The Amazon beauty dataset has over 2 Million customer reviews and ratings of Beauty related products sold on their website.
It contains
- the unique UserId (Customer Identification),
- the product ASIN (Amazon's unique product identification code for each product),
- Ratings (ranging from 1-5 based on customer satisfaction) and
- the Timestamp of the rating (in UNIX time)
This dataset contains product reviews and metadata from Amazon, including 142.8 million reviews spanning May 1996 - July 2014.
This dataset includes reviews (ratings, text, helpfulness votes), product metadata (descriptions, category information, price, brand, and image features), and links (also viewed/also bought graphs).
Performed exploratory data analysis on the data and extracted relevant info from the data.
Data was split into train and test and different types of recommender systems were used to get varied results from the data.Proper hyper parameter tuning was performed to increase our models recommending ability.
Finally built a product recommendation engine which recommends n products to the customers and also performs well given the amount and complexity of the dataset.