This paper studies the value of data for pricing purposes. Although pricing is central across industries, little is known about the minimal amount of data needed to achieve good pricing decisions. The present paper proposes a novel approach to quantify the informational content of data, through the introduction of a new class of robust data-driven policies and the development of factor-revealing dynamic programs. Studying the prototypical case of data coming in the form of samples from the willingness to pay of customers, we show that even a few samples (as few as 10) go a very long way in uncovering “good” prices. For example, quite strikingly, against a general class of distributions (monotone increasing hazard rate distributions), a single observation guarantees 64% of the performance an oracle with full knowledge of the distribution would achieve, two samples suffice to ensure 71%, and 10 samples guarantee 80% of such performance.
{"title":"Pricing with Samples","authors":"Amine Allouah, Achraf Bahamou, Omar Besbes","doi":"10.1287/opre.2021.2200","DOIUrl":"https://doi.org/10.1287/opre.2021.2200","url":null,"abstract":"This paper studies the value of data for pricing purposes. Although pricing is central across industries, little is known about the minimal amount of data needed to achieve good pricing decisions. The present paper proposes a novel approach to quantify the informational content of data, through the introduction of a new class of robust data-driven policies and the development of factor-revealing dynamic programs. Studying the prototypical case of data coming in the form of samples from the willingness to pay of customers, we show that even a few samples (as few as 10) go a very long way in uncovering “good” prices. For example, quite strikingly, against a general class of distributions (monotone increasing hazard rate distributions), a single observation guarantees 64% of the performance an oracle with full knowledge of the distribution would achieve, two samples suffice to ensure 71%, and 10 samples guarantee 80% of such performance.","PeriodicalId":19546,"journal":{"name":"Oper. Res.","volume":"119 1","pages":"1088-1104"},"PeriodicalIF":0.0,"publicationDate":"2022-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88247236","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}
A construction of the dual of a periodical formulation of infinite-horizon linear stochastic programs with a discount factor is discussed. The dual problem is used for computing a deterministic upper bound for the optimal value of the considered multistage stochastic program. Numerical experiments demonstrate behavior of that upper bound, especially when the discount factor is close to one.
{"title":"Dual Bounds for Periodical Stochastic Programs","authors":"A. Shapiro, Yi Cheng","doi":"10.1287/opre.2021.2245","DOIUrl":"https://doi.org/10.1287/opre.2021.2245","url":null,"abstract":"A construction of the dual of a periodical formulation of infinite-horizon linear stochastic programs with a discount factor is discussed. The dual problem is used for computing a deterministic upper bound for the optimal value of the considered multistage stochastic program. Numerical experiments demonstrate behavior of that upper bound, especially when the discount factor is close to one.","PeriodicalId":19546,"journal":{"name":"Oper. Res.","volume":"49 1","pages":"120-128"},"PeriodicalIF":0.0,"publicationDate":"2022-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85575546","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}
In Weighted Scoring Rules and Convex Risk Measures, Dr. Zachary J. Smith and Prof. J. Eric Bickel (both at the University of Texas at Austin) present a general connection between weighted proper scoring rules and investment decisions involving the minimization of a convex risk measure. Weighted scoring rules are quantitative tools for evaluating the accuracy of probabilistic forecasts relative to a baseline distribution. In their paper, the authors demonstrate that the relationship between convex risk measures and weighted scoring rules relates closely with previous economic characterizations of weighted scores based on expected utility maximization. As illustrative examples, the authors study two families of weighted scoring rules based on phi-divergences (generalizations of the Weighted Power and Weighted Pseudospherical Scoring rules) along with their corresponding risk measures. The paper will be of particular interest to the decision analysis and mathematical finance communities as well as those interested in the elicitation and evaluation of subjective probabilistic forecasts.
