International Research Journal of Education and Technology

In fashion websites i.e., online shopping (e.g., Flipkart, Myntra, Amazon), popular or high-quality fashion outfits are usually designed by fashion experts and followed by large audiences. Composing fashion outfits involves deep understanding of fashion standards while incorporating creativity for choosing multiple fashion items (e.g., Jewelry, Bag, Pants, Dress). An existing user can view a comment of others of that particular product and can view related products for user viewing product with irrelevant of color. In this proposed project we are introducing a new concept known as outfit automatically. In this concept when a user views a product, they can view relevant products based on color and on the appearances based on the meta-data. Also, we propose to leverage outfit popularity on fashion-oriented websites to supervise the scoring component. The scoring component is a multi-modal multiinstance deep learning system that evaluates instance aesthetics and set compatibility simultaneously. In online shopping we can watch advertisements, here we have a chance of fake, hackers, and unwanted URL’s. To avoid this, we are going to filter these advertisements by using concept known URL pattern matching technique. By this we will filter all advertise and allow only needful advertisement to the user end.