{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:24Z","timestamp":1750309464229,"version":"3.41.0"},"reference-count":21,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGecom Exch."],"published-print":{"date-parts":[[2024,6]]},"abstract":"<jats:p>\n            Customers can access hundreds of reviews for a single product in online marketplaces. Buyers often use reviews from other customers that share their type---such as height for clothing or skin type for skincare products---to estimate their values, which they may not know a priori. Customers with few relevant reviews may hesitate to purchase except at a low price, so for the seller, there is a tension between setting high prices and ensuring that there are enough reviews so buyers can confidently estimate their values. Simultaneously, sellers may use reviews to gauge the demand for items they wish to sell. In this work, we study this pricing problem in an online setting where the seller interacts with a set of buyers of finitely many types, one by one, over a series of\n            <jats:italic>T<\/jats:italic>\n            rounds. At each round, the seller first sets a price. Then, a buyer arrives and examines the reviews of the previous buyers with the same type, which reveal those buyers' ex-post values. Based on the reviews, the buyer decides to purchase if they have good reason to believe their ex-ante utility is positive. Crucially, the seller does not know the buyer's type when setting the price, nor even the distribution over types. We provide a no-regret algorithm that the seller can use to obtain high revenue. When there are\n            <jats:italic>d<\/jats:italic>\n            types, after\n            <jats:italic>T<\/jats:italic>\n            rounds, our algorithm achieves a problem-independent\n            <jats:italic>\u00d5<\/jats:italic>\n            (\n            <jats:italic>T<\/jats:italic>\n            <jats:sup>2\/3<\/jats:sup>\n            <jats:italic>d<\/jats:italic>\n            <jats:sup>1\/3<\/jats:sup>\n            ) regret bound. However, when the smallest probability\n            <jats:italic>q<\/jats:italic>\n            <jats:sub>min<\/jats:sub>\n            that any given type appears is large, specifically when\n            <jats:italic>q<\/jats:italic>\n            <jats:sub>min<\/jats:sub>\n            \u2208 \u03a9(\n            <jats:italic>d<\/jats:italic>\n            <jats:sup>\u22122\/3<\/jats:sup>\n            <jats:italic>T<\/jats:italic>\n            <jats:sup>\u22121\/3<\/jats:sup>\n            ), the same algorithm achieves a [EQUATION] regret bound. We complement these upper bounds with matching lower bounds in both regimes, showing that our algorithm is minimax optimal up to lower-order terms.\n          <\/jats:p>\n          <jats:p>\n            This is a summary of work that won the\n            <jats:italic>Exemplary AI Track Paper Award<\/jats:italic>\n            at EC'24.\n          <\/jats:p>","DOI":"10.1145\/3699824.3699830","type":"journal-article","created":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T16:36:42Z","timestamp":1728405402000},"page":"74-82","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Reviews: Learning to Price with Buyer and Seller Uncertainty"],"prefix":"10.1145","volume":"22","author":[{"given":"Wenshuo","family":"Guo","sequence":"first","affiliation":[{"name":"University of California, Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nika","family":"Haghtalab","sequence":"additional","affiliation":[{"name":"University of California, Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kirthevasan","family":"Kandasamy","sequence":"additional","affiliation":[{"name":"University of Wisconsin, Madison"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ellen","family":"Vitercik","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,8]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.3982\/ECTA15847"},{"volume-title":"ACM Conference on Economics and Computation (EC).","author":"Ashlagi I.","key":"e_1_2_1_2_1","unstructured":"Ashlagi, I., Daskalakis, C., and Haghpanah, N. 2016. Sequential mechanisms with ex-post participation guarantees. In ACM Conference on Economics and Computation (EC)."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2017.1676"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1756-2171.2006.tb00063.x"},{"volume-title":"International Conference on Algorithmic Learning Theory (ALT). 