🎬 Movie Recommendation System

This project implements a Movie Recommendation System using Python.
The system suggests movies to users based on similarity measures and user preferences, helping improve content discovery and user experience.

The project is implemented and executed using Google Colab.

---

📌 Project Overview

Movie recommendation systems are widely used by platforms like Netflix, Amazon Prime, and IMDb to suggest relevant movies to users.

This project focuses on:

• Understanding recommendation system concepts
• Implementing a content-based recommendation system
• Using similarity techniques to recommend movies

---

🧠 Recommendation Approach Used

🔹 Content-Based Filtering

• Recommends movies similar to a selected movie
• Uses movie attributes such as:
  • Genres
  • Keywords
  • Overview / Description
• Measures similarity using Cosine Similarity

---

🛠️ Technologies Used

• Python
• Google Colab
• Pandas – Data manipulation
• NumPy – Numerical operations
• Scikit-learn – Similarity computation
• NLTK / Text Processing (if applicable)

---

📂 Project Structure

Movie-Recommendation-System/ │ ├── Movie_Recommendation_Systems.ipynb # Main Colab notebook ├── README.md # Project documentation └── requirements.txt # Project dependencies

▶️ How to Run the Project

✅ Prerequisites

->Google account

->Internet connection

->Basic knowledge of Python

->No local setup is required since the project runs on Google Colab.

🔹 Step 1: Open the Notebook in Google Colab

Go to Google Colab

Click on File → Upload notebook

Upload the file: (https://colab.research.google.com/drive/1ynqNEKMB9xrRx53-l60FX7mKR6tEeQOS?usp=sharing)

Movie_Recommendation_Systems.ipynb

🔹Step 2: Install Required Libraries

Most required libraries are pre-installed in Colab.

If any library is missing, run the following cell: pip install pandas numpy scikit-learn

🔹 Step 3: Run the Notebook Cells

Click on Runtime → Run all, OR Run each cell one by one in sequence:

Import libraries

Load dataset: https://drive.google.com/file/d/1cCkwiVv4mgfl20ntgY3n4yApcWqqZQe6/view

Preprocess movie data

Compute cosine similarity

Generate recommendations

🔹 Step 4: Get Movie Recommendations

Provide a movie name as input (inside the notebook)

The system outputs a list of similar movies

Example:

recommend_movies("Inception")

🔹 Step 5: View Results

Recommended movie titles will be displayed directly in the notebook output

---

⚠️ Notes

Ensure the movie name entered exists in the dataset

Restart runtime and re-run all cells if any error occurs

---

👩‍💻 Author

Ravali Koppisetti