Search

The editors of Management Science acknowledge all our 2023 reviewers and guest associate editors who generously provided expert counsel and guidance on a voluntary basis. We are grateful for their contributions; without them, the journal could not function. Here, we list those reviewers who contributed four or more reviews in 2023. Supplemental Material: The complete list of our 2023 reviewers is available at https://doi.org/10.1287/mnsc.2024.acknowledgements.v70.n4. [ABSTRACT FROM AUTHOR]

The author reflects on the last six years as editor in chief of the journal. He talks about the major changes and bold initiatives he announced when he became editor in chief of the journal, submission volume in 2023, and some of the major initiatives introduced by the journal. Also mentioned are emerging trends in management science.

We examine whether the Environmental Protection Agency (EPA) uniformly enforces the Clean Air Act for politically connected and unconnected firms using a close election setting. We find no difference in regulated pollutant emissions or EPA investigations between the two groups, although connected firms experience less regulatory enforcement and lower penalties. These results are more pronounced for firms connected to politicians capable of influencing regulatory bureaucrats and for connected firms that are more important to their supported politicians. Taken together, our results show that campaign contributions can indirectly benefit firms by way of reduced environmental regulatory enforcement and penalties. This paper was accepted by Colin Mayer for the Special Issue of Management Science: Business and Climate Change. Supplemental Material: The data files and online appendix are available at https://doi.org/10.1287/mnsc.2020.3931. [ABSTRACT FROM AUTHOR]

Over the past decade, blockchains and cryptocurrencies have taken a central stage in financial technology (FinTech) innovation. In 2020–2021, as the academic finance and management community began actively investigating this domain, we issued a call for papers for a special issue to encourage interdisciplinary research in this emerging area. This section of Management Science presents the first systematic collection of knowledge, both theoretical and empirical, focusing on blockchain economics, crypto assets, decentralized finance, and Web3 ecosystems. We describe the editorial protocol employed for this special issue (now included in this volume as a special section), summarize what we learn about the field, and introduce the 15 articles included in the special section. We also offer several observations to highlight foundational issues in the new field and to guide future research in this exciting new area at the intersection of technology and finance. [ABSTRACT FROM AUTHOR]

In the high-stakes race for scalability, some blockchains have turned to committee-based consensus (CBC), whereby the chain's recordkeeping rights are entrusted to a committee of block producers elected via approval voting. Smaller committees boost speed and scalability but can compromise security when voters have limited information. In this environment, voting strategies are naturally nonlinear, and equilibria can become intractable. Despite this, we show that elections converge to optimality asymptotically (in voter numbers), exponentially quickly, and under relatively weak informational requirements. Compared to popular stake-weighted lottery and single-vote protocols used in practice, we find that CBC, when paired with approval voting, can offer meaningful efficiency and robustness gains if enough voters are engaged. This paper was accepted by Will Cong, Special Section of Management Science: Blockchains and Crypto Economics. Funding: This work was funded by The Hogeg Blockchain Research Institute. Supplemental Material: The data files and online appendix are available at https://doi.org/10.1287/mnsc.2022.03177. [ABSTRACT FROM AUTHOR]

The article announces the recipients of the 2023 Management Science Service Awards including the Distinguished Service Award to associate editors Sumit Agarwal, Turan Bali and Gordon Burtch and the Meritorious Service Award to associate editors Wilfred Amaldoss, Jennie Bai and Aurelien Baillon.

