Smart Movie Recommendation System

Introduction

This project is a smart movie recommendation system designed to enhance the user experience by providing personalized movie recommendations based on user preferences, popular trends, and highly rated movies.

Features

• Personalized Movie Recommendations: Based on user history, preferences, and popular movie trends.
• Cross-Platform Compatibility: Developed using Kotlin to run on multiple operating systems.
• Firebase Analytics Integration: Monitors user interactions to improve recommendation accuracy.

Movie Recommendation System

Step 1: Selecting Preferred Movies

Step 2: Display of Liked Movies

Step 3: Personalized Movie Recommendations

Modules

1. User: Interacts with the application to receive movie recommendations.
2. Application: The core module where movies are recommended and played.
3. Algorithm Service: Utilizes machine learning algorithms (content-based and collaborative filtering) to generate recommendations.
4. Database: Stores user profiles and movie preferences.

Project Design

Existing System

Most current movie recommendation systems rely on user profile analysis using basic filtering techniques. These systems often lack innovation and do not fully consider user preferences.

Proposed System

The proposed system uses a hybrid recommendation approach, combining content-based and collaborative filtering to provide more accurate and personalized movie recommendations. The system also suggests related movies and integrates a voice assistant for hands-free usage.

Steps to Download and Use

1. Clone the Repository

git clone https://github.com/arjunnrajput/Smart-ML-Based-Movie-Recommendation-System/ml

2. Open in Android Studio

• Open Android Studio and select Open an existing project.
• Navigate to the cloned directory and open it.

3. Configure Firebase

• Create a new project in the Firebase Console.
• Download the google-services.json file from Firebase and place it in the app/ directory of your project.
• Enable Firebase Analytics in your project.

4. Build the Project

• Sync the project with Gradle files.
• Build the project to ensure all dependencies are resolved.

5. Run the App

• Connect an Android device or use an emulator.
• Click the Run button in Android Studio to install the app on your device.

6. Test Features

• Register or log in to the app.
• Explore the movie recommendations, like your favorite movies, and test voice commands.

Implementation Steps

1. Get Sample Code: Start with the provided codebase.
2. Import Starter App: Import the project into Android Studio.
3. Create Firebase Console Project: Set up Firebase for data management and analytics.
4. Run the Starter App: Launch the initial version on a device.
5. Add Firebase Analytics: Integrate to track user interactions.
6. Export Data to BigQuery: Analyze data for model training.
7. Preprocess and Train Model: Use TensorFlow Lite for the recommendation model.
8. Integrate the Model: Implement the trained model into the app.
9. Run the App: Test the final version with movie recommendations.

Testing

• Unit Testing: Ensures the functionality of the recommendation system, particularly the movie recommendation feature.

Conclusion and Future Scope

The Smart Movie Recommendation System successfully delivers personalized movie recommendations. Future improvements may include refining the recommendation algorithms and expanding the system's features based on user feedback.