Episode
How Data Scientists Build Recommendation Engines from Scratch
- Podcast
- The Data Science Podcast with Fexingo: Analytics, Machine Learning, and Data-Driven Conversations
- Published
- Jun 10, 2026
- Duration seconds
- 577
- 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-build-recommendation-engines-from-scratch/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-build-recommendation-engines-from-scratch.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
Lucas and Luna walk through the real-world process of building a recommendation engine, using the open-source MovieLens dataset as their running case. They cover collaborative filtering, matrix factorization, the cold-start problem, and the engineering trade-offs between offline accuracy and online performance. Lucas explains why the Netflix Prize algorithm never made it into production, and Luna challenges the assumption that more data always helps. The episode ends with a practical checklist for any data scientist starting their first recommender system. #RecommendationEngine #CollaborativeFiltering #MatrixFactorization #MovieLens #NetflixPrize #ColdStart #DataScience #MachineLearning #Tech #Technology #FexingoBusiness #BusinessPodcast #DataEngineering #OfflineMetrics #OnlineAbtesting #Sparsity #ImplicitFeedback #ProductionML Keep every episode free: buymeacoffee.com/fexingo