Over the last two decades, researchers in operations management have increasingly leveraged laboratory experiments to identify key behavioral insights. These experiments inform behavioral theories of operations management, impacting domains including inventory, supply chain management, queuing, forecasting, and sourcing. Yet, until now, the replicability of most behavioral insights from these laboratory experiments has been untested. We remedy this with the first large-scale replication study in operations management. With the input of the wider operations management community, we identify 10 prominent experimental operations management papers published in Management Science, which span a variety of domains, to be the focus of our replication effort. For each paper, we conduct a high-powered replication study of the main results across multiple locations using original materials (when available and suitable). In addition, our study tests replicability in multiple modalities (in-person and online) due to laboratory closures during the COVID-19 pandemic. Our replication study contributes new knowledge about the robustness of several key behavioral theories in operations management and contributes more broadly to efforts in the operations management field to improve research transparency and reliability. This paper was accepted by David Simchi-Levi, operations management. Funding: The authors gratefully acknowledge financial support from Cornell University, the University of South Carolina, the University of Texas at Dallas, the University of Michigan, and the University of Wisconsin-Madison. Supplemental Material: The data files and online appendices are available at https://doi.org/10.1287/mnsc.2023.4866. [ABSTRACT FROM AUTHOR]

The article announces Management Science Distinguished Service Award was given to Sumit Agarwal, National University of Singapore Bali, Turan; Georgetown University.

Conditional quantile prediction involves estimating/predicting the quantile of a response random variable conditioned on observed covariates. The existing literature assumes the availability of independent and identically distributed (i.i.d.) samples of both the covariates and the response variable. However, such an assumption often becomes restrictive in many real-world applications. By contrast, we consider a fixed-design setting of the covariates, under which neither the response variable nor the covariates have i.i.d. samples. The present study provides a new data-driven distributionally robust framework under a fixed-design setting. We propose a regress-then-robustify method by constructing a surrogate empirical distribution of the noise. The solution of our framework coincides with a simple yet practical method that involves only regression and sorting, therefore providing an explanation for its empirical success. Measure concentration results are obtained for the surrogate empirical distribution, which further lead to finite-sample performance guarantees and asymptotic consistency. Numerical experiments are conducted to demonstrate the advantages of our approach. This paper was accepted by Hamid Nazerzadeh, Management Science Special Section on Data-Driven Prescriptive Analytics. [ABSTRACT FROM AUTHOR]

The editors of Management Science acknowledge all our 2021 reviewers and guest associate editors who generously provided expert counsel and guidance on a voluntary basis. We are grateful for their contributions; without them, the journal could not function. Here, we list those reviewers who contributed four or more reviews in 2021. [ABSTRACT FROM AUTHOR]

The Bass Model (BM) has an excellent track record in the realm of new product sales forecasting. However, its use for optimal dynamic pricing or advertising is relatively limited because the Generalized Bass Model (GBM), which extends the BM to handle marketing variables, uses only percentage changes in marketing variables, rather than their actual values. This restricts the GBM's prescriptive use, for example, to derive the optimal price path for a new product, conditional on an assumed launch price, but not the launch price itself. In this paper, we employ a utility-based extension of the BM, which can yield normative prescriptions regarding both the introductory price and the price path after launch, for the new product. We offer two versions of this utility-based diffusion model, namely, the Bass-Gumbel Diffusion Model (BGDM) and the Bass-Logit Diffusion Model (BLDM), the latter of which has been previously used. We show that both the BGDM and BLDM handily outperform the GBM in forecasting new product sales using empirical data from four product categories. We discuss how to estimate the BGDM and BLDM in the absence of past sales data. We compare the optimal pricing policy of the BLDM with the GBM and derive optimal pricing policies that are implied by the BLDM under various ranges of model parameters. We illustrate a dynamic pricing approach that allows managers to derive optimal marketing policies in a computationally convenient manner and extend this approach to a competitive, multiproduct case. This paper was accepted by Gui Liberali, Management Science Special Section on Data-Driven Prescriptive Analytics. [ABSTRACT FROM AUTHOR]

