🎬 PopFlix

"Because scrolling for 45 minutes is a real horror movie."

PopFlix is a smart movie recommendation system powered by machine learning. Just pick a movie you love, and PopFlix will suggest five similar films — complete with posters and titles.

📌 Project Highlights

• 🔍 Content-Based Filtering: Uses movie overviews and metadata (genres, keywords, cast, etc.) to compute similarities.
• 📐 Cosine Similarity: Quantifies how close two movies are in terms of their content.
• 🎥 TMDB Dataset: Real-world movie data including titles, overviews, cast, crew, genres, and more.
• ⚡ Fast & Accurate: Provides recommendations in real-time.

🧠 How It Works

1. Preprocessing: Cleans and merges relevant movie data.
2. Feature Engineering: Creates a combined string of keywords, genres, cast, director, etc.
3. Vectorization: Uses CountVectorizer or TfidfVectorizer to convert text to numeric vectors.
4. Similarity Scoring: Computes cosine similarity between movie vectors.
5. Recommendation: Suggests top N similar movies based on your input.

📁 Dataset

TMDB Movie Metadata:

• Kaggle: TMDB Movie Dataset
• Google Drive Backup: Download Link

🛠 Built With

• Programming Language: Python
• Libraries & Tools: Pandas, NumPy, Scikit-learn, Jupyter Notebook
• Dataset: TMDB Movie Metadata

🚀 Getting Started

1. Clone the repository

git clone https://github.com/YourUsername/PopFlix.git
cd PopFlix