Chun Cheng, Yossiri Adulyasak, Louis-Martin Rousseau
Problem definition: Drone delivery has recently garnered significant attention due to its potential for faster delivery at a lower cost than other delivery options. When scheduling drones from a depot for delivery to various destinations, the dispatcher must take into account the uncertain wind conditions, which affect the delivery times of drones to their destinations, leading to late deliveries. Methodology/results: To mitigate the risk of delivery delays caused by wind uncertainty, we propose a two-period drone scheduling model to robustly optimize the delivery schedule. In this framework, the scheduling decisions are made in the morning, with the provision for different delivery schedules in the afternoon that adapt to updated weather information available by midday. Our approach minimizes the essential riskiness index, which can simultaneously account for the probability of tardy delivery and the magnitude of lateness. Using wind observation data, we characterize the uncertain flight times via a cluster-wise ambiguity set, which has the benefit of tractability while avoiding overfitting the empirical distribution. A branch-and-cut (B&C) algorithm is developed for this adaptive distributionally framework to improve its scalability. Our adaptive distributionally robust model can effectively reduce lateness in out-of-sample tests compared with other classical models. The proposed B&C algorithm can solve instances to optimality within a shorter time frame than a general modeling toolbox. Managerial implications: Decision makers can use the adaptive robust model together with the cluster-wise ambiguity set to effectively reduce service lateness at customers for drone delivery systems.Funding: This work was supported by the National Natural Science Foundation of China [Grants 72101049 and 72232001], the Natural Science Foundation of Liaoning Province [Grant 2023-BS-091], the Fundamental Research Funds for the Central Universities [Grant DUT23RC(3)045], and the Major Project of the National Social Science Foundation [Grant 22&ZD151].Supplemental Material: The online appendices are available at https://doi.org/10.1287/msom.2022.0339 .
{"title":"Robust Drone Delivery with Weather Information","authors":"Chun Cheng, Yossiri Adulyasak, Louis-Martin Rousseau","doi":"10.1287/msom.2022.0339","DOIUrl":"https://doi.org/10.1287/msom.2022.0339","url":null,"abstract":"Problem definition: Drone delivery has recently garnered significant attention due to its potential for faster delivery at a lower cost than other delivery options. When scheduling drones from a depot for delivery to various destinations, the dispatcher must take into account the uncertain wind conditions, which affect the delivery times of drones to their destinations, leading to late deliveries. Methodology/results: To mitigate the risk of delivery delays caused by wind uncertainty, we propose a two-period drone scheduling model to robustly optimize the delivery schedule. In this framework, the scheduling decisions are made in the morning, with the provision for different delivery schedules in the afternoon that adapt to updated weather information available by midday. Our approach minimizes the essential riskiness index, which can simultaneously account for the probability of tardy delivery and the magnitude of lateness. Using wind observation data, we characterize the uncertain flight times via a cluster-wise ambiguity set, which has the benefit of tractability while avoiding overfitting the empirical distribution. A branch-and-cut (B&C) algorithm is developed for this adaptive distributionally framework to improve its scalability. Our adaptive distributionally robust model can effectively reduce lateness in out-of-sample tests compared with other classical models. The proposed B&C algorithm can solve instances to optimality within a shorter time frame than a general modeling toolbox. Managerial implications: Decision makers can use the adaptive robust model together with the cluster-wise ambiguity set to effectively reduce service lateness at customers for drone delivery systems.Funding: This work was supported by the National Natural Science Foundation of China [Grants 72101049 and 72232001], the Natural Science Foundation of Liaoning Province [Grant 2023-BS-091], the Fundamental Research Funds for the Central Universities [Grant DUT23RC(3)045], and the Major Project of the National Social Science Foundation [Grant 22&ZD151].Supplemental Material: The online appendices are available at https://doi.org/10.1287/msom.2022.0339 .","PeriodicalId":501267,"journal":{"name":"Manufacturing & Service Operations Management","volume":"101 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140833173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tugce Martagan, Marc Baaijens, Coen Dirckx, James Holman, Robert Meyer, Oscar Repping, Bram van Ravenstein
To support the 2024 MSOM Data-Driven Research Challenge, Merck & Co., Inc., Rahway, New Jersey (hereafter “MSD”), provides pharmaceutical manufacturing data from a continuous tablet production setting. The data set contains approximately 300 million data points related to around 75 process parameters monitored over 120 hours. In this paper, we present the data set and share our vision to inspire and facilitate new applications of operations management (OM) methodologies in pharmaceutical manufacturing. We begin with an introduction to pharmaceutical manufacturing for OM researchers and then elaborate on emerging technologies, common industry challenges, and research opportunities. We explain the data set and propose a roadmap for future research directions. Researchers are welcome to examine the proposed research questions or analyze other research questions using the data set.History: This paper has been accepted as part of the 2024 MSOM Data-Driven Research Challenge.Funding: This work was supported by The Dutch Research Council - NWO VIDI Grant.Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2024.0860
