Mengying Xue
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Mengying Xue has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Hao Shen
School of Business, Renmin University of China, Beijing 100872, China
3 shared publications - Zuo-Jun Max Shen
Faculty of Engineering & Faculty of Business and Economics, The University of Hong Kong, Hong Kong, China
3 shared publications - Tianhu Deng
Dongwu Business School, Soochow University, Suzhou, Jiangsu 215006, China
2 shared publications Dingzhi Liu
Oil and Gas Pipeline Engineering Department, China Petroleum Planning and Engineering Institute, China National Petroleum Corporation, Beijing, China 100083
1 shared publicationJ. George Shanthikumar
Krannert School of Management, Purdue University, West Lafayette, Indiana, 47907, USA
1 shared publication- Jeyaveerasingam George Shanthikumar
Mitchell E. Daniels, Jr., School of Business, Purdue University, West Lafayette, Indiana 47907
1 shared publication
Latest Publications
- 20 November 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
Rational Choice Models: The Temporal Tree Representation
Choice models, which specify the consumers’ choice probabilities of options over a given choice set, are widely studied and applied in many fields. We propose a temporal tree representation of choice that covers all rational choice models. Compared with existing structural choice models, the tree representation exhibits two major advantages that address the key challenges of model identification. First, all rational choice models have a tree representation, and a subclass of tree representation (with set-dependent branching) has a one-to-one correspondence with the rational choice models. This bridges the gap in the existing characterizations of structural models, which are unidentifiable, impose uninterpretable conditions, or do not cover the entire space of rational choice models. Second, the tree representation allows for the flexibility of systematically specifying the choice model structure based on available knowledge and data. In particular, the number of parameters needed to specify a tree representation can be primarily determined by the sufficient knowledge level, which corresponds to a specific layer of the tree branching. The sufficient knowledge level can be empirically determined based on the amount of available data, which, in turn, determines the number of parameters needed for model estimation. Therefore, the tree representation allows for a natural way of data integration, avoiding misspecification from restrictive assumptions and overfitting for general models. This paper was accepted by David Simchi-Levi, operations management. Funding: M. Xue’s research is partly support by the National Natural Science Foundation of China [72201257, 72571069, 72371240]. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2023.03967 .
- 20 November 2025
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
Rational Choice Models: The Temporal Tree Representation
Choice models, which specify the consumers’ choice probabilities of options over a given choice set, are widely studied and applied in many fields. We propose a temporal tree representation of choice that covers all rational choice models. Compared with existing structural choice models, the tree representation exhibits two major advantages that address the key challenges of model identification. First, all rational choice models have a tree representation, and a subclass of tree representation (with set-dependent branching) has a one-to-one correspondence with the rational choice models. This bridges the gap in the existing characterizations of structural models, which are unidentifiable, impose uninterpretable conditions, or do not cover the entire space of rational choice models. Second, the tree representation allows for the flexibility of systematically specifying the choice model structure based on available knowledge and data. In particular, the number of parameters needed to specify a tree representation can be primarily determined by the sufficient knowledge level, which corresponds to a specific layer of the tree branching. The sufficient knowledge level can be empirically determined based on the amount of available data, which, in turn, determines the number of parameters needed for model estimation. Therefore, the tree representation allows for a natural way of data integration, avoiding misspecification from restrictive assumptions and overfitting for general models. This paper was accepted by David Simchi-Levi, operations management. Funding: M. Xue’s research is partly support by the National Natural Science Foundation of China [72201257, 72571069, 72371240]. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2023.03967 .
