GraphRAG-based Real-Time Recommendation

Graduate Researcher · in collaboration with LG Electronics · Jan 2026 – Present

As a Graduate Researcher on a GraphRAG-based Recommendation System (in collaboration with LG Electronics, Jan 2026 – Present), I am building a graph-based retrieval and reasoning pipeline for real-time recommendation of news and OTT content.

Pipeline from trending-search news detection through a news-content graph to an LLM that explains each recommendation.
Trending news are scored by a trend detector, linked into a news–content graph over shared topics and people, and the retrieved candidates are passed to an LLM that reasons over the graph path to explain the recommendation.

Key contributions

  • Built a real-time data pipeline for news and OTT content ingestion and processing.
  • Designed a dual-graph framework aligning news–content graphs via shared entities.
  • Developed a graph-based retrieval pipeline using multi-hop traversal to generate candidate content.
  • Integrated LLMs for path-based reasoning over graph structures, enabling explainable recommendations.