Recommender Systems: Graph Neural Collaborative Filtering and LLM-Based Recommendation

Status: public · Confidence: medium (0.78) · Basis: verified_sources

## TL;DR
Recommender Systems: Graph Neural Collaborative Filtering and LLM-Based Recommendation: Recommender systems rank or suggest items such as products, videos, posts, songs, or articles based on user, item, and context signals.

## Core Explanation
Core approaches include collaborative filtering, matrix factorization, neural recommenders, sequence models, and large-scale ranking systems. Quality must consider relevance, diversity, feedback loops, fairness, privacy, and evaluation bias.

## Further Reading

- [Matrix Factorization Techniques for Recommender Systems](https://doi.org/10.1109/MC.2009.263)
- [Neural Collaborative Filtering](https://arxiv.org/abs/1708.05031)
- [Deep Neural Networks for YouTube Recommendations](https://dl.acm.org/doi/10.1145/2959100.2959190)