01
Recommender Systems
Working with large-scale purchase data from e-commerce, we study how to feed real service signals, such as items bought together, into Transformer-based sequence models to raise recommendation quality.
Sequential RecommendationBERTE-Commerce
Related work
- Enhancing E-Commerce Recommendation Systems with Multiple Item Purchase Data: A Bidirectional Encoder Representations from Transformers-Based Approach Applied Sciences, 2024
- Self-Supervised Recommendation via Multi-View Fusion of Co-purchase Graph and Text Embeddings Korea Computer Congress 2026 (KCC 2026), 2026
- Next-Item Recommendation with View-wise Normalized Graph, Text, and Image Fusion KICS Fall Conference 2026 (Korean Institute of Communications and Information Sciences), 2026
- Leveraging Concurrent Purchase History for Enhanced E-commerce Recommendations Proceedings of the 2023 Summer and Fall Conference of the Korean Artificial Intelligence Association, 2023