Model-Free Assortment Pricing with Transaction Data

We study the problem when a firm sets prices for products based on the transaction data, that is, which product past customers chose from an assortment and what were the historical prices that they observed. Our approach does not impose a model on the distribution of the customers’ valuations and on...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Management science 2023-10, Vol.69 (10), p.5830-5847
1. Verfasser: Chen, Ningyuan
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 5847
container_issue 10
container_start_page 5830
container_title Management science
container_volume 69
creator Chen, Ningyuan
description We study the problem when a firm sets prices for products based on the transaction data, that is, which product past customers chose from an assortment and what were the historical prices that they observed. Our approach does not impose a model on the distribution of the customers’ valuations and only assumes, instead, that purchase choices satisfy incentive-compatible constraints. The uncertainty set of potential valuations of each past customer can then be encoded as a polyhedral set, and our approach maximizes the worst case revenue, assuming that new customers’ valuations are drawn from the empirical distribution implied by the collection of such polyhedra. We study the single-product case analytically and relate it to the traditional model-based approach. Then, we show that the optimal prices in the general case can be approximated at any arbitrary precision by solving a compact mixed-integer linear program. We further design three approximation strategies that are of low computational complexity and interpretable. In particular, the cutoff pricing heuristic has a competent provable performance guarantee. Comprehensive numerical studies based on synthetic and real data suggest that our pricing approach is uniquely beneficial when the historical data has a limited size or is susceptible to model misspecification. This paper was accepted by Omar Besbes, revenue management and market analytics. Funding: This work was supported by the Rotman School of Management (TD-MDAL Research Grant) and the Natural Sciences and Engineering Research Council of Canada [Grants RGPIN-2015-06757, RGPIN-2020-04038, RGPIN-2020-06054, RGPIN-2021-04295]. Supplemental Material: The e-companion and data files are available at https://doi.org/10.1287/mnsc.2022.4651 .
doi_str_mv 10.1287/mnsc.2022.4651
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2879349088</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2879349088</sourcerecordid><originalsourceid>FETCH-LOGICAL-c325t-7329f977f2752e7eb4aa2223a2fbfa19c26920cda11c22af1fc4f3f8dad4581d3</originalsourceid><addsrcrecordid>eNqFkLFOwzAURS0EEqWwMkdiTrCf49geq0IBqQiGMluuY0Oqxi62K8TfkyhIjExvOfdevYPQNcEVAcFve59MBRigqhtGTtCMMGhKxjA5RTOMgZVEYnmOLlLaYYy54M0M0efQ2n25itYWi5RCzL31uXiNnen8e_HV5Y9iE7VP2uQu-OJOZ32JzpzeJ3v1e-fobXW_WT6W65eHp-ViXRoKLJecgnSScwecgeV2W2sNAFSD2zpNpIFGAjatJsQAaEecqR11otVtzQRp6RzdTL2HGD6PNmW1C8foh0k1_CtpLbEQA1VNlIkhpWidOsSu1_FbEaxGMWoUo0YxahQzBIopYE3wXfrDRTP4EYTyASknpPMuxD79V_kDwINvCQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2879349088</pqid></control><display><type>article</type><title>Model-Free Assortment Pricing with Transaction Data</title><source>INFORMS PubsOnLine</source><creator>Chen, Ningyuan</creator><creatorcontrib>Chen, Ningyuan</creatorcontrib><description>We study the problem when a firm sets prices for products based on the transaction data, that is, which product past customers chose from an assortment and what were the historical prices that they observed. Our approach does not impose a model on the distribution of the customers’ valuations and only assumes, instead, that purchase choices satisfy incentive-compatible constraints. The uncertainty set of potential valuations of each past customer can then be encoded as a polyhedral set, and our approach maximizes the worst case revenue, assuming that new customers’ valuations are drawn from the empirical distribution implied by the collection of such polyhedra. We study the single-product case analytically and relate it to the traditional model-based approach. Then, we show that the optimal prices in the general case can be approximated at any arbitrary precision by solving a compact mixed-integer linear program. We further design three approximation strategies that are of low computational complexity and interpretable. In particular, the cutoff pricing heuristic has a competent provable performance guarantee. Comprehensive numerical studies based on synthetic and real data suggest that our pricing approach is uniquely beneficial when the historical data has a limited size or is susceptible to model misspecification. This paper was accepted by Omar Besbes, revenue management and market analytics. Funding: This work was supported by the Rotman School of Management (TD-MDAL Research Grant) and the Natural Sciences and Engineering Research Council of Canada [Grants RGPIN-2015-06757, RGPIN-2020-04038, RGPIN-2020-06054, RGPIN-2021-04295]. Supplemental Material: The e-companion and data files are available at https://doi.org/10.1287/mnsc.2022.4651 .