- 4 December 2024
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
Data-Driven Reliable Facility Location Design
We study the reliable (uncapacitated) facility location (RFL) problem in a data-driven environment where historical observations of random demands and disruptions are available. Owing to the combinatorial optimization nature of the RFL problem and the mixed-binary randomness of parameters therein, the state-of-the-art RFL models applied to the data-driven setting either suggest overly conservative solutions or become computationally prohibitive for large- or even moderate-size problems. In this paper, we address the RFL problem by presenting an innovative prescriptive model aiming to balance solution conservatism with computational efficiency. In particular, our model selects facility locations to minimize the fixed costs plus the expected operating costs approximated by a tractable data-driven estimator, which equals to a probabilistic upper bound on the intractable Kolmogorov distributionally robust optimization estimator. The solution of our model is obtained by solving a mixed-integer linear program that does not scale in the training data size. Our approach is proved to be asymptotically optimal, and offers a theoretical guarantee for its out-of-sample performance in situations with limited data. In addition, we discuss the adaptation of our approach when facing data with covariate information. Numerical results demonstrate that our model significantly outperforms several important RFL models with respect to both in-sample and out-of-sample performances as well as computational efficiency. This paper was accepted by Chung Piaw Teo, optimization. Funding: H. Shen acknowledges the support from the National Natural Science Foundation of China [Grants 72371240, 72001206]. M. Xue acknowledges the support from the National Natural Science Foundation of China [Grant 72201257]. Z.J. M. Shen acknowledges the support from National Natural Science Foundation of China [Grant 71991462], Hong Kong ITC Mainland-Hong Kong Joint Funding Scheme [MHP/192/23], and RGC Theme-based Research Scheme [T32-707/22-N]. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2021.02115 .
- 4 December 2024
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Management Science
Data-Driven Reliable Facility Location Design
We study the reliable (uncapacitated) facility location (RFL) problem in a data-driven environment where historical observations of random demands and disruptions are available. Owing to the combinatorial optimization nature of the RFL problem and the mixed-binary randomness of parameters therein, the state-of-the-art RFL models applied to the data-driven setting either suggest overly conservative solutions or become computationally prohibitive for large- or even moderate-size problems. In this paper, we address the RFL problem by presenting an innovative prescriptive model aiming to balance solution conservatism with computational efficiency. In particular, our model selects facility locations to minimize the fixed costs plus the expected operating costs approximated by a tractable data-driven estimator, which equals to a probabilistic upper bound on the intractable Kolmogorov distributionally robust optimization estimator. The solution of our model is obtained by solving a mixed-integer linear program that does not scale in the training data size. Our approach is proved to be asymptotically optimal, and offers a theoretical guarantee for its out-of-sample performance in situations with limited data. In addition, we discuss the adaptation of our approach when facing data with covariate information. Numerical results demonstrate that our model significantly outperforms several important RFL models with respect to both in-sample and out-of-sample performances as well as computational efficiency. This paper was accepted by Chung Piaw Teo, optimization. Funding: H. Shen acknowledges the support from the National Natural Science Foundation of China [Grants 72371240, 72001206]. M. Xue acknowledges the support from the National Natural Science Foundation of China [Grant 72201257]. Z.J. M. Shen acknowledges the support from National Natural Science Foundation of China [Grant 71991462], Hong Kong ITC Mainland-Hong Kong Joint Funding Scheme [MHP/192/23], and RGC Theme-based Research Scheme [T32-707/22-N]. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2021.02115 .
- Open Access
- 1 January 2023
- Published by Elsevier in SSRN Electronic Journal
Data-Driven Reliable Facility Location Design
We study the reliable (uncapacitated) facility location (RFL) problem in a data-driven environment where historical observations of random demands and disruptions are available. Owing to the combinatorial optimization nature of the RFL problem and the mixed-binary randomness of parameters therein, the state-of-the-art RFL models applied to the data-driven setting either suggest overly conservatism solutions, or become computationally prohibitive for large- or even moderate-size problems. In this paper, we address the RFL problem by presenting an innovative prescriptive model aiming to balance solution conservatism with computational efficiency. In particular, our model selects facility locations to minimize the fixed costs plus the expected operating costs approximated by a tractable data-driven estimator, which equals to a probabilistic upper bound on the intractable Kolmogorov distributionally robust optimization estimator. The solution of our model is obtained by solving a mixed-integer linear program that does not scale in the training data size. Our approach is proved to be asymptotically optimal, and offers a theoretical guarantee for its out-of-sample performance in situations with limited data. In addition, we discuss the adaptation of our approach when facing data with covariate information. Numerical results demonstrate that our model significantly outperforms several important RFL models with respect to both in-sample and out-of-sample performances as well as computational efficiency.
