TasteGraph is a personalized movie discovery system that moves beyond fixed genre tags and generic similarity scores. The system represents users, movies, genres, actors, and directors as a Neo4j knowledge graph. In parallel, an autoencoder compresses high-dimensional movie features and user preference signals into a compact 64-dimensional latent representation. Users select several favorite films, and TasteGraph builds multiple local taste neighborhoods instead of reducing their preferences to a single average point. It then recommends nearby movies and explains each recommendation through relationship paths in the graph. Our prototype demonstrates three core steps: 1. Select a favorite movie. 2. Calculate its local neighborhood. 3. Display nearby recommendations with explainable connections. The project combines graph relationships with learned representations to create recommendations that are more personal, exploratory, and understandable. The next step is to evaluate the system with a larger dataset and retrain a commercial version using only properly authorized data.
Built at OpenAI Codex - Fast Hacks in Tokyo
TasteGraph
TasteGraph is a personalized movie discovery system that moves beyond fixed genre tags and generic similarity scores. The system represents users, movies, genres, actors, and directors as a Neo4j knowledge graph. In parallel, an autoencoder compresses high-dimensional movie features and user preference signals into a compact 64-dimensional latent representation. Users select several favorite films, and TasteGraph builds multiple local taste neighborhoods instead of reducing their preferences to a single average point. It then recommends nearby movies and explains each recommendation through relationship paths in the graph. Our prototype demonstrates three core steps: 1. Select a favorite movie. 2. Calculate its local neighborhood. 3. Display nearby recommendations with explainable connections. The project combines graph relationships with learned representations to create recommendations that are more personal, exploratory, and understandable. The next step is to evaluate the system with a larger dataset and retrain a commercial version using only properly authorized data.
Keep exploring what builders shipped.
HackerSquad project
Nihongo Lens
Understand it. Use it at work. Nihongo Lens is a five-minute Japanese learning companion for foreign workers living in Japan. It turns a real workplace conversation—or something the user wants to say in English—into an understandable translation, a natural Japanese reply, audio practice, a practical shift mission, and personalized review cards.
GEO Card
geo card
Run a free AI search readiness audit. Check crawler access, schema, entity clarity, and citation-ready content—no signup or API keys required. https://geo-card-ruby.vercel.app/
DE
Belief Graph
Start with a statement you encountered. Break it down into beliefs required for the statement to make sense. Choose if you agree with all of the required beliefs. Lets you see where you agree or disagree with someone. https://belief-graph.redacid.chatgpt.site/