</description><identifier>ISSN: 0025-1909</identifier><identifier>EISSN: 1526-5501</identifier><identifier>DOI: 10.1287/mnsc.2022.4651</identifier><language>eng</language><publisher>Linthicum: INFORMS</publisher><subject>Approximation ; approximation algorithm ; assortment ; Customers ; Data ; data-driven ; Heuristic ; incentive-compatible ; Prices ; pricing ; Pricing policies ; robust optimization ; Uncertainty</subject><ispartof>Management science, 2023-10, Vol.69 (10), p.5830-5847</ispartof><rights>Copyright Institute for Operations Research and the Management Sciences Oct 2023</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c325t-7329f977f2752e7eb4aa2223a2fbfa19c26920cda11c22af1fc4f3f8dad4581d3</citedby><cites>FETCH-LOGICAL-c325t-7329f977f2752e7eb4aa2223a2fbfa19c26920cda11c22af1fc4f3f8dad4581d3</cites><orcidid>0000-0003-0900-7631 ; 0000-0002-0001-8572 ; 0000-0001-5993-4295 ; 0000-0002-3948-1011</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://pubsonline.informs.org/doi/full/10.1287/mnsc.2022.4651$$EHTML$$P50$$Ginforms$$H</linktohtml><link.rule.ids>314,776,780,3678,27903,27904,62592</link.rule.ids></links><search><creatorcontrib>Chen, Ningyuan</creatorcontrib><title>Model-Free Assortment Pricing with Transaction Data</title><title>Management science</title><description>We study the problem when a firm sets prices for products based on the transaction data, that is, which product past customers chose from an assortment and what were the historical prices that they observed. Our approach does not impose a model on the distribution of the customers’ valuations and only assumes, instead, that purchase choices satisfy incentive-compatible constraints. The uncertainty set of potential valuations of each past customer can then be encoded as a polyhedral set, and our approach maximizes the worst case revenue, assuming that new customers’ valuations are drawn from the empirical distribution implied by the collection of such polyhedra. We study the single-product case analytically and relate it to the traditional model-based approach. Then, we show that the optimal prices in the general case can be approximated at any arbitrary precision by solving a compact mixed-integer linear program. We further design three approximation strategies that are of low computational complexity and interpretable. In particular, the cutoff pricing heuristic has a competent provable performance guarantee. Comprehensive numerical studies based on synthetic and real data suggest that our pricing approach is uniquely beneficial when the historical data has a limited size or is susceptible to model misspecification. This paper was accepted by Omar Besbes, revenue management and market analytics. Funding: This work was supported by the Rotman School of Management (TD-MDAL Research Grant) and the Natural Sciences and Engineering Research Council of Canada [Grants RGPIN-2015-06757, RGPIN-2020-04038, RGPIN-2020-06054, RGPIN-2021-04295]. Supplemental Material: The e-companion and data files are available at https://doi.org/10.1287/mnsc.2022.4651 .</description><subject>Approximation</subject><subject>approximation algorithm</subject><subject>assortment</subject><subject>Customers</subject><subject>Data</subject><subject>data-driven</subject><subject>Heuristic</subject><subject>incentive-compatible</subject><subject>Prices</subject><subject>pricing</subject><subject>Pricing policies</subject><subject>robust optimization</subject><subject>Uncertainty</subject><issn>0025-1909</issn><issn>1526-5501</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNqFkLFOwzAURS0EEqWwMkdiTrCf49geq0IBqQiGMluuY0Oqxi62K8TfkyhIjExvOfdevYPQNcEVAcFve59MBRigqhtGTtCMMGhKxjA5RTOMgZVEYnmOLlLaYYy54M0M0efQ2n25itYWi5RCzL31uXiNnen8e_HV5Y9iE7VP2uQu-OJOZ32JzpzeJ3v1e-fobXW_WT6W65eHp-ViXRoKLJecgnSScwecgeV2W2sNAFSD2zpNpIFGAjatJsQAaEecqR11otVtzQRp6RzdTL2HGD6PNmW1C8foh0k1_CtpLbEQA1VNlIkhpWidOsSu1_FbEaxGMWoUo0YxahQzBIopYE3wXfrDRTP4EYTyASknpPMuxD79V_kDwINvCQ</recordid><startdate>20231001</startdate><enddate>20231001</enddate><creator>Chen, Ningyuan</creator><general>INFORMS</general><general>Institute for Operations Research and the Management