"You may also like"
summary
Builds a working recommender that indexes TMDB metadata and joins GroupLens user ratings to produce re-ranked suggestions. Uses Solr MoreLikeThis for a fast first-pass, then tunes edismax weights on TMDB columns, then re-ranks the top 100 with a Learning-to-Rank pipeline using Cortex/MxNet producing ~300 movie features plus 3 user features, training (default 1000 iterations). Matches MovieLens IDs to TMDB, ships a Corona Clojure wrapper and demo repo that run end-to-end.
AI-written summary · about
chapters (11)
- 0:00Introduction and team
- 1:26Designing the starter kit
- 3:54Content-based filtering approach
- 6:42Why choose Solr over others
- 9:10Setting up Solr with Closure
- 13:22Using MoreLikeThis for recommendations
- 17:33Collaborative filtering with re-ranking
- 24:39Balancing recommendation strategies
- 26:06Closure vs REST API benefits
- 28:58Acknowledgments and credits
- 30:23Q&A session
related talks
57mHands-On with LLM-Powered Recommenders: Hybrid Architectures
01h 21mUnlocking Personalization: A Deep Dive into Modern Recommendation Algorithms
01h 48mRecommendation engines explained
15mWhat they didn’t teach you in Grad School #bbuzz
46mBeyond Bag of Words A Practitioner’s Guide to Advanced NLP
48mCollective Intelligence
33mPicking What to Watch Next: Build a Recommendation System
38mBuilding Recommender System in PHP8