Recommending similar products (apparel) to the given product (apparel) in any e-commerce websites.
Product recommendations are the alternative way of navigating through the online shop. Showing similar products to the user which user is searching for.
The recommendation engine, uses information about 1,80,000 products and each product will have multiple features named. We will try multiple techniques using text/title and image to recommend similar products/items Each product/item has 19 features in the raw dataset out of these 19 features, we will be using only 6 features
- asin ( Amazon standard identification number)
- brand ( brand to which the product belongs to )
- color ( Color information of apparel, it can contain many colors as a value ex: red and black stripes )
- product_type_name (type of the apperal, ex: SHIRT/TSHIRT )
- medium_image_url ( url of the image )
Using idf_w2v, brand, color, image features for finding the similar images using weighted average method.