{"title":"MSD: Continuous Pharmaceutical Manufacturing Data for the 2024 MSOM Data-Driven Research Challenge","authors":"Tugce Martagan, Marc Baaijens, Coen Dirckx, James Holman, Robert Meyer, Oscar Repping, Bram van Ravenstein","doi":"10.1287/msom.2024.0860","DOIUrl":"https://doi.org/10.1287/msom.2024.0860","url":null,"abstract":"To support the 2024 MSOM Data-Driven Research Challenge, Merck & Co., Inc., Rahway, New Jersey (hereafter “MSD”), provides pharmaceutical manufacturing data from a continuous tablet production setting. The data set contains approximately 300 million data points related to around 75 process parameters monitored over 120 hours. In this paper, we present the data set and share our vision to inspire and facilitate new applications of operations management (OM) methodologies in pharmaceutical manufacturing. We begin with an introduction to pharmaceutical manufacturing for OM researchers and then elaborate on emerging technologies, common industry challenges, and research opportunities. We explain the data set and propose a roadmap for future research directions. Researchers are welcome to examine the proposed research questions or analyze other research questions using the data set.History: This paper has been accepted as part of the 2024 MSOM Data-Driven Research Challenge.Funding: This work was supported by The Dutch Research Council - NWO VIDI Grant.Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2024.0860","PeriodicalId":501267,"journal":{"name":"Manufacturing & Service Operations Management","volume":"54 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140833753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Problem definition: Ride-hailing platforms offering shared rides devote effort to reducing the trip-lengthening detours that accommodate fellow customers’ divergent transportation needs. By reducing shared-ride delay, improving shared-ride efficiency has the twin benefits of making shared rides more attractive to customers and increasing the number of customers a driver can serve per unit time. Methodology/results: We analytically model a ride-hailing platform that can offer individual rides and shared rides. We establish results that are counter to naive intuition: greater customer sensitivity to shared-ride delay and greater labor cost can reduce the value of improving shared-ride efficiency, and an increase in shared-ride efficiency can prompt a platform to add individual-ride service. We show that when network effects are small, increasing shared-ride efficiency pushes wages to extremes: if the current wage is high (low), increasing shared-ride efficiency pushes the wage higher (lower). We provide a sharp characterization of whether shared-ride efficiency and labor supply are complements or substitutes. We provide simple conditions under which increasing shared-ride efficiency reduces (alternatively, increases) labor welfare. We provide evidence that increasing shared-ride efficiency increases consumer surplus. Managerial implications: Our results inform a platform’s decision of whether to invest in improving shared-ride efficiency, as well as how to change its service offering and wage, as shared-ride efficiency improves.Supplemental Material: The online supplement is available at https://doi.org/10.1287/msom.2021.0545 .
{"title":"Shared-Ride Efficiency of Ride-Hailing Platforms","authors":"Terry A. Taylor","doi":"10.1287/msom.2021.0545","DOIUrl":"https://doi.org/10.1287/msom.2021.0545","url":null,"abstract":"Problem definition: Ride-hailing platforms offering shared rides devote effort to reducing the trip-lengthening detours that accommodate fellow customers’ divergent transportation needs. By reducing shared-ride delay, improving shared-ride efficiency has the twin benefits of making shared rides more attractive to customers and increasing the number of customers a driver can serve per unit time. Methodology/results: We analytically model a ride-hailing platform that can offer individual rides and shared rides. We establish results that are counter to naive intuition: greater customer sensitivity to shared-ride delay and greater labor cost can reduce the value of improving shared-ride efficiency, and an increase in shared-ride efficiency can prompt a platform to add individual-ride service. We show that when network effects are small, increasing shared-ride efficiency pushes wages to extremes: if the current wage is high (low), increasing shared-ride efficiency pushes the wage higher (lower). We provide a sharp characterization of whether shared-ride efficiency and labor supply are complements or substitutes. We provide simple conditions under which increasing shared-ride efficiency reduces (alternatively, increases) labor welfare. We provide evidence that increasing shared-ride efficiency increases consumer surplus. Managerial implications: Our results inform a platform’s decision of whether to invest in improving shared-ride efficiency, as well as how to change its service offering and wage, as shared-ride efficiency improves.Supplemental Material: The online supplement is available at https://doi.org/10.1287/msom.2021.0545 .","PeriodicalId":501267,"journal":{"name":"Manufacturing & Service Operations Management","volume":"112 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140804211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Problem definition: Recent global crises have caused unprecedented economic uncertainty and intensified retailers’ concerns over inventory risks. Mitigating inventory risks and incentivizing retailer orders is critical to managing retail supply chains and restoring their norms after severe impacts. We study the allocation of inventory risk using contracts in a retail supply chain with a risk-neutral manufacturer and a risk-averse retailer. We consider two factors that affect the effectiveness of contracting: (1) asymmetric risk aversion information—retailers’ attitudes are typically diverse and unknown to the manufacturer, and (2) uncertain outside opportunity—retailers typically face a volatile external business environment. Methodology/results: With a game-theoretic model that captures the interaction among risk aversion, information asymmetry, and outside opportunity, we derive the contracting equilibrium under two widely adopted risk allocation schemes—push (i.e., the retailer bears the inventory risk) and pull (i.e., the manufacturer bears the inventory risk) contracts. Contrary to the conventional wisdom that pull contracts are more effective in risk mitigation, we show that push contracts may induce larger expected order quantities and achieve the highest supply chain efficiency due to the interaction of asymmetric risk aversion information and risky outside opportunities. We also find that the manufacturer may