User-Centric Product Discovery for Personalized e-Commerce Recommendations

Mustafa Keskin, Enis Teper, Sinan Keçeci

2025

Abstract

Personalized recommendations in e-commerce platforms often rely on user-item interactions or product similarity. In this work, we explore a user2user recommendation paradigm, where products are recommended based on purchases made by similar users. We investigate three methods for modeling user similarity: binary category vectors with sparse dot-product search, GraphSAGE embeddings trained on a user–product bipartite graph, and behavioral user embeddings obtained by averaging Node2Vec-based product vectors. Recommendations are drawn from complementary or previously browsed categories and ranked using recency-aware, diversity-promoting strategies. Offline experiments using HitRate@K demonstrate that graph and embedding-based methods significantly outperform the category-based baseline, effectively capturing latent user preferences and surfacing relevant, novel items.

Paper Citation

in Harvard Style

Keskin M., Teper E. and Keçeci S. (2025). User-Centric Product Discovery for Personalized e-Commerce Recommendations. In Proceedings of the 2nd International Conference on Advances in Electrical, Electronics, Energy, and Computer Sciences - Volume 1: ICEEECS; ISBN 978-989-758-783-2, SciTePress, pages 25-30. DOI: 10.5220/0014287000004848

in Bibtex Style

@conference{iceeecs25,
author={Mustafa Keskin and Enis Teper and Sinan Keçeci},
title={User-Centric Product Discovery for Personalized e-Commerce Recommendations},
booktitle={Proceedings of the 2nd International Conference on Advances in Electrical, Electronics, Energy, and Computer Sciences - Volume 1: ICEEECS},
year={2025},
pages={25-30},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0014287000004848},
isbn={978-989-758-783-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Advances in Electrical, Electronics, Energy, and Computer Sciences - Volume 1: ICEEECS
TI - User-Centric Product Discovery for Personalized e-Commerce Recommendations
SN - 978-989-758-783-2
AU - Keskin M.
AU - Teper E.
AU - Keçeci S.
PY - 2025
SP - 25
EP - 30
DO - 10.5220/0014287000004848
PB - SciTePress