A recommendation algorithm implemented with Biased Matrix Factorization method which is tested over 1 million movielens dataset with state-of-the-art validation RMSE around ~ 0.83-0.84 and over modified movielns dataset during Capillary Technology Data Science Challenge for recommending 5 movies to 2245 test users.
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
- Tensorflow - Used in Deep Neural Network to create models
- Numpy - Multidimensioanl Mathematical Computing
- Pandas - Used to load dataset
- Matplotlib - Used to plot Graph
Clone the repository
git clone https://github.com/zishansami102/Recommendation-Engine
Run the following command to start training model with movie lens data
python train.py
Run the following command to start training model with Capillary Technology modified movie lens data
python captrain.py
Run the following command to generate a file which test the recommended ratings to the users in training dataset.
python run.py
To train for new unknown user, edit the movieId and ratings in retrain.py to observe the predicted ratings on modified dataset
python retrain.py
Build websites with AI, publish in seconds - Makeweb.ai
To start contributing in this repository, create an issue and then start working.