We study a general problem of allocating limited resources to heterogeneous customers over time under model uncertainty. Each type of customer can be serviced using different actions, each of which stochastically consumes some combination of resources and returns different rewards for the resources consumed. We consider a general model in which the resource consumption distribution associated with each customer type–action combination is not known but is consistent and can be learned over time. In addition, the sequence of customer types to arrive over time is arbitrary and completely unknown. We overcome both the challenges of model uncertainty and customer heterogeneity by judiciously synthesizing two algorithmic frameworks from the literature: inventory balancing, which "reserves" a portion of each resource for high-reward customer types that could later arrive based on competitive ratio analysis, and online learning, which "explores" the resource consumption distributions for each customer type under different actions based on regret analysis. We define an auxiliary problem, which allows for existing competitive ratio and regret bounds to be seamlessly integrated. Furthermore, we propose a new variant of upper confidence bound (UCB), dubbed lazyUCB, which conducts less exploration in a bid to focus on "exploitation" in view of the resource scarcity. Finally, we construct an information-theoretic family of counterexamples to show that our integrated framework achieves the best possible performance guarantee. We demonstrate the efficacy of our algorithms on both synthetic instances generated for the online matching with stochastic rewards problem under unknown probabilities and a publicly available hotel data set. Our framework is highly practical in that it requires no historical data (no fitted customer choice models or forecasting of customer arrival patterns) and can be used to initialize allocation strategies in fast-changing environments. This paper was accepted by J. George Shanthikumar, Management Science Special Section on Data-Driven Prescriptive Analytics. [ABSTRACT FROM AUTHOR]

Clinical pathways outline standardized processes in the delivery of care for a specific disease. Patient journeys through the healthcare system, however, can deviate substantially from these pathways. Given the positive benefits of clinical pathways, it is important to measure the concordance of patient pathways so that variations in health system performance or bottlenecks in the delivery of care can be detected, monitored, and acted upon. This paper proposes the first data-driven inverse optimization approach to measuring pathway concordance in any problem context. Our specific application considers clinical pathway concordance for stage III colon cancer. We develop a novel concordance metric and demonstrate using real patient data from Ontario, Canada that it has a statistically significant association with survival. Our methodological approach considers a patient's journey as a walk in a directed graph, where the costs on the arcs are derived by solving an inverse shortest path problem. The inverse optimization model uses two sources of information to find the arc costs: reference pathways developed by a provincial cancer agency (primary) and data from real-world patient-related activity from patients with both positive and negative clinical outcomes (secondary). Thus, our inverse optimization framework extends existing models by including data points of both varying "primacy" and "alignment." Data primacy is addressed through a two-stage approach to imputing the cost vector, whereas data alignment is addressed by a hybrid objective function that aims to minimize and maximize suboptimality error for different subsets of input data. This paper was accepted by Chung Piaw Teo, Management Science Special Section on Data-Driven Prescriptive Analytics. [ABSTRACT FROM AUTHOR]

Personalized marketing in retail requires a model to predict how different marketing actions affect product choices by individual customers. Large retailers often handle millions of transactions daily, involving thousands of products in hundreds of categories. Product choice models thus need to scale to large product assortments and customer bases, without extensive product attribute information. To address these challenges, we propose a custom deep neural network model. The model incorporates bottleneck layers to encode cross-product relationships, calibrates time-series filters to capture purchase dynamics for products with different interpurchase times, and relies on weight sharing between the products to improve convergence and scale to large assortments. The model applies to loyalty card transaction data without predefined categories or product attributes to predict customer-specific purchase probabilities in response to marketing actions. In a simulation, the proposed product choice model predicts purchase decisions better than baseline methods by adjusting the predicted probabilities for the effects of recent purchases and price discounts. The improved predictions lead to substantially higher revenue gains in a simulated coupon personalization problem. We verify predictive performance using transaction data from a large retailer with experimental variation in price discounts. This paper was accepted by Gui Liberali, Management Science Special Section on Data-Driven Prescriptive Analytics. [ABSTRACT FROM AUTHOR]

