Automatic classification of products in P2P marketplaces

Article type: Research Article

Authors: Vallejos, Sebastian^{a; c} | Armentano, Marcelo G.^{a; c; *} | Berdun, Luis^{a; c} | Schiaffino, Silvia^{a; c} | González Císaro, Sandra^b | Nigro, Oscar^b | Balduzzi, Leonardo^d | Cuesta, Ignacio^d

Affiliations: [a] Universidad Nac. del Centro de la Pcia. de Bs. As., Fac. Cs. Exactas, ISISTAN, Tandil, Argentina | [b] Universidad Nac. del Centro de la Pcia. de Bs. As., Fac. Cs. Exactas, INTIA, Tandil, Argentina | [c] CONICET, Tandil, Argentina | [d] Región Global, Tandil, Argentina

Correspondence: [*] Corresponding author. Marcelo G. Armentano. E-mail: marcelo.armentano@isistan.unicen.edu.ar.

Abstract: Product classification is a critical task for the smooth running of the purchase process in e-commerce websites. When it comes to P2P marketplaces, users can act both as sellers and as buyers, and they need to assign predefined categories to the products they want to sell. Besides being tedious for users, this task can result in ambiguous or inaccurate assignments. This article presents a method for the automatic categorization of items offered in a local P2P marketplace using a multi-level classification approach. Our experiments demonstrated a significant improvement in the classification results of the proposed solution compared to a traditional direct classification approach.

Keywords: Classification, e-commerce, NLP, P2P marketplace

DOI: 10.3233/JIFS-219344

Journal: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-11, 2024