- 1 January 2023
- Published by Elsevier in SSRN Electronic Journal
Open AccessData-Driven Reliable Facility Location Design
We study the reliable (uncapacitated) facility location (RFL) problem in a data-driven environment where historical observations of random demands and disruptions are available. Owing to the combinatorial optimization nature of the RFL problem and the mixed-binary randomness of parameters therein, the state-of-the-art RFL models applied to the data-driven setting either suggest overly conservatism solutions, or become computationally prohibitive for large- or even moderate-size problems. In this paper, we address the RFL problem by presenting an innovative prescriptive model aiming to balance solution conservatism with computational efficiency. In particular, our model selects facility locations to minimize the fixed costs plus the expected operating costs approximated by a tractable data-driven estimator, which equals to a probabilistic upper bound on the intractable Kolmogorov distributionally robust optimization estimator. The solution of our model is obtained by solving a mixed-integer linear program that does not scale in the training data size. Our approach is proved to be asymptotically optimal, and offers a theoretical guarantee for its out-of-sample performance in situations with limited data. In addition, we discuss the adaptation of our approach when facing data with covariate information. Numerical results demonstrate that our model significantly outperforms several important RFL models with respect to both in-sample and out-of-sample performances as well as computational efficiency.
- 1 September 2022
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Manufacturing & Service Operations Management
- Vol. 24 (5) , 2444-2462
Offline-Channel Planning in Smart Omnichannel Retailing
Problem definition: Observing the retail industry inevitably evolving into omnichannel, we study an offline-channel planning problem that helps an omnichannel retailer make store location and location-dependent assortment decisions in its offline channel to maximize profit across both online and offline channels, given that customers’ purchase decisions depend on not only their preferences across products but also, their valuation discrepancies across channels, as well as the hassle costs incurred. Academic/practical relevance: The proposed model and the solution approach extend the literature on retail-channel management, omnichannel assortment planning, and the broader field of smart retailing/cities. Methodology: We derive parameterized models to capture customers’ channel choice and product choice behaviors and customize a corresponding parameter estimation approach employing the expectation-maximization method. To solve the proposed optimization model, we develop a tractable mixed integer second-order conic programming reformulation and explore the structural properties of the reformulation to derive strengthening cuts in closed form. Results: We numerically validate the efficacy of the proposed solution approach and demonstrate the parameter estimation approach. We further draw managerial insights from the numerical studies using real data sets. Managerial implications: We verify that omnichannel retailers should provide location-dependent offline assortments. In addition, our benchmark studies reveal the necessity and significance of jointly determining offline store locations and assortments, as well as of incorporating the online channel while making offline-channel planning decisions.
- 1 September 2022
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Manufacturing & Service Operations Management
- Vol. 24 (5) , 2444-2462
Offline-Channel Planning in Smart Omnichannel Retailing
Problem definition: Observing the retail industry inevitably evolving into omnichannel, we study an offline-channel planning problem that helps an omnichannel retailer make store location and location-dependent assortment decisions in its offline channel to maximize profit across both online and offline channels, given that customers’ purchase decisions depend on not only their preferences across products but also, their valuation discrepancies across channels, as well as the hassle costs incurred. Academic/practical relevance: The proposed model and the solution approach extend the literature on retail-channel management, omnichannel assortment planning, and the broader field of smart retailing/cities. Methodology: We derive parameterized models to capture customers’ channel choice and product choice behaviors and customize a corresponding parameter estimation approach employing the expectation-maximization method. To solve the proposed optimization model, we develop a tractable mixed integer second-order conic programming reformulation and explore the structural properties of the reformulation to derive strengthening cuts in closed form. Results: We numerically validate the efficacy of the proposed solution approach and demonstrate the parameter estimation approach. We further draw managerial insights from the numerical studies using real data sets. Managerial implications: We verify that omnichannel retailers should provide location-dependent offline assortments. In addition, our benchmark studies reveal the necessity and significance of jointly determining offline store locations and assortments, as well as of incorporating the online channel while making offline-channel planning decisions.