Sciences</general><scope>OQ6</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8BJ</scope><scope>FQK</scope><scope>JBE</scope><orcidid>https://orcid.org/0000-0003-0900-7631</orcidid><orcidid>https://orcid.org/0000-0002-0001-8572</orcidid><orcidid>https://orcid.org/0000-0001-5993-4295</orcidid><orcidid>https://orcid.org/0000-0002-3948-1011</orcidid></search><sort><creationdate>20231001</creationdate><title>Model-Free Assortment Pricing with Transaction Data</title><author>Chen, Ningyuan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c325t-7329f977f2752e7eb4aa2223a2fbfa19c26920cda11c22af1fc4f3f8dad4581d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Approximation</topic><topic>approximation algorithm</topic><topic>assortment</topic><topic>Customers</topic><topic>Data</topic><topic>data-driven</topic><topic>Heuristic</topic><topic>incentive-compatible</topic><topic>Prices</topic><topic>pricing</topic><topic>Pricing policies</topic><topic>robust optimization</topic><topic>Uncertainty</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Chen, Ningyuan</creatorcontrib><collection>ECONIS</collection><collection>CrossRef</collection><collection>International Bibliography of the Social Sciences (IBSS)</collection><collection>International Bibliography of the Social Sciences</collection><collection>International Bibliography of the Social Sciences</collection><jtitle>Management science</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Chen, Ningyuan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Model-Free Assortment Pricing with Transaction Data</atitle><jtitle>Management science</jtitle><date>2023-10-01</date><risdate>2023</risdate><volume>69</volume><issue>10</issue><spage>5830</spage><epage>5847</epage><pages>5830-5847</pages><issn>0025-1909</issn><eissn>1526-5501</eissn><abstract>We study the problem when a firm sets prices for products based on the transaction data, that is, which product past customers chose from an assortment and what were the historical prices that they observed. Our approach does not impose a model on the distribution of the customers’ valuations and only assumes, instead, that purchase choices satisfy incentive-compatible constraints. The uncertainty set of potential valuations of each past customer can then be encoded as a polyhedral set, and our approach maximizes the worst case revenue, assuming that new customers’ valuations are drawn from the empirical distribution implied by the collection of such polyhedra. We study the single-product case analytically and relate it to the traditional model-based approach. Then, we show that the optimal prices in the general case can be approximated at any arbitrary precision by solving a compact mixed-integer linear program. We further design three approximation strategies that are of low computational complexity and interpretable. In particular, the cutoff pricing heuristic has a competent provable performance guarantee. Comprehensive numerical studies based on synthetic and real data suggest that our pricing approach is uniquely beneficial when the historical data has a limited size or is susceptible to model misspecification. This paper was accepted by Omar Besbes, revenue management and market analytics. Funding: This work was supported by the Rotman School of Management (TD-MDAL Research Grant) and the Natural Sciences and Engineering Research Council of Canada [Grants RGPIN-2015-06757, RGPIN-2020-04038, RGPIN-2020-06054, RGPIN-2021-04295]. Supplemental Material: The e-companion and data files are available at https://doi.org/10.1287/mnsc.2022.4651 .</abstract><cop>Linthicum</cop><pub>INFORMS</pub><doi>10.1287/mnsc.2022.4651</doi><tpages>18</tpages><orcidid>https://orcid.org/0000-0003-0900-7631</orcidid><orcidid>https://orcid.org/0000-0002-0001-8572</orcidid><orcidid>https://orcid.org/0000-0001-5993-4295</orcidid><orcidid>https://orcid.org/0000-0002-3948-1011</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0025-1909
ispartof Management science, 2023-10, Vol.69 (10), p.5830-5847
issn 0025-1909
1526-5501
language eng
recordid cdi_proquest_journals_2879349088
source INFORMS PubsOnLine
subjects Approximation
approximation algorithm
assortment
Customers
Data
data-driven
Heuristic
incentive-compatible
Prices
pricing
Pricing policies
robust optimization
Uncertainty
title Model-Free Assortment Pricing with Transaction Data
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-25T13%3A55%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Model-Free%20Assortment%20Pricing%20with%20Transaction%20Data&rft.jtitle=Management%20science&rft.au=Chen,%20Ningyuan&rft.date=2023-10-01&rft.volume=69&rft.issue=10&rft.spage=5830&rft.epage=5847&rft.pages=5830-5847&rft.issn=0025-1909&rft.eissn=1526-5501&rft_id=info:doi/10.1287/mnsc.2022.4651&rft_dat=%3Cproquest_cross%3E2879349088%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2879349088&rft_id=info:pmid/&rfr_iscdi=true