obtain higher profits with push contracts when both the heterogeneity in the retailer’s risk attitude and the risk of the outside opportunity are sufficiently high. In addition, when the risk of the outside opportunity is in a medium range, the push contract allows the manufacturer to fully eliminate the information rent and achieve the supply chain’s first-best outcomes. We further evaluate the effects of product profitability and demand uncertainty and generalize the retailer’s risk measure to any coherent risk measure. Managerial implications: Our analysis highlights the importance of modeling asymmetric risk aversion information and risky outside opportunities in analyzing supply chain contracting. When considering these practical factors, allocating more inventory risks to a risk-averse retailer may be better than a risk-neutral manufacturer. Our results provide novel insights into the selection of proper contract types for managing inventory risks in retail supply chains.Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2022.0624 .
{"title":"Allocating Inventory Risk in Retail Supply Chains: Risk Aversion, Information Asymmetry, and Outside Opportunity","authors":"Chengfan Hou, Mengshi Lu","doi":"10.1287/msom.2022.0624","DOIUrl":"https://doi.org/10.1287/msom.2022.0624","url":null,"abstract":"Problem definition: Recent global crises have caused unprecedented economic uncertainty and intensified retailers’ concerns over inventory risks. Mitigating inventory risks and incentivizing retailer orders is critical to managing retail supply chains and restoring their norms after severe impacts. We study the allocation of inventory risk using contracts in a retail supply chain with a risk-neutral manufacturer and a risk-averse retailer. We consider two factors that affect the effectiveness of contracting: (1) asymmetric risk aversion information—retailers’ attitudes are typically diverse and unknown to the manufacturer, and (2) uncertain outside opportunity—retailers typically face a volatile external business environment. Methodology/results: With a game-theoretic model that captures the interaction among risk aversion, information asymmetry, and outside opportunity, we derive the contracting equilibrium under two widely adopted risk allocation schemes—push (i.e., the retailer bears the inventory risk) and pull (i.e., the manufacturer bears the inventory risk) contracts. Contrary to the conventional wisdom that pull contracts are more effective in risk mitigation, we show that push contracts may induce larger expected order quantities and achieve the highest supply chain efficiency due to the interaction of asymmetric risk aversion information and risky outside opportunities. We also find that the manufacturer may obtain higher profits with push contracts when both the heterogeneity in the retailer’s risk attitude and the risk of the outside opportunity are sufficiently high. In addition, when the risk of the outside opportunity is in a medium range, the push contract allows the manufacturer to fully eliminate the information rent and achieve the supply chain’s first-best outcomes. We further evaluate the effects of product profitability and demand uncertainty and generalize the retailer’s risk measure to any coherent risk measure. Managerial implications: Our analysis highlights the importance of modeling asymmetric risk aversion information and risky outside opportunities in analyzing supply chain contracting. When considering these practical factors, allocating more inventory risks to a risk-averse retailer may be better than a risk-neutral manufacturer. Our results provide novel insights into the selection of proper contract types for managing inventory risks in retail supply chains.Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2022.0624 .","PeriodicalId":501267,"journal":{"name":"Manufacturing & Service Operations Management","volume":"56 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140609077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Problem definition: The opioid epidemic is a crisis that has plagued the United States for decades. One central issue of the epidemic is inequitable access to treatment for opioid use disorder (OUD), which puts certain populations at a higher risk of opioid overdose. Methodology/results: We integrate a predictive dynamical model and a prescriptive optimization problem to compute high-quality opioid treatment facility and treatment budget allocations for each U.S. state. Our predictive model is a differential equation-based epidemiological model that captures the dynamics of the opioid epidemic. We use a process inspired by neural ordinary differential equations to fit this model to opioid epidemic data for each state and obtain estimates for unknown parameters in the model. We then incorporate this epidemiological model into a corresponding mixed-integer optimization problem (MIP) that aims to minimize the number of opioid overdose deaths and the number of people with OUD. We develop strong relaxations based on McCormick envelopes to efficiently compute approximate solutions to our MIPs that have a mean optimality gap of 3.99%. Our method provides socioeconomically equitable solutions, as it incentivizes investments in areas with higher social vulnerability (from the U.S. Centers for Disease Control’s Social Vulnerability Index) and opioid prescribing rates. On average, when allowing for overbudget solutions, our approach decreases the number of people with OUD by [Formula: see text], increases the number of people in treatment by [Formula: see text], and decreases the number of opioid-related deaths by [Formula: see text] after 2 years compared with the baseline epidemiological model’s predictions. Managerial implications: Our solutions show that policymakers should target adding treatment facilities to counties that have significantly fewer facilities than their population share and are more socially vulnerable. Furthermore, we demonstrate that our optimization approach, guided by epidemiological and socioeconomic factors, should help inform these strategic decisions, as it yields population health benefits in comparison with benchmarks based solely on population and social vulnerability.History: This paper has been accepted in the Manufacturing & Service Operations Management Frontiers in Operations Initiative.Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2023.0042 .