- 12 June 2021
- Published by SAGE Publications in Production and Operations Management
- Vol. 31 (2) , 847-867
Consumer Choice Models and Estimation: A Review and Extension
Choice models are widely applied in psychology, economics, transportation, marketing, and operations studies. We review the existing developments on the modeling of consumers’ choices, including the attraction model, the utility‐based model, the temporal model, and the rank‐based model. The relationships among different classes of structural models are established and analyzed. Moreover, an operational data analytics (ODA) framework is presented to estimate the general consumer choice model using data. This framework, generalizing the existing estimation methods for specific structural models, strikes a delicate balance between the (likely imprecise) structural knowledge and the data. This is achieved by articulating the domain of validation through extending the structural knowledge and by formulating the data‐integration model based on the associated structural properties. We demonstrate the implementation of the ODA framework to identify the appropriate consumer choice models. The ODA estimate outperforms the existing parametric and nonparametric methods, particularly over the choice sets that are not covered in the data. We also discuss potential future research of developing ODA approaches to study the related aspects of consumer choice models.
- 12 June 2021
- Published by SAGE Publications in Production and Operations Management
- Vol. 31 (2) , 847-867
Consumer Choice Models and Estimation: A Review and Extension
Choice models are widely applied in psychology, economics, transportation, marketing, and operations studies. We review the existing developments on the modeling of consumers’ choices, including the attraction model, the utility‐based model, the temporal model, and the rank‐based model. The relationships among different classes of structural models are established and analyzed. Moreover, an operational data analytics (ODA) framework is presented to estimate the general consumer choice model using data. This framework, generalizing the existing estimation methods for specific structural models, strikes a delicate balance between the (likely imprecise) structural knowledge and the data. This is achieved by articulating the domain of validation through extending the structural knowledge and by formulating the data‐integration model based on the associated structural properties. We demonstrate the implementation of the ODA framework to identify the appropriate consumer choice models. The ODA estimate outperforms the existing parametric and nonparametric methods, particularly over the choice sets that are not covered in the data. We also discuss potential future research of developing ODA approaches to study the related aspects of consumer choice models.
- 10 September 2020
- Published by Wiley in Naval Research Logistics (NRL)
- Vol. 67 (8) , 670-684
Spatial pricing and product allocation in online retailing
Spatial pricing means a retailer price discriminates its customers based on their geographic locations. In this article, we study how an online retailer should jointly allocate multiple products and facilitate spatial price discrimination to maximize profits. When deciding between a centralized product allocation ((i.e., different products are allocated to the same fulfillment center) and decentralized product allocation (ie, different products are allocated to different fulfillment centers), the retailer faces the tradeoff between shipment pooling (ie, shipping multiple products in one package), and demand localization (ie, stocking products to satisfy local demand) based on its understanding of customers' product valuations. In our basic model, we consider two widely used spatial pricing policies: free on board (FOB) pricing that charges each customer the exact amount of shipping cost, and uniform delivered (UD) pricing that provides free shipping. We propose a stylized model and find that centralized product allocation is preferred when demand localization effect is relatively low or shipment pooling benefit is relatively high under both spatial pricing policies. Moreover, centralized product allocation is more preferred under the FOB pricing which encourages the purchase of virtual bundles of multiple products. Furthermore, we respectively extend the UD and FOB pricing policies to flat rate shipping (ie, the firm charges a constant shipping fee for each purchase), and linear rate shipping (ie, the firm sets the shipping fee as a fixed proportion of firm's actual fulfillment costs). While similar observations from the basic model still hold, we find the firm can improve its profit by sharing the fulfillment cost with its customers via the flat rate or linear rate shipping fee structure.
