Angels or demons? Classifying desirable heavy users and undesirable power sellers in online C2C marketplace

Hikaru Yamamoto (), Nina Sugiyama (), Fujio Toriumi (), Hikaru Kashida () and Takuma Yamaguchi ()
Additional contact information
Hikaru Yamamoto: Keio University
Nina Sugiyama: The University of Tokyo
Fujio Toriumi: The University of Tokyo
Hikaru Kashida: Mercari, Inc
Takuma Yamaguchi: Mercari, Inc

Journal of Computational Social Science, 2019, vol. 2, issue 2, No 11, 315-329

Abstract: Abstract To grow and succeed, online consumer-to-consumer (C2C) marketplaces need to increase the number of users and transactions, because their main revenue is usually the transaction fee. To increase the number of users and transactions, uncertainty must be reduced and a safe and enjoyable transaction environment must be maintained. In this paper, we aim to detect malicious users and power sellers who can harm the healthy growth of an online C2C platform. Using the data set of a major online C2C marketplace called Mercari, we classified undesirable users by building a classification model for banned users. The results of the banned user prediction indicated that most banned users are heavy sellers. Heavy sellers are desirable from the viewpoint of increasing the transaction fee revenue, but many are power sellers who are running full-time businesses on the platform, making it difficult for non-professional sellers to compete, and their dominance may eventually alienate users. Thus, we built another classification model to classify desirable and undesirable power sellers. Applying the model to the CART classifier, we successfully classified non-professional heavy users and undesirable power sellers in an online C2C marketplace.

Keywords: Online platform; Consumer-to-consumer marketplace; Online fraud; Banned user prediction (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s42001-019-00050-y Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:spr:jcsosc:v:2:y:2019:i:2:d:10.1007_s42001-019-00050-y

Ordering information: This journal article can be ordered from
http://www.springer. ... iences/journal/42001

DOI: 10.1007/s42001-019-00050-y

Access Statistics for this article

Journal of Computational Social Science is currently edited by Takashi Kamihigashi

More articles in Journal of Computational Social Science from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().