{"title":"Frontiers in Operations: Equitable Data-Driven Facility Location and Resource Allocation to Fight the Opioid Epidemic","authors":"Joyce Luo, Bartolomeo Stellato","doi":"10.1287/msom.2023.0042","DOIUrl":"https://doi.org/10.1287/msom.2023.0042","url":null,"abstract":"Problem definition: The opioid epidemic is a crisis that has plagued the United States for decades. One central issue of the epidemic is inequitable access to treatment for opioid use disorder (OUD), which puts certain populations at a higher risk of opioid overdose. Methodology/results: We integrate a predictive dynamical model and a prescriptive optimization problem to compute high-quality opioid treatment facility and treatment budget allocations for each U.S. state. Our predictive model is a differential equation-based epidemiological model that captures the dynamics of the opioid epidemic. We use a process inspired by neural ordinary differential equations to fit this model to opioid epidemic data for each state and obtain estimates for unknown parameters in the model. We then incorporate this epidemiological model into a corresponding mixed-integer optimization problem (MIP) that aims to minimize the number of opioid overdose deaths and the number of people with OUD. We develop strong relaxations based on McCormick envelopes to efficiently compute approximate solutions to our MIPs that have a mean optimality gap of 3.99%. Our method provides socioeconomically equitable solutions, as it incentivizes investments in areas with higher social vulnerability (from the U.S. Centers for Disease Control’s Social Vulnerability Index) and opioid prescribing rates. On average, when allowing for overbudget solutions, our approach decreases the number of people with OUD by [Formula: see text], increases the number of people in treatment by [Formula: see text], and decreases the number of opioid-related deaths by [Formula: see text] after 2 years compared with the baseline epidemiological model’s predictions. Managerial implications: Our solutions show that policymakers should target adding treatment facilities to counties that have significantly fewer facilities than their population share and are more socially vulnerable. Furthermore, we demonstrate that our optimization approach, guided by epidemiological and socioeconomic factors, should help inform these strategic decisions, as it yields population health benefits in comparison with benchmarks based solely on population and social vulnerability.History: This paper has been accepted in the Manufacturing & Service Operations Management Frontiers in Operations Initiative.Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2023.0042 .","PeriodicalId":501267,"journal":{"name":"Manufacturing & Service Operations Management","volume":"87 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140570095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rakesh Allu, Maya Ganesh, Sarang Deo, Sripad K. Devalkar
Problem definition: Beneficiaries of social assistance programs with transfers of undifferentiated commodities often have a designated agent to collect their entitlements from. This gives monopoly power to agents over beneficiaries. When coupled with weak government monitoring, agents do not have incentives to adhere to stipulated operating guidelines, leading to reduced uptake by beneficiaries. Some governments are attempting to break the monopoly by allowing beneficiaries to choose agents. However, the impact of choice on uptake may be limited by lack of alternate agents in beneficiaries’ vicinities, restricted ability of agents to compete with undifferentiated commodities, and collusion among agents. Methodology/results: Using a reverse difference-in-differences framework on data from a food security program in two neighboring states in India, Andhra Pradesh and Telangana, we find that providing agent choice results in a 6.6% increase in the quantity of entitlements collected by the beneficiary households. We also find that increase in uptake is about four times higher in regions with high agent density compared with those with low agent density. This emphasizes the importance of having an alternate agent in the vicinity for choice to be effective. Nearly all of the increase in uptake is attributable to new beneficiaries collecting entitlements from their preassigned agent. This is suggestive of agents improving adherence to operating guidelines in response to choice. We find associative evidence for this response in the number of days agents keep their shops open. Managerial implications: Governments executing in-kind transfers of undifferentiated commodities are piloting interventions to provide choice to their beneficiaries. Replacement of in-kind transfers with cash, an increasingly popular intervention, may be challenging in volatile markets, as the magnitude of the transfer needs to be periodically adjusted. Our results indicate that alternate designs of providing choice even in a limited form, that is, the place where the beneficiaries can collect their entitlements with products and prices fixed, can present a viable alternative.Funding: This research was partially supported by a grant from the Omidyar Network to the Digital Identity Research Initiative at the Indian School of Business.Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2022.0528 .
