Everyday a million products are being recommended to users based on popularity and other metrics on e-commerce websites. The most popular e-commerce website boosts average order value by 50%, increases revenues by 300%, and improves conversion. In addition to being a powerful tool for increasing revenues, product recommendations are so essential that customers now expect to see similar features on all other eCommerce sites.
Amazon Reviews data (http://jmcauley.ucsd.edu/data/amazon/) The repository has several datasets. For this project, we are using the Electronics dataset.
To make a recommendation system that recommends at least five(5) new products based on the user's habits.
- Read and explore the given dataset.
- Take a subset of the dataset to make it less sparse/ denser.
- Build Popularity Recommender model.
- Split the data randomly into a train and test dataset.
- Build Collaborative Filtering model.
- Get top - K ( K = 5) recommendations. Since our goal is to recommend new products to each user based on his/her habits, we will recommend 5 new products.