The increasing impact of algorithmic decisions on people's lives compels us to scrutinize their fairness and, in particular, the disparate impacts that ostensibly color-blind algorithms can have on different groups. Examples include credit decisioning, hiring, advertising, criminal justice, personalized medicine, and targeted policy making, where in some cases legislative or regulatory frameworks for fairness exist and define specific protected classes. In this paper we study a fundamental challenge to assessing disparate impacts in practice: protected class membership is often not observed in the data. This is particularly a problem in lending and healthcare. We consider the use of an auxiliary data set, such as the U.S. census, to construct models that predict the protected class from proxy variables, such as surname and geolocation. We show that even with such data, a variety of common disparity measures are generally unidentifiable, providing a new perspective on the documented biases of popular proxy-based methods. We provide exact characterizations of the tightest possible set of all possible true disparities that are consistent with the data (and possibly additional assumptions). We further provide optimization-based algorithms for computing and visualizing these sets and statistical tools to assess sampling uncertainty. Together, these enable reliable and robust assessments of disparities—an important tool when disparity assessment can have far-reaching policy implications. We demonstrate this in two case studies with real data: mortgage lending and personalized medicine dosing. This paper was accepted by Hamid Nazerzadeh, Management Science Special Section on Data-Driven Prescriptive Analytics. [ABSTRACT FROM AUTHOR]

Many real-world optimization problems have input parameters estimated from data whose inherent imprecision can lead to fragile solutions that may impede desired objectives and/or render constraints infeasible. We propose a joint estimation and robustness optimization (JERO) framework to mitigate estimation uncertainty in optimization problems by seamlessly incorporating both the parameter estimation procedure and the optimization problem. Toward that end, we construct an uncertainty set that incorporates all of the data, and the size of the uncertainty set is based on how well the parameters are estimated from that data when using a particular estimation procedure: regressions, the least absolute shrinkage and selection operator, and maximum likelihood estimation (among others). The JERO model maximizes the uncertainty set's size and so obtains solutions that—unlike those derived from models dedicated strictly to robust optimization—are immune to parameter perturbations that would violate constraints or lead to objective function values exceeding their desired levels. We describe several applications and provide explicit formulations of the JERO framework for a variety of estimation procedures. To solve the JERO models with exponential cones, we develop a second-order conic approximation that limits errors beyond an operating range; with this approach, we can use state-of-the-art second-order conic programming solvers to solve even large-scale convex optimization problems. This paper was accepted by J. George Shanthikumar, Management Science Special Section on Data-Driven Prescriptive Analytics. [ABSTRACT FROM AUTHOR]

Motivated by the real-world problem of a logistics company, this paper proposes a novel distribution-free prescriptive analytics approach—termed kernelized empirical risk minimization (kernelized ERM)—to solve a complex two-stage capacity planning problem with multivariate demand and vector-valued capacity decisions and compares this approach both theoretically and numerically with an extension of the well-known sample average approximation (SAA) approach termed weighted SAA. Both approaches use integrated machine learning algorithms to prescribe capacities directly from historical demand and numerous features (covariates) without having to make assumptions about the underlying multivariate demand distribution. We provide extensive analytical insights into both approaches. Most important, we prove the universal approximation property for the kernelized ERM approach when using a universal (data-independent) kernel and show how out-of-sample guarantees can be derived for various kernels. We demonstrate the applicability of both approaches to a real-world planning problem and evaluate their performance relative to traditional parametric approaches that first estimate a multivariate demand distribution and then solve a stochastic optimization problem and a nonparametric approach (SAA). Our results suggest that the two prescriptive analytics approaches can result in substantial performance improvements of up to 58% compared with traditional approaches. Additional numerical analyses shed light on the behavior and performance drivers of the various approaches and demonstrate that in our case, the prescriptive approaches are much more robust to variations of exogenous cost parameters than traditional approaches. This paper was accepted by J. George Shanthikumar, Management Science Special Section on Data-Driven Prescriptive Analytics. [ABSTRACT FROM AUTHOR]

