You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.
A web application implementing a machine learning-based recommendation system for Amazon using users ratings. Built using python and streamlit, this project demonstrates the use of collaborative filtering and content-based algorithms, as well as classic ML and EDA, to enhance user shopping experiences.
Notifications You must be signed in to change notification settings
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Go to fileAmazon product recommendation app is an app for predicting 5 recommended items for a given user. The engine behind the app is an ML model that has learned the users prior activities on Amazon: items rated, similar users activity, item ratings by other users.
The Amazon product ratings prediction.ipynb notebook contains the research and analysis conducted for the Amazon Recommendation System project. It encompasses data exploration, preprocessing, model building, and evaluation. The notebook outlines the methodology behind the recommendation engine and discusses the results and insights gained from the data. The only dataset needed for the project is the amazon_reviews.csv, and it can also be downloaded directly from kaggle. The rest of the datasets are just the byproducts and outputs of this dataset and the Jupyter notebook commands and src scripts. After running all cells in the notebook one by one, all relevant datasets will be created and the streamlit app can run correctly.
pip install streamlit pandas numpy