{"title":"Technology-Enabled Agent Choice and Uptake of Social Assistance Programs: Evidence from India’s Food Security Program","authors":"Rakesh Allu, Maya Ganesh, Sarang Deo, Sripad K. Devalkar","doi":"10.1287/msom.2022.0528","DOIUrl":"https://doi.org/10.1287/msom.2022.0528","url":null,"abstract":"Problem definition: Beneficiaries of social assistance programs with transfers of undifferentiated commodities often have a designated agent to collect their entitlements from. This gives monopoly power to agents over beneficiaries. When coupled with weak government monitoring, agents do not have incentives to adhere to stipulated operating guidelines, leading to reduced uptake by beneficiaries. Some governments are attempting to break the monopoly by allowing beneficiaries to choose agents. However, the impact of choice on uptake may be limited by lack of alternate agents in beneficiaries’ vicinities, restricted ability of agents to compete with undifferentiated commodities, and collusion among agents. Methodology/results: Using a reverse difference-in-differences framework on data from a food security program in two neighboring states in India, Andhra Pradesh and Telangana, we find that providing agent choice results in a 6.6% increase in the quantity of entitlements collected by the beneficiary households. We also find that increase in uptake is about four times higher in regions with high agent density compared with those with low agent density. This emphasizes the importance of having an alternate agent in the vicinity for choice to be effective. Nearly all of the increase in uptake is attributable to new beneficiaries collecting entitlements from their preassigned agent. This is suggestive of agents improving adherence to operating guidelines in response to choice. We find associative evidence for this response in the number of days agents keep their shops open. Managerial implications: Governments executing in-kind transfers of undifferentiated commodities are piloting interventions to provide choice to their beneficiaries. Replacement of in-kind transfers with cash, an increasingly popular intervention, may be challenging in volatile markets, as the magnitude of the transfer needs to be periodically adjusted. Our results indicate that alternate designs of providing choice even in a limited form, that is, the place where the beneficiaries can collect their entitlements with products and prices fixed, can present a viable alternative.Funding: This research was partially supported by a grant from the Omidyar Network to the Digital Identity Research Initiative at the Indian School of Business.Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2022.0528 .","PeriodicalId":501267,"journal":{"name":"Manufacturing & Service Operations Management","volume":"123 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140570007","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Irene Lo, Vahideh Manshadi, Scott Rodilitz, Ali Shameli
Problem definition: Volunteer crowdsourcing platforms match volunteers with tasks that are often recurring. To ensure completion of such tasks, platforms frequently use a lever known as “adoption,” which amounts to a commitment by the volunteer to repeatedly perform the task. Despite reducing match uncertainty, high levels of adoption can decrease the probability of forming new matches, which in turn can suppress growth. We study how platforms should manage this trade-off. Our research is motivated by a collaboration with Food Rescue U.S. (FRUS), a volunteer-based food recovery organization active in more than 30 locations. For platforms such as FRUS, effectively using nonmonetary levers, such as adoption, is critical. Methodology/results: Motivated by the volunteer management literature and our analysis of FRUS data, we develop a model for two-sided markets that repeatedly match volunteers with tasks. We study the platform’s optimal policy for setting the adoption level to maximize the total discounted number of matches. When market participants are homogeneous, we fully characterize the optimal myopic policy and show that it takes a simple extreme form: depending on volunteer characteristics and market thickness, either allow for full adoption or disallow adoption. In the long run, we show that such a policy is either optimal or achieves a constant-factor approximation. We further extend our analysis to settings with heterogeneity and find that the structure of the optimal myopic policy remains the same if volunteers are heterogeneous. However, if tasks are heterogeneous, it can be optimal to only allow adoption for the harder-to-match tasks. Managerial implications: Our work sheds light on how two-sided platforms need to carefully control the double-edged impacts that commitment levers have on growth and engagement. Setting a misguided adoption level may result in marketplace decay. At the same time, a one-size-fits-all solution may not be effective, as the optimal design crucially depends on the characteristics of the volunteer population.Supplemental Material: The online appendices are available at https://doi.org/10.1287/msom.2020.0426 .
