A content-based movie recommendation system built with Python. This project recommends movies based on textual similarity using Natural Language Processing (NLP) techniques.

• 🔍 Recommend similar movies based on a selected title
• 🧠 Utilizes content-based filtering
• 💻 Beginner-friendly code with a clean interface (Jupyter Notebook)
• 📊 Uses NLP techniques for analyzing textual data

• Includes movie titles, overviews, keywords, genres, and cast
• Preprocessed to extract meaningful content for similarity analysis

• Python
• Pandas
• Scikit-learn
• NLP – TF-IDF, CountVectorizer
• Cosine Similarity

1. 🧹 Data cleaning and preprocessing
2. 🔡 Vectorization of textual features
3. 📐 Calculation of similarity scores using cosine similarity
4. 🎯 Retrieval of top-N similar movies based on input

Clone the repository and install the dependencies:

git clone https://github.com/ShridhiGupta/WhatToWatch.git
cd WhatToWatch
pip install -r requirements.txt

Launch Jupyter Notebook and execute the cells:

jupyter notebook

Choose your input movie title to get recommendations.

• 🤝 Add collaborative filtering
• 🌐 Build a web interface using Streamlit or Flask
• 🎞️ Integrate TMDB API for posters, ratings, and trailers

Here’s a quick look at the movie recommendation output:

This project is licensed under the MIT License.

Feel free to contribute, suggest improvements, or ⭐ star the repository!