Episode
How Data Scientists Use Knowledge Graphs for Recommendation Systems
- Podcast
- The Data Science Podcast with Fexingo: Analytics, Machine Learning, and Data-Driven Conversations
- Published
- Jul 16, 2026
- Duration seconds
- 498
- Processing state
not_requested
Actions
POST https://stenobird.com/v1/public/podcasts/the-data-science-podcast-with-fexingo-analytics-machine-learning-and-data-driven-conversations-7871831/episodes/how-data-scientists-use-knowledge-graphs-for-recommendation-systems/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/the-data-science-podcast-with-fexingo-analytics-machine-learning-and-data-driven-conversations-7871831/how-data-scientists-use-knowledge-graphs-for-recommendation-systems.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
On this episode of The Data Science Podcast, Lucas and Luna explore how knowledge graphs are transforming recommendation systems beyond traditional collaborative filtering. They dive into a real-world case from a major e-commerce platform that improved cross-category discovery by 22 percent using graph-based embeddings. The conversation covers the trade-offs between graph neural networks and embedding-based methods, the challenge of cold-start items, and why encoding user intent as relational paths matters more than ever. If you've ever wondered why your streaming service suggests a documentary about fungi after you watched a true crime series, this episode explains the graph structure behind that leap. #KnowledgeGraphs #RecommendationSystems #GraphNeuralNetworks #Embeddings #AI #MachineLearning #DataScience #Ecommerce #ColdStart #UserIntent #GraphBasedML #Technology #FexingoBusiness #BusinessPodcast #DataSciencePodcast #GraphAlgorithms #Personalization #GraphEmbeddings Keep every episode free: buymeacoffee.com/fexingo