{"title":"Commitment on Volunteer Crowdsourcing Platforms: Implications for Growth and Engagement","authors":"Irene Lo, Vahideh Manshadi, Scott Rodilitz, Ali Shameli","doi":"10.1287/msom.2020.0426","DOIUrl":"https://doi.org/10.1287/msom.2020.0426","url":null,"abstract":"Problem definition: Volunteer crowdsourcing platforms match volunteers with tasks that are often recurring. To ensure completion of such tasks, platforms frequently use a lever known as “adoption,” which amounts to a commitment by the volunteer to repeatedly perform the task. Despite reducing match uncertainty, high levels of adoption can decrease the probability of forming new matches, which in turn can suppress growth. We study how platforms should manage this trade-off. Our research is motivated by a collaboration with Food Rescue U.S. (FRUS), a volunteer-based food recovery organization active in more than 30 locations. For platforms such as FRUS, effectively using nonmonetary levers, such as adoption, is critical. Methodology/results: Motivated by the volunteer management literature and our analysis of FRUS data, we develop a model for two-sided markets that repeatedly match volunteers with tasks. We study the platform’s optimal policy for setting the adoption level to maximize the total discounted number of matches. When market participants are homogeneous, we fully characterize the optimal myopic policy and show that it takes a simple extreme form: depending on volunteer characteristics and market thickness, either allow for full adoption or disallow adoption. In the long run, we show that such a policy is either optimal or achieves a constant-factor approximation. We further extend our analysis to settings with heterogeneity and find that the structure of the optimal myopic policy remains the same if volunteers are heterogeneous. However, if tasks are heterogeneous, it can be optimal to only allow adoption for the harder-to-match tasks. Managerial implications: Our work sheds light on how two-sided platforms need to carefully control the double-edged impacts that commitment levers have on growth and engagement. Setting a misguided adoption level may result in marketplace decay. At the same time, a one-size-fits-all solution may not be effective, as the optimal design crucially depends on the characteristics of the volunteer population.Supplemental Material: The online appendices are available at https://doi.org/10.1287/msom.2020.0426 .","PeriodicalId":501267,"journal":{"name":"Manufacturing & Service Operations Management","volume":"27 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140570098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Problem definition: Most of the display advertising inventory is sold through real-time auctions. The participants of these auctions are typically bidders (Google, Criteo, RTB House, and Trade Desk for instance) that participate on behalf of advertisers. In order to estimate the value of each display opportunity, they usually train advanced machine learning algorithms using historical data. In the labeled training set, the inputs are vectors of features representing each display opportunity, and the labels are the generated rewards. In practice, the rewards are given by the advertiser and are tied to whether a particular user converts. Consequently, the rewards are aggregated at the user level and never observed at the display level. A fundamental task that has, to the best of our knowledge, been overlooked is to account for this mismatch and split, or attribute, the rewards at the right granularity level before training a learning algorithm. We call this the label attribution problem. Methodology/results: In this paper, we develop an approach to the label attribution problem, which is both theoretically justified and practical. In particular, we develop a fixed point algorithm that allows for large-scale implementation and showcase our solution using a large-scale publicly available data set from Criteo, a large demand-side platform. We dub our approach the fixed point label attribution algorithm. Managerial implications: There is often a hidden leap of faith when transforming the advertiser’s signal into display labeling. Demand Side Platforms providers should be careful when building their machine learning pipeline and carefully solve the label attribution step.
问题定义:大部分显示广告库存都是通过实时拍卖出售的。这些拍卖的参与者通常是代表广告商参与拍卖的竞标者(如 Google、Criteo、RTB House 和 Trade Desk)。为了估算每个展示机会的价值,他们通常使用历史数据训练高级机器学习算法。在有标签的训练集中,输入是代表每个展示机会的特征向量,而标签则是生成的奖励。在实践中,奖励由广告商提供,并与特定用户是否转化挂钩。因此,奖励是在用户层面汇总的,从未在展示层面观察到。据我们所知,一个被忽视的基本任务就是在训练学习算法之前,考虑到这种不匹配,并在正确的粒度水平上分割或归属奖励。我们称之为标签归属问题。方法/结果:在本文中,我们针对标签归属问题开发了一种既有理论依据又切实可行的方法。特别是,我们开发了一种可大规模实施的定点算法,并使用来自大型需求方平台 Criteo 的大规模公开数据集展示了我们的解决方案。我们将这种方法命名为定点标签归因算法。管理意义:在将广告商的信号转化为展示标签时,往往存在着隐性的信仰飞跃。需求方平台提供商在构建机器学习管道时应小心谨慎,仔细解决标签归因步骤。
{"title":"Fixed Point Label Attribution for Real-Time Bidding","authors":"Martin Bompaire, Antoine Désir, Benjamin Heymann","doi":"10.1287/msom.2021.0611","DOIUrl":"https://doi.org/10.1287/msom.2021.0611","url":null,"abstract":"Problem definition: Most of the display advertising inventory is sold through real-time auctions. The participants of these auctions are typically bidders (Google, Criteo, RTB House, and Trade Desk for instance) that participate on behalf of advertisers. In order to estimate the value of each display opportunity, they usually train advanced machine learning algorithms using historical data. In the labeled training set, the inputs are vectors of features representing each display opportunity, and the labels are the generated rewards. In practice, the rewards are given by the advertiser and are tied to whether a particular user converts. Consequently, the rewards are aggregated at the user level and never observed at the display level. A fundamental task that has, to the best of our knowledge, been overlooked is to account for this mismatch and split, or attribute, the rewards at the right granularity level before training a learning algorithm. We call this the label attribution problem. Methodology/results: In this paper, we develop an approach to the label attribution problem, which is both theoretically justified and practical. In particular, we develop a fixed point algorithm that allows for large-scale implementation and showcase our solution using a large-scale publicly available data set from Criteo, a large demand-side platform. We dub our approach the fixed point label attribution algorithm. Managerial implications: There is often a hidden leap of faith when transforming the advertiser’s signal into display labeling. Demand Side Platforms providers should be careful when building their machine learning pipeline and carefully solve the label attribution step.","PeriodicalId":501267,"journal":{"name":"Manufacturing & Service Operations Management","volume":"12 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140302680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Miao Bai, Ying Cui, Guangwen Kong, Anthony Zhenhuan Zhang
