MemRerank: Preference Memory for Personalized Product Reranking
📰 ArXiv cs.AI
MemRerank is a preference memory framework for personalized product reranking using user purchase history
Action Steps
- Distill user purchase history into concise signals
- Use query-independent signals for personalized product reranking
- Evaluate the effectiveness of MemRerank using end-to-end benchmarks
Who Needs to Know This
Product managers and AI engineers can benefit from this framework to improve personalized product recommendations for users
Key Insight
💡 MemRerank framework effectively uses user purchase history for personalized product recommendations
Share This
💡 Personalized product reranking with MemRerank
Key Takeaways
MemRerank is a preference memory framework for personalized product reranking using user purchase history
Full Article
Title: MemRerank: Preference Memory for Personalized Product Reranking
Abstract:
arXiv:2603.29247v1 Announce Type: cross Abstract: LLM-based shopping agents increasingly rely on long purchase histories and multi-turn interactions for personalization, yet naively appending raw history to prompts is often ineffective due to noise, length, and relevance mismatch. We propose MemRerank, a preference memory framework that distills user purchase history into concise, query-independent signals for personalized product reranking. To study this problem, we build an end-to-end benchmar
Abstract:
arXiv:2603.29247v1 Announce Type: cross Abstract: LLM-based shopping agents increasingly rely on long purchase histories and multi-turn interactions for personalization, yet naively appending raw history to prompts is often ineffective due to noise, length, and relevance mismatch. We propose MemRerank, a preference memory framework that distills user purchase history into concise, query-independent signals for personalized product reranking. To study this problem, we build an end-to-end benchmar
DeepCamp AI