We study the problem of computing data-driven personalized reserve prices in eager second price auctions without having any assumption on valuation distributions. Here, the input is a data set that contains the submitted bids of n buyers in a set of auctions, and the problem is to return personalized reserve prices r that maximize the revenue earned on these auctions by running eager second price auctions with reserve r. For this problem, which is known to be NP complete, we present a novel linear program (LP) formulation and a rounding procedure, which achieves a 0.684 approximation. This improves over the 1 2 -approximation algorithm from Roughgarden and Wang. We show that our analysis is tight for this rounding procedure. We also bound the integrality gap of the LP, which shows that it is impossible to design an algorithm that yields an approximation factor larger than 0.828 with respect to this LP. This paper was accepted by Chung Piaw Teo, Management Science Special Section on Data-Driven Prescriptive Analytics. [ABSTRACT FROM AUTHOR]

We consider a logit model-based framework for modeling joint pricing and assortment decisions that take into account customer features. This model provides a significant advantage when one has insufficient data for any one customer and wishes to generalize learning about one customer's preferences to the population. Under this model, we study the statistical learning task of model fitting from a static store of precollected customer data. This setting, in contrast to the popular learning and earning paradigm, represents the situation many business teams encounter in which their data collection abilities have outstripped their data analysis capabilities. In this learning setting, we establish finite-sample convergence guarantees on the model parameters. The parameter convergence guarantees are then extended to out-of-sample performance guarantees in terms of revenue, in the form of a high-probability bound on the gap between the expected revenue of the best action taken under the estimated parameters and the revenue generated by a decision maker with full knowledge of the choice model. We further discuss practical implications of these bounds. We demonstrate the personalization approach using ticket purchase data from an airline carrier. This paper was accepted by J. George Shanthikumar, Management Science Special Section on Data-Driven Prescriptive Analytics. [ABSTRACT FROM AUTHOR]

The article offers information on the 2023 Information Systems Best AE Award for Management Science, with the lead line stating that Professor Gordon Burtch of Boston University has been selected for outstanding service as associate editor. Topics include Professor Burtch's efficient handling of a large number of papers, his short average turnaround time, and the sustained high quality and competence demonstrated in his work.

The article announces the nomination of Professor Brad Staats by the journal to receive the 2023 Manufacturing and Service Operations Management (MSOM) Society Best Associate Editor (AE) Award.

Entrepreneurs must choose between alternative strategies for bringing their idea to market. They face uncertainty regarding both the quality of their idea as well as the efficacy of each strategy. Although entrepreneurs can reduce this uncertainty by conducting tests, any single test conflates the signal of the efficacy of the particular strategy and the quality of the idea. Resolving this conflation requires exploring multiple strategies. Consequently, entrepreneurial choice is enhanced by finding ways to lower the cost of testing multiple strategies, receiving guidance as to the types of tests likely to reduce signal conflation, and optimally sequencing tests based on previous beliefs. This creates a role for judgment that may be provided by trusted third parties such as mentors and investors. We hypothesize that institutions that lower the cost of transmitting and aggregating judgment spur entrepreneurial performance. This paper was accepted by David Simchi-Levi, Special Section of Management Science: 65th Anniversary. [ABSTRACT FROM AUTHOR]

We trace the evolution of research on organizational learning. As organizations acquire experience, their performance typically improves at a decreasing rate. Although this learning-curve pattern is found in many industries, organizations vary in the rate at which they learn. In order to understand this variation, we separate organizational learning into four processes: search, knowledge creation, knowledge retention, and knowledge transfer. Within each process, we present research on how dimensions of experience and of the organizational context affect learning processes and outcomes. Our goals are to describe major findings and to identify opportunities for future research. The article concludes with a discussion of research directions that are likely to be productive in the future. These directions include investigating how new technological and organizational developments are likely to affect organizational learning. This paper was accepted by David Simchi-Levi, Special Section of Management Science: 65th Anniversary. [ABSTRACT FROM AUTHOR]