Problem definition: Public health interventions, such as social distancing and lockdown, play an important role in containing infectious disease outbreaks, such as coronavirus disease 2019 (COVID-19). Yet, these interventions could cause significant financial losses because of the disruption to regular socioeconomic activities. Moreover, an individual’s activity level is influenced not only by public health policies but also by one’s perception of the disease burden of infection. Strategic planning is required to optimize the timing and intensity of these public health interventions by considering individual responses. Methodology/results: We use the multinomial logit choice model to characterize individual reactions to the risk of infection and public health interventions and integrate it into a repeated Stackelberg game with the susceptible-infected-recovered disease transmission dynamics. We find that the individual equilibrium activity level is higher than the socially optimal activity level because of an individual’s ignorance of the negative externality imposed on others. As a result, implementing lockdown and social distancing policies at moderate disease prevalence may be equivalently critical, if not more, compared with their implementations when the disease prevalence is at its peak level. To verify these findings, we conduct numerical studies based on representative COVID-19 data in Minnesota. Managerial implications: Our results call for policymakers’ attention to consider the impact of individuals’ responses in the planning for different pandemic containment measures. Individuals’ responses in the pandemic may significantly affect the optimal implementation of lockdown and social distancing policies.Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2022.0514 .
{"title":"No Panic in Pandemic: The Impact of Individual Choice on Public Health Policy","authors":"Miao Bai, Ying Cui, Guangwen Kong, Anthony Zhenhuan Zhang","doi":"10.1287/msom.2022.0514","DOIUrl":"https://doi.org/10.1287/msom.2022.0514","url":null,"abstract":"Problem definition: Public health interventions, such as social distancing and lockdown, play an important role in containing infectious disease outbreaks, such as coronavirus disease 2019 (COVID-19). Yet, these interventions could cause significant financial losses because of the disruption to regular socioeconomic activities. Moreover, an individual’s activity level is influenced not only by public health policies but also by one’s perception of the disease burden of infection. Strategic planning is required to optimize the timing and intensity of these public health interventions by considering individual responses. Methodology/results: We use the multinomial logit choice model to characterize individual reactions to the risk of infection and public health interventions and integrate it into a repeated Stackelberg game with the susceptible-infected-recovered disease transmission dynamics. We find that the individual equilibrium activity level is higher than the socially optimal activity level because of an individual’s ignorance of the negative externality imposed on others. As a result, implementing lockdown and social distancing policies at moderate disease prevalence may be equivalently critical, if not more, compared with their implementations when the disease prevalence is at its peak level. To verify these findings, we conduct numerical studies based on representative COVID-19 data in Minnesota. Managerial implications: Our results call for policymakers’ attention to consider the impact of individuals’ responses in the planning for different pandemic containment measures. Individuals’ responses in the pandemic may significantly affect the optimal implementation of lockdown and social distancing policies.Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2022.0514 .","PeriodicalId":501267,"journal":{"name":"Manufacturing & Service Operations Management","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140201785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Problem definition: Product service plays a crucial role for brands to retain customers and spur revenue growth. It is, however, often outsourced to a third-party provider, driven by cost savings and the ability to focus on core businesses. Although there is a large body of literature studying service outsourcing, the impact of service environment uncertainty (i.e., changing customer needs and shifting resource requirements) has received sparse attention in the past but is becoming a major concern because of increased market turbulence. This research explores how environment uncertainty in service provision influences a brand’s intent to outsource, and, if the brand decides to outsource, how it can retain the potential cost advantages offered by a third-party provider. Methodology/results: This research develops a normative model to explore key drivers that impact service outsourcing outcomes under environment uncertainty and partial observability. We find that environment uncertainty can accelerate a brand’s propensity to outsource, and a brand typically benefits from outsourcing initially. Yet, we show that such benefits can dissipate over time because of partial observability. Monitoring efforts help to mitigate the adverse impact of environment uncertainty and partial observability, but cannot attain anticipated outsourcing benefits unless monitoring is costless. In contrast, nudging service providers to self-report the cost of resources is effective even if the monitoring cost is high. Managerial implications: Brands should carefully consider environment uncertainty, partial observability, and monitoring ability when deciding whether to outsource product services to third-party providers. A heuristic monitoring policy can be effective when the monitoring cost is very high or very low but can perform poorly when the monitoring cost is in the intermediate range. Thus, outsourcing is more attractive when environment uncertainty is significant, but the value of outsourcing can only be realized when (a) partial observability is insignificant, (b) monitoring is inexpensive, or (c) provider self-reporting can be nudged. If none of the conditions hold, then the brand can suffer significant losses from the anticipated benefits of product service outsourcing.Funding: This research is partially supported by the first author's 2022 Dean’s Excellence Summer Research Grant from W. P. Carey School of Business, Arizona State University.Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2022.0222 .