- 10 September 2020
- Published by Wiley in Naval Research Logistics (NRL)
- Vol. 67 (8) , 670-684
Spatial pricing and product allocation in online retailing
Spatial pricing means a retailer price discriminates its customers based on their geographic locations. In this article, we study how an online retailer should jointly allocate multiple products and facilitate spatial price discrimination to maximize profits. When deciding between a centralized product allocation ((i.e., different products are allocated to the same fulfillment center) and decentralized product allocation (ie, different products are allocated to different fulfillment centers), the retailer faces the tradeoff between shipment pooling (ie, shipping multiple products in one package), and demand localization (ie, stocking products to satisfy local demand) based on its understanding of customers' product valuations. In our basic model, we consider two widely used spatial pricing policies: free on board (FOB) pricing that charges each customer the exact amount of shipping cost, and uniform delivered (UD) pricing that provides free shipping. We propose a stylized model and find that centralized product allocation is preferred when demand localization effect is relatively low or shipment pooling benefit is relatively high under both spatial pricing policies. Moreover, centralized product allocation is more preferred under the FOB pricing which encourages the purchase of virtual bundles of multiple products. Furthermore, we respectively extend the UD and FOB pricing policies to flat rate shipping (ie, the firm charges a constant shipping fee for each purchase), and linear rate shipping (ie, the firm sets the shipping fee as a fixed proportion of firm's actual fulfillment costs). While similar observations from the basic model still hold, we find the firm can improve its profit by sharing the fulfillment cost with its customers via the flat rate or linear rate shipping fee structure.
- 26 September 2019
- Published by Wiley in Naval Research Logistics (NRL)
- Vol. 66 (7) , 547-564
Optimizing natural gas pipeline transmission with nonuniform elevation: A new initialization approach
In this paper, we develop an iterative piecewise linear approximation approach with a novel initialization method to solve natural gas pipeline transmission problems with the nonuniform network elevation. Previous approaches, such as energy minimization methods, cannot be applied to solve problems with the nonuniform network elevation because they exclude pressure range constraints, and thus provide solutions far from optimum. We propose a new initialization model that considers pressure range constraints and improves the optimality of the solutions and the computational efficiency. Furthermore, we extend the energy minimization methods and provide the necessary conditions under which the extended methods operate in networks with the nonuniform elevation. We test the performances of the methods with previously reported pipeline networks from the literature, with the open data set GasLib, and with our industrial collaborator. The initialization approach is shown to be more efficient than the method with fixed initial breakpoints. The newly proposed initialization approach generates solutions with a higher accuracy than the extended energy minimization methods, especially in large‐size networks. The proposed method has been applied to natural gas transmission planning by the China National Petroleum Corporation and has brought a direct profit increase of 330 million U.S. dollars in 2015‐2017.
- 26 September 2019
- Published by Wiley in Naval Research Logistics (NRL)
- Vol. 66 (7) , 547-564
Optimizing natural gas pipeline transmission with nonuniform elevation: A new initialization approach
In this paper, we develop an iterative piecewise linear approximation approach with a novel initialization method to solve natural gas pipeline transmission problems with the nonuniform network elevation. Previous approaches, such as energy minimization methods, cannot be applied to solve problems with the nonuniform network elevation because they exclude pressure range constraints, and thus provide solutions far from optimum. We propose a new initialization model that considers pressure range constraints and improves the optimality of the solutions and the computational efficiency. Furthermore, we extend the energy minimization methods and provide the necessary conditions under which the extended methods operate in networks with the nonuniform elevation. We test the performances of the methods with previously reported pipeline networks from the literature, with the open data set GasLib, and with our industrial collaborator. The initialization approach is shown to be more efficient than the method with fixed initial breakpoints. The newly proposed initialization approach generates solutions with a higher accuracy than the extended energy minimization methods, especially in large‐size networks. The proposed method has been applied to natural gas transmission planning by the China National Petroleum Corporation and has brought a direct profit increase of 330 million U.S. dollars in 2015‐2017.
- 1 January 2019
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Applied Analytics
- Vol. 49 (1) , 23-39
Operations Research Enables Better Planning of Natural Gas Pipelines
China National Petroleum Corporation collaborated with researchers from the University of California and Tsinghua University to develop software for planning its natural gas pipelines. The work resulted in increased profits of $530 million between 2015 and 2017 and a budget reduction of more than $20 billion in construction costs for the subsequent five years.
- 1 January 2019
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Applied Analytics
- Vol. 49 (1) , 23-39
Operations Research Enables Better Planning of Natural Gas Pipelines
China National Petroleum Corporation collaborated with researchers from the University of California and Tsinghua University to develop software for planning its natural gas pipelines. The work resulted in increased profits of $530 million between 2015 and 2017 and a budget reduction of more than $20 billion in construction costs for the subsequent five years.