Earticle

초록

영어

The rapid growth of e-commerce platforms demands recommendation systems that balance scalability with representational expressiveness. While Matrix Factorization (MF)-based collaborative filtering offers computational efficiency, it fails to capture high-order contextual relationships among items. Graph Neural Networks (GNNs) address this limitation but incur prohibitive computational costs in large-scale, real-time settings. To resolve this tradeoff, we propose a unified hybrid framework integrating MFbased candidate generation and GNN-based re-ranking within a retrieve–then–rank architecture. The MF stage efficiently generates a candidate set, while the GNN stage refines rankings via a heterogeneous graph incorporating user–item interactions, item attributes, and category structures. We further introduce an availability-aware scoring mechanism that integrates real-time stock information to enhance practical applicability. Extensive experiments on a large-scale e-commerce dataset demonstrate that the proposed framework consistently outperforms baseline methods, effectively mitigates data sparsity, and maintains computational efficiency suitable for real-world deployment.

목차

Abstract
1. Introduction
2. Related Works
2.1. Retrieval and Ranking in Recommendation Systems
2.2 Deep Learning and Graph-based Recommendation
3. Methodology
3.1. Matrix Factorization for Implicit Feedback
3.2. Light Graph Convolutional Network (LightGCN)
4. Proposed Method
4.1. Hybrid Architecture and Notations
4.2. Step 1: Data Preprocessing and Time-Aware Splitting
4.3. Step 2: Candidate Generation via ALS& MF-BPR Ensemble
4.4. Step 3: Context-Aware Re-ranking via GNN
4.5. Step 4: Hybrid Integration and Availability-Aware Weighting
5. Experiments
5.1. Dataset Description
5.2. Data Preprocessing
5.3. Performance Metrics
5.4. Experimental Setup
6. Results
6.1. Baseline Comparison
6.2. Hyperparameter Sensitivity Analysis
6.3. Top-K Analysis
6.4. Implications
7. Conclusion
References

키워드

저자

• Yoonsung Kim [ Department of Electronics Engineering, Tech University of Korea ]
• Seungwon Park [ Department of Business Administration, Tech University of Korea ]
• Won Seo [ Department of Mechatronics Engineering, Tech University of Korea ]
• Yuhee Kwon [ Department of Mechatronics Engineering, Tech University of Korea ] Corresponding Author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  한국경영정보학회 정기 학술대회 [KMIS Conference]

• 간기

  반년간

• 수록기간

  1990~2026

• 십진분류

  KDC 325 DDC 658