Many patients in need of a kidney transplant have a willing but incompatible (or poorly matched) living donor. Kidney exchange programs arrange exchanges among such patient-donor pairs, in cycles and chains of exchange, so that each patient receives a compatible kidney. Kidney exchange has become a standard form of transplantation in the United States and a few other countries, in large part because of continued attention to the operational details that arose as obstacles were overcome and new obstacles became relevant. We review some of the key operational issues in the design of successful kidney exchange programs. Kidney exchange has yet to reach its full potential, and the paper further describes some open questions that we hope will continue to attract attention from researchers interested in the operational aspects of dynamic exchange. This paper was accepted by David Simchi-Levi, Special Section of Management Science: 65th Anniversary. [ABSTRACT FROM AUTHOR]

In this paper, I provide some observations on how the academic field of operations management has changed over the past 40 years. For this purpose, I have identified and classified the operations management (OM) papers published in Management Science in 1976 and in 2016. From this review, I comment on what's changed, what's new, and what we might see in the future. In reflecting on these changes, I also document and discuss how the OM editorial structure and mission have evolved at Management Science over this time. This paper was accepted by David Simchi-Levi, Special Section of Management Science: 65th Anniversary. [ABSTRACT FROM AUTHOR]

Understanding the process of innovation has been a central concern of management researchers, but despite this progress, there remains much that we do not understand. Deepening our knowledge is critically important given the enormous environmental and social challenges we face as a society. Pursing incremental innovation will continue to be hugely important, but this paper argues that building a richer understanding of architectural or systemic innovation will also be crucial. This paper suggests that the study of organizational purpose may provide a particularly fruitful avenue for future research. This paper was accepted by David Simchi-Levi, Special Section of Management Science: 65th Anniversary. [ABSTRACT FROM AUTHOR]

In this paper, we reflect on research in decision analysis that has appeared in Management Science and its impact on decision analysis practice and applications. We consider professional applications of decision analysis in business and government settings as well as everyday conversational applications. This paper was accepted by David Simchi-Levi, Special Section of Management Science: 65th Anniversary. [ABSTRACT FROM AUTHOR]

Revenue management has evolved over the years from its origins in the airline industry into a much broader discipline that analyzes algorithmic methods for demand and marketplace management, but many outside of the discipline are not aware of this transformation. The field's transition tracks the widespread adoption of algorithmic decision-making techniques by businesses in a wide variety of industries over the last decade. We study this evolution in the field's breadth of research, with a particular focus on revenue-management papers that study online marketplaces such as e-commerce retailing, digital advertisement, and ride-hailing markets for urban transportation. This paper was accepted by David Simchi-Levi, Special Section of Management Science: 65th Anniversary. [ABSTRACT FROM AUTHOR]

This paper uses the 65th anniversary of Management Science as an opportunity to examine how well the journal has performed against its primary goal to promote development and encourage application of a science of management. We also highlight recent trends that are impacting this mission and discuss how recent initiatives address these issues. [ABSTRACT FROM AUTHOR]

I argue that academic research in accounting has strayed from producing work that is useful to either practitioners or policy makers. I use three criteria to arrive at that assessment: (i) How many products and processes have accounting research produced in the last 50 years? (ii) How much overlap do we observe between issues that Chief Financial Officers (CFOs) and Chief Executive Officers (CEOs) worry about and our published research? (iii) Is the science or the knowhow in academe in a particular area ahead of that in practice? I conjecture that tuition-funded research drives this problem. I review several initiatives that have been tried at Columbia and elsewhere (i) to better integrate academic research and practice and (ii) to disseminate our findings to practitioners. I suggest that Management Science set up a forum to encourage submissions of papers that use rigorous methods to address pressing applied problems. This paper was accepted by David Simchi-Levi, Special Section of Management Science: 65th Anniversary. [ABSTRACT FROM AUTHOR]

