Our study highlights a consequence of increased product variety and inventory levels that has previously been overlooked in studies of retail product variety and inventory management. It also quantifies the impact of phantom products on store sales. In addition, our study provides empirical evidence to support earlier claims that higher product variety and inventory levels lead to an increase in defect rate. We discuss the implications of our findings for retail inventory and assortment planning and for the design of retail stores.
The impact of forecast errors on organizational cost, and the usefulness of worker flexibility measures in offsetting their negative effects were evaluated in a labor intensive warehouse environment. Unlike past studies measuring forecast error in terms of forecast standard deviation, this study also considers the impact of forecast bias, which occurs when the mean of the error distribution is non-zero. Results indicate that forecast bias is more damaging to warehouse cost, compared to forecast standard deviation. Workforce flexibility measures, such as worker cross-training and proportion of full and part-time labor, provide a solid buffer against forecast standard deviation. However, they are much less effective against forecast bias. This has important managerial implications as a large portion of forecast bias is managerially introduced.
In this study the interaction of forecasting method (econometric versus exponential smoothing) and two situational factors are evaluated for their effects upon accuracy. Data from two independent sets of ex ante quarterly forecasts for 19 classes of mail were used to test hypotheses. Counter to expectations, the findings revealed that forecasting method did not interact with the forecast time horizon (short versus long term). However, as hypothesized, forecasting method interacted significantly with product/market definition (First Class versus other mail), an indicator of buyer sensitivity to marketing/environmental changes. Results are discussed in the context of future research on forecast accuracy.
This research analyzes how individual differences affect performance in judgmental time-series forecasting. Decision makers with the ability to balance intuitive judgment with cognitive deliberation, as measured by the Cognitive Reflection Test, tend to have lower forecast errors. This relationship holds when controlling for intelligence. Further, forecast errors increase for very fast or very slow decisions. We provide evidence that forecast performance can be improved by manipulating decision speed.
Typical forecast‐error measures such as mean squared error, mean absolute deviation and bias generally are accepted indicators of forecasting performance. However, the eventual cost impact of forecast errors on system performance and the degree to which cost consequences are explained by typical error measures have not been studied thoroughly. The present paper demonstrates that these typical error measures often are not good predictors of cost consequences in material requirements planning (MRP) settings. MRP systems rely directly on the master production schedule (MPS) to specify gross requirements. These MRP environments receive forecast errors indirectly when the errors create inaccuracies in the MPS.
Our study results suggest that within MRP environments the predictive capabilities of forecast‐error measures are contingent on the lot‐sizing rule and the product components structure When forecast errors and MRP system costs are coanalyzed, bias emerges as having reasonable predictive ability. In further investigations of bias, loss functions are evaluated to explain the MRP cost consequences of forecast errors. Estimating the loss functions of forecast errors through regression analysis demonstrates the superiority of loss functions as measures over typical forecast error measures in the MPS.
We consider the problem of managing demand risk in tactical supply chain planning for a particular global consumer electronics company. The company follows a deterministic replenishment-and-planning process despite considerable demand uncertainty. As a possible way to formally address uncertainty, we provide two risk measures, “demand-at-risk” (DaR) and “inventory-at-risk” (IaR) and two linear programming models to help manage demand uncertainty. The first model is deterministic and can be used to allocate the replenishment schedule from the plants among the customers as per the existing process. The other model is stochastic and can be used to determine the “ideal” replenishment request from the plants under demand uncertainty. The gap between the output of the two models as regards requested replenishment and the values of the risk measures can be used by the company to reallocate capacity among different products and to thus manage demand/inventory risk.
Revenue management has been used in a variety of industries and generally takes the form of managing demand by manipulating length of customer usage and price. Supply mix is rarely considered, although it can have considerable impact on revenue. In this research, we focused on developing an optimal supply mix, specifically on determining the supply mix that would maximize revenue. We used data from a Chevys restaurant, part of a large chain of Mexican restaurants, in conjunction with a simulation model to evaluate and enumerate all possible supply (table) mixes. Compared to the restaurant's existing table mix, the optimal mix is capable of handling a 30% increase in customer volume without increasing waiting times beyond their original levels. While our study was in a restaurant context, the results of this research are applicable to other service businesses.