在加权评分规则和凸风险度量中，Zachary J. Smith博士和J. Eric Bickel教授(均来自德克萨斯大学奥斯汀分校)提出了加权适当评分规则和涉及凸风险度量最小化的投资决策之间的一般联系。加权评分规则是评估相对于基线分布的概率预测准确性的定量工具。在他们的论文中，作者证明了凸风险度量和加权评分规则之间的关系与先前基于期望效用最大化的加权评分的经济特征密切相关。作为示例，作者研究了基于phi-divergence的两类加权评分规则(加权幂和加权伪球面评分规则的推广)及其相应的风险度量。本文将对决策分析和数学金融社区以及对主观概率预测的启发和评估感兴趣的人特别感兴趣。
{"title":"Weighted Scoring Rules and Convex Risk Measures","authors":"Zachary J. Smith, J. Bickel","doi":"10.1287/opre.2021.2190","DOIUrl":"https://doi.org/10.1287/opre.2021.2190","url":null,"abstract":"In Weighted Scoring Rules and Convex Risk Measures, Dr. Zachary J. Smith and Prof. J. Eric Bickel (both at the University of Texas at Austin) present a general connection between weighted proper scoring rules and investment decisions involving the minimization of a convex risk measure. Weighted scoring rules are quantitative tools for evaluating the accuracy of probabilistic forecasts relative to a baseline distribution. In their paper, the authors demonstrate that the relationship between convex risk measures and weighted scoring rules relates closely with previous economic characterizations of weighted scores based on expected utility maximization. As illustrative examples, the authors study two families of weighted scoring rules based on phi-divergences (generalizations of the Weighted Power and Weighted Pseudospherical Scoring rules) along with their corresponding risk measures. The paper will be of particular interest to the decision analysis and mathematical finance communities as well as those interested in the elicitation and evaluation of subjective probabilistic forecasts.","PeriodicalId":19546,"journal":{"name":"Oper. Res.","volume":"25 1","pages":"3371-3385"},"PeriodicalIF":0.0,"publicationDate":"2022-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84203549","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}
When Should I Transfer This Customer? “Please hold while I transfer you to next level of support.” Most of us have been on the receiving end of this message. In this study, the authors look at transfers from the service worker’s perspective. They create an online experiment in which participants play the role of call center agents who need to decide whether to transfer a virtual service request or continue attempting to resolve it. Consistent with compensation schemes common in call centers, participants receive a bonus for each successful resolution and may pay a penalty if they transfer. The authors find that these incentives generally work well; however, agents appear to overreact to transfer penalties by handling more requests than they should and transferring too few requests. Although this may be good news for customers who dislike being transferred, such behaviors may be costly for the call center; thus, managers need to be careful when rolling out complex compensation schemes.
{"title":"The Gatekeeper's Dilemma: \"When Should I Transfer This Customer?\"","authors":"Brett A. Hathaway, E. Kagan, M. Dada","doi":"10.1287/opre.2021.2211","DOIUrl":"https://doi.org/10.1287/opre.2021.2211","url":null,"abstract":"When Should I Transfer This Customer? “Please hold while I transfer you to next level of support.” Most of us have been on the receiving end of this message. In this study, the authors look at transfers from the service worker’s perspective. They create an online experiment in which participants play the role of call center agents who need to decide whether to transfer a virtual service request or continue attempting to resolve it. Consistent with compensation schemes common in call centers, participants receive a bonus for each successful resolution and may pay a penalty if they transfer. The authors find that these incentives generally work well; however, agents appear to overreact to transfer penalties by handling more requests than they should and transferring too few requests. Although this may be good news for customers who dislike being transferred, such behaviors may be costly for the call center; thus, managers need to be careful when rolling out complex compensation schemes.","PeriodicalId":19546,"journal":{"name":"Oper. Res.","volume":"8 1","pages":"843-859"},"PeriodicalIF":0.0,"publicationDate":"2022-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79425457","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}
The quality of radiation therapy treatment plans and the efficiency of the planning process are heavily affected by the choice of planning objectives. Although simple objectives enable efficient treatment planning, the resulting treatment quality might not be clinically acceptable; complex objectives can generate high-quality treatment, yet the planning process becomes computationally prohibitive. In “Objective Selection for Cancer Treatment: An Inverse Optimization Approach,” by integrating inverse optimization and feature selection techniques, Ajayi, Lee, and Schaefer propose a novel objective selection method that uses historical radiation therapy treatment data to infer a set of planning objectives that are tractable and parsimonious yet clinically effective. Although the objective selection problem is a large-scale bilevel mixed-integer program, the authors propose various solution approaches inspired by feature selection greedy algorithms and patient-specific anatomical characteristics.
{"title":"Objective Selection for Cancer Treatment: An Inverse Optimization Approach","authors":"T. Ajayi, Taewoo Lee, A. Schaefer","doi":"10.1287/opre.2021.2192","DOIUrl":"https://doi.org/10.1287/opre.2021.2192","url":null,"abstract":"The quality of radiation therapy treatment plans and the efficiency of the planning process are heavily affected by the choice of planning objectives. Although simple objectives enable efficient treatment planning, the resulting treatment quality might not be clinically acceptable; complex objectives can generate high-quality treatment, yet the planning process becomes computationally prohibitive. In “Objective Selection for Cancer Treatment: An Inverse Optimization Approach,” by integrating inverse optimization and feature selection techniques, Ajayi, Lee, and Schaefer propose a novel objective selection method that uses historical radiation therapy treatment data to infer a set of planning objectives that are tractable and parsimonious yet clinically effective. Although the objective selection problem is a large-scale bilevel mixed-integer program, the authors propose various solution approaches inspired by feature selection greedy algorithms and patient-specific anatomical characteristics.","PeriodicalId":19546,"journal":{"name":"Oper. Res.","volume":"11 1","pages":"1717-1738"},"PeriodicalIF":0.0,"publicationDate":"2022-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76438193","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}
Utility-based shortfall risk measures effectively captures a decision maker's risk attitude on tail losses. In this paper, we consider a situation where the decision maker's risk attitude toward tail losses is ambiguous and introduce a robust version of shortfall risk, which mitigates the risk arising from such ambiguity. Specifically, we use some available partial information or subjective judgement to construct a set of plausible utility-based shortfall risk measures and define a so-called preference robust shortfall risk as through the worst risk that can be measured in this (ambiguity) set. We then apply the robust shortfall risk paradigm to optimal decision-making problems and demonstrate how the latter can be reformulated as tractable convex programs when the underlying exogenous uncertainty is discretely distributed.
