A movie recommendation system, or a movie recommender system, is an ML-based approach to filtering or predicting the users’ film preferences based on their past choices and behavior.
Link to run the web application: https://mrs-prashantkr.herokuapp.com/
Used TMDB Movie Dataset form Kaggel https://www.kaggle.com/datasets/tmdb/tmdb-movie-metadata
- Python - To build the Machine Learning model.
- Jupyter Notebook (You can use any other IDE like Google Colab) - To train the model.
- Streamlit Framework - To create Web Application for our model.
- Heroku - To deploy our model.
- Pandas
- NumPy
- SciKit Learn
- Streamlit
- Requests
- Pickle
- Jupyter Notebook
- Pycharm (Any other IDE can work)
- Any Browser
- Dowload the Datasets
- Copy and paste the Jupyter Notebook ipynb code in a New Notebook in your system
- Generate the pickle file
- Create a python project in Pycharm (or any Python IDE)
- Import the pickle file in that project
- Use the Streamlit code template to build the web application
The code for this project was developed by Prashant Kumar, inspired by the materials from CampusX.
Refer the below screenshots working of the application.
Similarly you can select different movies form the picklist and get recommendation based on the selection.