128--129","author":"Boursier E.","key":"e_1_2_1_5_1","unstructured":"Boursier, E., Perchet, V., and Scarsini, M. 2022. Social learning in non-stationary environments. In International Conference on Algorithmic Learning Theory (ALT). 128--129."},{"volume-title":"ACM Conference on Economics and Computation (EC).","author":"Braverman M.","key":"e_1_2_1_6_1","unstructured":"Braverman, M., Mao, J., Schneider, J., and Weinberg, M. 2018. Selling to a no-regret buyer. In ACM Conference on Economics and Computation (EC)."},{"volume-title":"Rational herds: Economic models of social learning","author":"Chamley C.","key":"e_1_2_1_7_1","unstructured":"Chamley, C. 2004. Rational herds: Economic models of social learning. Cambridge University Press."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.geb.2022.03.012"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2016.2526"},{"volume-title":"Conference on Neural Information Processing Systems (NeurIPS).","author":"Deng Y.","key":"e_1_2_1_10_1","unstructured":"Deng, Y., Schneider, J., and Sivan, B. 2019. Prior-free dynamic auctions with low regret buyers. In Conference on Neural Information Processing Systems (NeurIPS)."},{"volume-title":"Annual ACM-SIAM Symposium on Discrete Algorithms (SODA).","author":"Devanur N. R.","key":"e_1_2_1_11_1","unstructured":"Devanur, N. R., Peres, Y., and Sivan, B. 2014. Perfect Bayesian equilibria in repeated sales. In Annual ACM-SIAM Symposium on Discrete Algorithms (SODA)."},{"volume-title":"ACM Conference on Economics and Computation (EC).","author":"Feng Z.","key":"e_1_2_1_12_1","unstructured":"Feng, Z., Podimata, C., and Syrgkanis, V. 2018. Learning to bid without knowing your value. In ACM Conference on Economics and Computation (EC)."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1177\/1938965520902012"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2019.1861"},{"key":"e_1_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Kakhbod A. Lanzani G. and Xing H. 2021. Heterogeneous Learning in Product Markets. Available at SSRN 3961223.","DOI":"10.2139\/ssrn.3961223"},{"key":"e_1_2_1_16_1","first-page":"1","article-title":"VCG mechanism design with unknown agent values under stochastic bandit feedback","volume":"24","author":"Kandasamy K.","year":"2023","unstructured":"Kandasamy, K., Gonzalez, J. E., Jordan, M. I., and Stoica, I. 2023. VCG mechanism design with unknown agent values under stochastic bandit feedback. Journal of Machine Learning Research 24, 53, 1--45.","journal-title":"Journal of Machine Learning Research"},{"volume-title":"Symposium on Foundations of Computer Science (FOCS).","author":"Kleinberg R.","key":"e_1_2_1_17_1","unstructured":"Kleinberg, R. and Leighton, T. 2003. The value of knowing a demand curve: Bounds on regret for online posted-price auctions. In Symposium on Foundations of Computer Science (FOCS)."},{"volume-title":"ACM Conference on Economics and Computation (EC).","author":"Nekipelov D.","key":"e_1_2_1_18_1","unstructured":"Nekipelov, D., Syrgkanis, V., and Tardos, E. 2015. Econometrics for learning agents. In ACM Conference on Economics and Computation (EC)."},{"key":"e_1_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Papadimitriou C. Pierrakos G. Psomas A. and Rubinstein A. 2022. On the complexity of dynamic mechanism design. Games and Economic Behavior.","DOI":"10.1016\/j.geb.2022.01.024"},{"volume-title":"Conference on Learning Theory (COLT).","author":"Weed J.","key":"e_1_2_1_20_1","unstructured":"Weed, J., Perchet, V., and Rigollet, P. 2016. Online learning in repeated auctions. In Conference on Learning Theory (COLT)."},{"volume-title":"European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD).","author":"Zhao H.","key":"e_1_2_1_21_1","unstructured":"Zhao, H. and Chen, W. 2020. Stochastic one-sided full-information bandit. In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)."}],"container-title":["ACM SIGecom Exchanges"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3699824.3699830","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3699824.3699830","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:33Z","timestamp":1750295433000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3699824.3699830"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":21,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["10.1145\/3699824.3699830"],"URL":"https:\/\/doi.org\/10.1145\/3699824.3699830","relation":{},"ISSN":["1551-9031"],"issn-type":[{"type":"electronic","value":"1551-9031"}],"subject":[],"published":{"date-parts":[[2024,6]]},"assertion":[{"value":"2024-10-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}