🎬 Just built and deployed my Movie Recommendation System 🚀 Excited to share my full-stack project where I implemented a personalized movie recommendation engine using user preferences and content-based filtering! 🔗 Live Demo: https://lnkd.in/gUFbRXWz 🎥 Demo Video: (attached below 👇) 💡 What makes it interesting? ✔ Personalized recommendations based on likes, ratings & wishlist ✔ Search-based movie suggestions ✔ Smart fallback recommendation (genre-based) ✔ Fully deployed frontend + backend 🧠 Tech Stack: ⚡ React (Vite) + Tailwind CSS ⚙️ Node.js + Express 🗄️ MongoDB 🎥 TMDB API (for movie posters) ✨ Key Features: ❤️ Wishlist system 👍 Like / 👎 Dislike ⭐ Ratings & Reviews 👤 Profile with editable bio & profile pic 🎯 Recommendation engine ⚠️ Fun challenge: The original similarity matrix (~300MB) couldn’t be deployed, so I implemented a smart fallback recommendation system to ensure smooth user experience in production. This project helped me understand: 👉 Recommendation systems 👉 Full-stack deployment (Vercel + Render) 👉 Real-world problem solving Would love your feedback 🙌 #FullStackDevelopment #ReactJS #NodeJS #MongoDB #WebDevelopment #MachineLearning #Projects #OpenToWork #StudentDeveloper

To view or add a comment, sign in

Explore content categories