2026-09-19T13:32:47Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1269692023-03-10T18:40:34Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Sinan Aral. Kumar, Madhav(Scientist in business management)Massachusetts Institute of Technology. Sloan School of Management. Sloan School of Management 2020-09-03T16:46:01Z 2020-09-03T16:46:01Z 2020 2020 https://hdl.handle.net/1721.1/126969 1191221749 Thesis: S.M. in Management Research, Massachusetts Institute of Technology, Sloan School of Management, May, 2020 Cataloged from the official PDF of thesis. Includes bibliographical references (pages 51-52). Bundling, the practice of jointly selling two or more products at a discount, is a widely used strategy in industry and a well examined concept in academia. Historically, the focus has been on theoretical studies in the context of monopolistic firms and assumed product relationships, e.g., complementarity in usage. We develop a new machine-learning-driven methodology for designing bundles in a large-scale, cross-category retail setting. We leverage historical purchases and consideration sets created from click-stream data to generate dense continuous representations of products called embeddings. We then put minimal structure on these embeddings and develop heuristics for complementarity and substitutability among products. Subsequently, we use the heuristics to create multiple bundles for each product and test their performance using a field experiment with a large retailer. We combine the results from the experiment with product embeddings using a hierarchical model that maps bundle features to their purchase likelihood, as measured by the add-to-cart rate. We find that our embeddings-based heuristics are strong predictors of bundle success, robust across product categories, and generalize well to the retailer's entire assortment. by Madhav Kumar. S.M. in Management Research S.M.inManagementResearch Massachusetts Institute of Technology, Sloan School of Management 52 pages eng Massachusetts Institute of Technology MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided. http://dspace.mit.edu/handle/1721.1/7582 Sloan School of Management. Discount bundling via dense product embeddings Thesis application/pdf 2020-09-03T16:45:58Z Publication Master Sloan unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="ed1c46da-7afa-459f-9f9d-b306401f2a14"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Discount bundling via dense product embeddings</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2020</PublicationDate> <Authors> <Author> <DisplayName>Kumar, Madhav(Scientist in business management)Massachusetts Institute of Technology.</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Sloan School of Management.</Keyword> <Abstract>Bundling, the practice of jointly selling two or more products at a discount, is a widely used strategy in industry and a well examined concept in academia. Historically, the focus has been on theoretical studies in the context of monopolistic firms and assumed product relationships, e.g., complementarity in usage. We develop a new machine-learning-driven methodology for designing bundles in a large-scale, cross-category retail setting. We leverage historical purchases and consideration sets created from click-stream data to generate dense continuous representations of products called embeddings. We then put minimal structure on these embeddings and develop heuristics for complementarity and substitutability among products. Subsequently, we use the heuristics to create multiple bundles for each product and test their performance using a field experiment with a large retailer. We combine the results from the experiment with product embeddings using a hierarchical model that maps bundle features to their purchase likelihood, as measured by the add-to-cart rate. We find that our embeddings-based heuristics are strong predictors of bundle success, robust across product categories, and generalize well to the retailer&apos;s entire assortment.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>