We use cooperative game theory to investigate multiplayer allocation problems under the almost diminishing marginal contributions (ADMC) property. This property indicates that a player's marginal contribution to a non-empty coalition decreases as the size of the coalition increases. We develop ADMC games for such problems and derive a necessary and sufficient condition for the non-emptiness of the core. When the core is non-empty, at least one extreme point exists, and the maximum number of extreme points is the total number of players. The Shapley value may not be in the core, which depends on the gap of each coalition. A player can receive a higher allocation based on the Shapley value in the core than based on the nucleolus, if the gap of the player is no greater than the gap of the complementary coalition. We also investigate the least core value for ADMC games with an empty core. To illustrate the applications of our results, we analyze a code-sharing game, a group buying game, and a scheduling profit game. This paper was accepted by Chung Piaw Teo, optimization. [ABSTRACT FROM AUTHOR]

The referral priority program--an emerging business practice adopted by a growing number of technology companies that manage a waitlist of customers--enables existing customers on the waitlist to gain priority access if they successfully refer new customers to the waitlist. Unlike more commonly used referral reward programs, this novel mechanism does not offer monetary compensation to referring customers, but leverages customers' own disutility of delays to create referral incentives. Despite this appealing feature, our queueing-game-theoretic analysis finds that the effectiveness of such a scheme as a marketing tool for customer acquisition and an operational approach for waitlist management depends crucially on the underlying market conditions, particularly the base market size of spontaneous customers. The referral priority program does not generate referrals when the base market size is either too large or too small. When customers do refer, the program could actually backfire--namely, by reducing the system throughput and customer welfare--if the base market size is intermediately large. This phenomenon occurs because the presence of referred customers severely cannibalizes the demand of spontaneous customers. We also compare the referral priority program with the referral reward program when the service provider optimally sets the admission price. Numerical study suggests that the referral priority program is more profitable than the referral reward program when the base market size is intermediately small. History: Accepted by Serguei Netessine, operations management. Supplemental Material: The online appendix is available at https://doi.org/10.1287/mnsc.2018.3034. Keywords: referrals * priority queues * system throughput * customer welfare * conversion rate * batch arrivals, 1. Introduction Many technology companies are breaking new ground today as they introduce sign-up waitlists for a limited release of their products to eager customers before a mass-market launch. Notable [...]

Product expiration is an important problem in the consumer packaged goods (CPG) industry costing l%-2% of gross retail sales and eroding industry profits substantially. It can be caused by several factors related to store operations, supply chain practices, and product characteristics. Existing methods used in the industry are inadequate to identify the causes of expiration, leading to inadequate efforts to reduce expiration. Using retail data for 768 SKUs and 10,000 stores (745,638 store-SKU-level observations), as well as upstream supply chain data from a CPG manufacturer, we show the extent to which expiration of products in retail stores is driven by case size, inventory aging in the supply chain, minimum order rules, manufacturers' incentive programs for the sales force, replenishment workload, and many control variables. A counterfactual analysis based on the model shows that our subject manufacturer can reduce expiration by up to $38.82 million per year by implementing four selected initiatives involving case size, supply chain aging, minimum order rules, and sales incentives. Further, targeted initiatives can be designed using combinations of these variables for subsets of products with the highest occurrence of expiration. History: Accepted by Serguei Netessine, operations management. Funding: The authors thank the industry collaborator AlphaCo for providing $60,000 of financial support to this study. Supplemental Material: The online appendix is available at https://doi.org/10.1287/mnsc.2018.3051. Keywords: retail operations * consumer packaged goods * product expiration. food waste * empirical * perishable inventory * supply chain management * marketing/operations interface * sustainable operations management * zero-inflated models * direct store delivery, 1. Introduction Consumer packaged goods (CPG) products, such as soft drinks, shelf-stable dry food, and health and beauty aids, that turn into waste at retail stores were estimated to cost [...]