问题定义:产品服务对品牌留住客户和刺激收入增长起着至关重要的作用。然而,出于节约成本和专注于核心业务的考虑,产品服务往往被外包给第三方供应商。虽然有大量文献研究服务外包,但服务环境不确定性(即不断变化的客户需求和资源需求的变化)的影响过去很少受到关注,但由于市场动荡加剧,它正成为一个主要问题。本研究探讨了服务提供环境的不确定性如何影响品牌的外包意向,以及如果品牌决定外包,如何保留第三方供应商提供的潜在成本优势。方法/结果:本研究建立了一个规范模型,以探讨在环境不确定和部分可观察性条件下影响服务外包结果的关键驱动因素。我们发现,环境的不确定性会加速品牌的外包倾向,品牌通常会在初期从外包中获益。然而,我们发现,由于部分可观测性,这种好处会随着时间的推移而消失。监测工作有助于减轻环境不确定性和部分可观测性的不利影响,但除非监测不需要成本,否则无法实现预期的外包效益。相反,即使监控成本很高,鼓励服务提供商自我报告资源成本也是有效的。管理意义:品牌在决定是否将产品服务外包给第三方供应商时,应仔细考虑环境的不确定性、部分可观察性和监控能力。当监控成本很高或很低时,启发式监控政策会很有效,但当监控成本处于中间范围时,监控政策就会表现不佳。因此,当环境的不确定性很大时,外包更有吸引力,但只有在以下情况下,外包的价值才能实现:(a) 部分可观测性微不足道;(b) 监控成本低廉;或 (c) 可以鼓励供应商自我报告。如果上述条件都不成立,那么品牌就会因产品服务外包的预期效益而蒙受巨大损失:本研究部分由第一作者获得亚利桑那州立大学 W. P. 凯里商学院 2022 年院长优秀暑期研究奖学金资助:在线附录见 https://doi.org/10.1287/msom.2022.0222 。
{"title":"Product Service Outsourcing: Impact of Environment Uncertainty and Partial Observability","authors":"Yimin Wang, Mei Li, Ning Ma, Heng Zhang","doi":"10.1287/msom.2022.0222","DOIUrl":"https://doi.org/10.1287/msom.2022.0222","url":null,"abstract":"Problem definition: Product service plays a crucial role for brands to retain customers and spur revenue growth. It is, however, often outsourced to a third-party provider, driven by cost savings and the ability to focus on core businesses. Although there is a large body of literature studying service outsourcing, the impact of service environment uncertainty (i.e., changing customer needs and shifting resource requirements) has received sparse attention in the past but is becoming a major concern because of increased market turbulence. This research explores how environment uncertainty in service provision influences a brand’s intent to outsource, and, if the brand decides to outsource, how it can retain the potential cost advantages offered by a third-party provider. Methodology/results: This research develops a normative model to explore key drivers that impact service outsourcing outcomes under environment uncertainty and partial observability. We find that environment uncertainty can accelerate a brand’s propensity to outsource, and a brand typically benefits from outsourcing initially. Yet, we show that such benefits can dissipate over time because of partial observability. Monitoring efforts help to mitigate the adverse impact of environment uncertainty and partial observability, but cannot attain anticipated outsourcing benefits unless monitoring is costless. In contrast, nudging service providers to self-report the cost of resources is effective even if the monitoring cost is high. Managerial implications: Brands should carefully consider environment uncertainty, partial observability, and monitoring ability when deciding whether to outsource product services to third-party providers. A heuristic monitoring policy can be effective when the monitoring cost is very high or very low but can perform poorly when the monitoring cost is in the intermediate range. Thus, outsourcing is more attractive when environment uncertainty is significant, but the value of outsourcing can only be realized when (a) partial observability is insignificant, (b) monitoring is inexpensive, or (c) provider self-reporting can be nudged. If none of the conditions hold, then the brand can suffer significant losses from the anticipated benefits of product service outsourcing.Funding: This research is partially supported by the first author's 2022 Dean’s Excellence Summer Research Grant from W. P. Carey School of Business, Arizona State University.Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2022.0222 .","PeriodicalId":501267,"journal":{"name":"Manufacturing & Service Operations Management","volume":"23 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140201856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}