Intelligent Recommendation-Driven Auction Platform for Peer-to-Peer Trading

Abstract

With the increasing demand for efficient and sustainable peer-to-peer marketplaces, students and individuals often face challenges in trading underutilized goods such as textbooks, electronics, and furniture. Existing platforms lack personalized guidance and intelligent matching, resulting in inefficiencies and lost opportunities. This paper presents an Intelligent Recommendation-Driven Auction Platform for Peer-to-Peer Trading, which integrates a collaborative filtering-based recommendation system with an auction mechanism to optimize user experience and transaction efficiency. The platform predicts user preferences, suggests relevant items, and facilitates competitive bidding to ensure fair market pricing. Experimental evaluation demonstrates that the proposed system improves successful transaction rates, reduces search time for items, and enhances user satisfaction compared to traditional peer-to-peer marketplaces. The results indicate that combining recommendation algorithms with intelligent auction mechanisms can significantly enhance the effectiveness and sustainability of community-driven trading platforms.

KEYWORDS: Peer-to-Peer Trading, Auction Platform, Collaborative Filtering, Recommendation System, Intelligent Marketplace