Retailers must constantly strive for excellence in operations; extremely narrow profit margins leave little room for waste and inefficiency. This article reports a retailer's challenge to balance transportation, shelf space, and inventory costs. A retailer sells multiple products with stochastic demand. Trucks are dispatched from a warehouse and arrive at a store with a constant lead time. Each truck has a finite capacity and incurs a fixed shipping cost, no matter the number of units shipped. There is a per unit shelf-space cost as well as holding and backorder penalty costs. Three policies are considered for dispatching trucks: a minimum quantity continuous review policy, a full service periodic review policy, and a minimum quantity periodic review policy. The first policy ships a truck when demand since the previous shipment equals a fixed fraction of a truck's capacity, i.e., a minimum truck utilization. The exact analysis of that policy is the same as the analysis of reorder point policies for the multiechelon problem with one-warehouse, multiple retailers, and stochastic demand. That analysis is not computationally prohibitive, but the minimum quantity level can be chosen with a simple economic order quantity (EOQ) heuristic. An extensive numerical study finds the following: Either of the two periodic review policies may have substantially higher costs than the continuous review policy, in particular when the warehouse to store lead time is short; the EOQ heuristic performs quite well; the minimum quantity policy's total cost is relatively insensitive to the chosen transportation utilization, and its total cost is close to a lower bound developed for this problem.
This paper reports some research, ideas, and theory about managerial decision making. The first research projects dealt with are aggregate production and employment scheduling. From this is developed the idea that management's own (past) decisions can be incorporated into a system of improving their present decisions. Decision rules are developed, with the coefficients in the rules derived from management's past decisions (rather than from a cost or value model). Half a dozen test cases are used to illustrate and test these ideas (theory). Some rationale about decision making in organizations and criteria surfaces is supplied to help interpret the major ideas presented.
Forecast sharing is studied in a supply chain with a manufacturer that faces stochastic demand for a single product and a supplier that is the sole source for a critical component. The following sequence of events occurs: the manufacturer provides her initial forecast to the supplier along with a contract, the supplier constructs capacity (if he accepts the contract), the manufacturer receives an updated forecast and submits a final order. Two contract compliance regimes are considered. If the supplier accepts the contract under forced compliance then he has little flexibility with respect to his capacity choice; under voluntary compliance, however, he maintains substantial flexibility. Optimal supply chain performance requires the manufacturer to share her initial forecast truthfully, but she has an incentive to inflate her forecast to induce the supplier to build more capacity. The supplier is aware of this bias, and so may not trust the manufacturer's forecast, harming supply chain performance. We study contracts that allow the supply chain to share demand forecasts credibly under either compliance regime.
In a recent paper, Lee, So, and Tang (2000) showed that in a two-level supply chain with non-stationary AR(1) end demand, the manufacturer benefits significantly when the retailer shares point-of-sale (POS) demand data. We show in this paper, analytically and through simulation, that the manufacturer's benefit is insignificant when the parameters of the AR(1) process are known to both parties, as in Lee, So, and Tang (LST). The key reason for the difference between our results and those of LST is that LST assume that the manufacturer also uses an AR(1) process to forecast the retailer order quantity. However, the manufacturer can reduce the variance of its forecast further by using the entire order history to which it has access. Thus, when intelligent use of already available internal information (order history) suffices, there is no need to invest in interorganizational systems for information sharing.
We consider a cooperative, two-stage supply chain consisting of two members: a retailer and a supplier. In our first model, called local forecasting, each member updates the forecasts of future demands periodically, and is able to integrate the adjusted forecasts into his replenishment process. Forecast adjustments made at both levels of the supply chain can be correlated. The supply chain has a decentralized information structure, so that day-to-day inventory and forecast information are known locally only. In our second model, named collaborative forecasting, the supply chain members jointly maintain and update a single forecasting process in the system. Hence, forecasting information becomes centralized. Finally, we consider as a benchmark the special case in which forecasts are not integrated into the replenishment processes at all. We propose a unified framework that allows us to study and compare the three types of settings. This study comes at a time when various types of collaborative forecasting partnerships are being experimented within industry, and when the drivers for success or failure of such initiatives are not yet fully understood. In addition to providing some managerial insights into questions that arise in this context, our set of models is tailored to serve as building blocks for future work in this emerging area of research.
