MPIF in E-Commerce Recommendation: Application of Multi-Pairwise Ranking with Heterogeneous Implicit Feedback
Electronics · 2026-02-27 · 15 (5) · 985
DOI: 10.3390/electronics15050985 ↗At a glance
Journal article in Electronics, published online on 2026-02-27. Written by Cui Chen and 5 co-authors. Cited 1 times so far (Crossref); 27 references. The full text is freely available (open access, CC BY 4.0). Funded by: Beijing Institute of Graphic Communication, the Publishing science emerging interdisciplinary platform construction project of Beijing Institute of Graphic Communication, Open Foundation of State key Laboratory of Networking and Switching Technology.
Abstract (original language)
To address the one-class collaborative filtering (OCCF) issue in e-commerce recommendation with only positive implicit feedback, mainstream methods adopt pairwise preference learning represented by Bayesian Personalized Ranking (BPR). However, BPR relies on an invalid assumption and suffers from severe data sparsity. This paper proposes Multi-pairwise Ranking with Heterogeneous Implicit Feedback (MPIF), which exploits heterogeneous implicit and auxiliary information to mine deep user preferences, constructs six pairwise preferences for classified items, and optimizes the model via stochastic gradient descent (SGD). Experiments on three real-world datasets verify that MPIF+ outperforms all state-of-the-art baselines on Normalized Discounted Cumulative Gain at rank 5 (NDCG@5), Precision at rank 5 (Pre@5), Recall at rank 5 (Rec@5), and Area Under Curve (AUC). It yields maximum improvements of 34.2%, 5.5%, and 32.9% on NDCG@5 for the Sobazaar, Retailrocket, and REES46 datasets, respectively, achieving significant and stable recommendation gains.
Funding
- Beijing Institute of Graphic Communication
- the Publishing science emerging interdisciplinary platform construction project of Beijing Institute of Graphic Communication
- Open Foundation of State key Laboratory of Networking and Switching Technology
- Beijing Municipal Education Commission & Beijing Natural Science Foundation Co-financing Project
- Project of Construction and Support for high-level Innovative Teams of Beijing Municipal Institutions
Cite
APA
Chen, C., Wang, H., Liu, L., Qin, P., Ma, S., & Cheng, M. (2026). MPIF in E-Commerce Recommendation: Application of Multi-Pairwise Ranking with Heterogeneous Implicit Feedback. Electronics, 15(5), 985. https://doi.org/10.3390/electronics15050985
Vancouver
Chen C, Wang H, Liu L, Qin P, Ma S, Cheng M. MPIF in E-Commerce Recommendation: Application of Multi-Pairwise Ranking with Heterogeneous Implicit Feedback. Electronics. 2026;15(5):985. doi:10.3390/electronics15050985
BibTeX
@article{Chen2026,
author = {Chen, Cui and Wang, Hongjuan and Liu, Long and Qin, Peijun and Ma, Siyuan and Cheng, Mingzhi},
title = {MPIF in E-Commerce Recommendation: Application of Multi-Pairwise Ranking with Heterogeneous Implicit Feedback},
journal = {Electronics},
year = {2026},
volume = {15},
number = {5},
pages = {985},
doi = {10.3390/electronics15050985}
}
EUVIMED