Reviews as Matchmakers: Dynamic Learning of Product Fit

Tommaso Bondi () and Lijuan Luo ()
Additional contact information
Tommaso Bondi: SC Johnson College of Business, Cornell University, Ithaca, NY, USA
Lijuan Luo: SC Johnson College of Business, Cornell University, Ithaca, NY, USA

No 26-03, Working Papers from NET Institute

Abstract: Online reviews are usually modeled as quality signals, but their text also tells readers which products suit them. We study this matching role in a dynamic model in which majority and minority consumers care about partly different product features. As matching improves, each product’s buyers become more alike, and its reviews say less about the features that matter only to consumers of the other type. The unique equilibrium therefore features partial matching, sustained by mismatched buyers whose reviews cover what matched buyers leave out. In the benchmark model, uniformly degrading what consumers see never raises equilibrium matching. Pooled AI summaries of the most frequently mentioned features leave minority readers no better informed than a page written only by fans. Descriptive evidence from 11.6 million Goodreads reviews shows that review text separates fit from quality and that readers who like and dislike a book write about different things. This paper suggests that platforms can serve minority readers better by building AI summaries within reader segments and by not letting majority endorsement decide which reviews are most visible.

Keywords: online reviews; product fit; social learning; information design; AI summaries; platform design (search for similar items in EconPapers)
JEL-codes: D82 D83 L15 L86 M31 (search for similar items in EconPapers)
Pages: 84 pages
Date: 2026-09
New Economics Papers: this item is included in nep-des and nep-mic
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.netinst.org/Bondi_26-03.pdf (application/pdf)
no

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:net:wpaper:2603

Access Statistics for this paper

More papers in Working Papers from NET Institute
Bibliographic data for series maintained by Nicholas Economides ().