This paper presents a compact integer-programming model for large-scale continuous tour scheduling problems that incorporate meal-break window, start-time band, and start-time interval policies. For practical scheduling environments, generalized set-covering formulations (GSCFs) of such problems often contain hundreds of millions of integer decision variables, usually precluding identification of optimal solutions. As an alternative, we present an implicit integer-programming model that frequently has fewer than 1,500 variables and can be formulated and solved using PC-based hardware and software platforms. An empirical study using labor-requirement distributions for customer service representatives at a Motorola, Inc. call center was used to demonstrate the importance of having a model that can evaluate tradeoffs among the various scheduling policies.
The impact of forecasted demand and forecast error, introduced in the Master Production Schedule, upon Material Requirements Planning (MRP) Systems is investigated. A computerized simulation was built to examine several questions. Results indicate that forecasting error, especially the mean error, does impact MRP system inventory costs and shortages; the greater the forecast error the greater the shortages. An exception to this general relationship was that a slight forecast BIAS may improve MRP system performance, which was the case for systems studied herein. Lot-sizing rules and product structure (bill of material structure) were also found to impact total MRP system inventory costs and shortages. The more complicated the MRP structure, the greater the differentiation among lot-sizing rules and the greater the cost impact of forecast errors. A good lot-sizing rule appears to be the period order quantity rule. However, as the forecast error level gets higher, it becomes difficult to select the better lot-sizing rule. Based on this study, suggestions are presented for the production manager's consideration, especially the inventory-production control manager.
Judgement based forecasts are widely used in practice either alone or in conjunction with computer prepared forecasts. This study empirically examines the improvement in accuracy which can be gained from combining judgemental forecasts, either with other judgemental or with quantitatively derived forecasts. Two judgemental forecasting approaches are used by each of two different groups in a laboratory setting to give four sets of judgemental forecasts for the 68 monthly time series of the M-competition. These are combined either with each other or with forecasts from deseasonalised single exponential smoothing. Combined forecasts are found to be more accurate than single forecasts with the greatest benefit realised at short forecast horizons and for easier (as opposed to harder) forecast series. Averaging was observed to be a far better way of combining judgemental forecasts than a judgemental, nonsystematic combination.
The concept and operation of supply chain (SC) visibility remain underexplored questions in supply chain management, as is the question of the facilitating role of inter-organizational information systems (IOIS) in achieving SC visibility. This paper seeks to elaborate on the novel concept of IOIS visibility and to explore the antecedents and consequences of IOIS visibility. Investigating SC cooperation from the perspectives of both partners (buyers and suppliers) is important, especially when channel partners depend on each other and when asymmetries in IOIS visibility can exist. The data that this study requires were collected from 51 matched pairs of intermediate producers of telecommunication equipment components and their immediate suppliers. The results show that IOIS visibility is an important predictor of supply chain performance from the supplier's perspective. In turn, IOIS visibility is significantly influenced by the supply chain partner's internal IS integration and inter-organizational IT infrastructure compatibility.
The decision problems involved in setting the aggregate production rate of a factory and setting the size of its work force are frequently both complex and difficult. The quality of these decisions can be of great importance to the profitability of an individual company, and when viewed on a national scale these decisions have a significant influence on the efficiency of the economy as a whole. This paper reports some of the findings of a research team that has been developing new methods to enable production executives to make better decisions and to make them more easily than they can with prevailing procedures. With the cooperation of a manufacturing concern, the new methods have been developed in the context of a set of concrete production scheduling problems that were found in a factory operated by the company.
The new method which is presented in this paper, involves: (1) formalizing and quantifying the decision problem (using a quadratic approximation to the criterion function) and (2), calculating a generalized optimal solution of the problem in the form of a (linear) decision rule. Like a rule of thumb, an optimal decision rule prescribes a course of action when it is applied to a particular set of circumstances; but, unlike most rules of thumb, an optimal decision rule prescribes courses of action for which the claim can be made that the decisions are “the best possible,” the meaning of “best” being clearly specified. The ultimate test, of course, must be whether the new decision methods do or do not outperform prevailing decision methods when full allowance is made for the cost of obtaining the optimal decisions.