{"title":"Shortfall Risk Models When Information on Loss Function Is Incomplete","authors":"E. Delage, Shaoyan Guo, Huifu Xu","doi":"10.1287/opre.2021.2212","DOIUrl":"https://doi.org/10.1287/opre.2021.2212","url":null,"abstract":"Utility-based shortfall risk measures effectively captures a decision maker's risk attitude on tail losses. In this paper, we consider a situation where the decision maker's risk attitude toward tail losses is ambiguous and introduce a robust version of shortfall risk, which mitigates the risk arising from such ambiguity. Specifically, we use some available partial information or subjective judgement to construct a set of plausible utility-based shortfall risk measures and define a so-called preference robust shortfall risk as through the worst risk that can be measured in this (ambiguity) set. We then apply the robust shortfall risk paradigm to optimal decision-making problems and demonstrate how the latter can be reformulated as tractable convex programs when the underlying exogenous uncertainty is discretely distributed.","PeriodicalId":19546,"journal":{"name":"Oper. Res.","volume":"26 1","pages":"3511-3518"},"PeriodicalIF":0.0,"publicationDate":"2022-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87134830","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}
Jacob B. Feldman, Dennis J. Zhang, Xiaofei Liu, N. Zhang
We compare the performance of two approaches for finding the optimal set of products to display to customers landing on Alibaba's two online marketplaces, Tmall and Taobao. Both approaches were placed online simultaneously and tested on real customers for one week. The first approach we test is Alibaba's current practice. This procedure embeds thousands of product and customer features within a sophisticated machine-learning algorithm that is used to estimate the purchase probabilities of each product for the customer at hand. Our second approach uses a featurized multinomial logit (MNL) model to predict purchase probabilities for each arriving customer. In this way, we use less sophisticated machinery to estimate purchase probabilities, but we employ a model that was built to capture customer purchasing behavior and, more specifically, substitution patterns. Our experiments show that despite the lower prediction power of our MNL-based approach, it generates significantly higher revenue per visit compared with the current machine-learning algorithm with the same set of features.
{"title":"Customer Choice Models vs. Machine Learning: Finding Optimal Product Displays on Alibaba","authors":"Jacob B. Feldman, Dennis J. Zhang, Xiaofei Liu, N. Zhang","doi":"10.1287/opre.2021.2158","DOIUrl":"https://doi.org/10.1287/opre.2021.2158","url":null,"abstract":"We compare the performance of two approaches for finding the optimal set of products to display to customers landing on Alibaba's two online marketplaces, Tmall and Taobao. Both approaches were placed online simultaneously and tested on real customers for one week. The first approach we test is Alibaba's current practice. This procedure embeds thousands of product and customer features within a sophisticated machine-learning algorithm that is used to estimate the purchase probabilities of each product for the customer at hand. Our second approach uses a featurized multinomial logit (MNL) model to predict purchase probabilities for each arriving customer. In this way, we use less sophisticated machinery to estimate purchase probabilities, but we employ a model that was built to capture customer purchasing behavior and, more specifically, substitution patterns. Our experiments show that despite the lower prediction power of our MNL-based approach, it generates significantly higher revenue per visit compared with the current machine-learning algorithm with the same set of features.","PeriodicalId":19546,"journal":{"name":"Oper. Res.","volume":"16 1","pages":"309-328"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84086206","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}
Fabio Furini, I. Ljubić, E. Malaguti, P. Paronuzzi
{"title":"Casting Light on the Hidden Bilevel Combinatorial Structure of the Capacitated Vertex Separator Problem","authors":"Fabio Furini, I. Ljubić, E. Malaguti, P. Paronuzzi","doi":"10.1287/opre.2021.2110","DOIUrl":"https://doi.org/10.1287/opre.2021.2110","url":null,"abstract":"","PeriodicalId":19546,"journal":{"name":"Oper. Res.","volume":"288 1","pages":"2399-2420"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79415916","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}
Veronica Dal Sasso, Leonardo Lamorgese, C. Mannino, A. Tancredi, P. Ventura
.
{"title":"Easy Cases of Deadlock Detection in Train Scheduling","authors":"Veronica Dal Sasso, Leonardo Lamorgese, C. Mannino, A. Tancredi, P. Ventura","doi":"10.1287/opre.2022.2283","DOIUrl":"https://doi.org/10.1287/opre.2022.2283","url":null,"abstract":".","PeriodicalId":19546,"journal":{"name":"Oper. Res.","volume":"37 1","pages":"2101-2118"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75090397","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：