Inspiration
Today we live in a world of fashion. Fashion depends on person to person. It differs based on the person, place, community, and most importantly, time. Online shopping platforms provide consumers with convenience of shopping at home.
What it does
Fashion recommendation systems provide recommendations to consumers based on their browsing, pictures, and previous purchase history. It makes people’s life convenient by suggesting good outfits to users.
How we built it
Importing the required structures and models. A framework is an interface that enables coders to create and implement machine learning models more quickly and easily. Feature extraction methods are used to obtain features that will be helpful in picture classification and recognition. Feature extraction is a technique for separating variables into features, thereby decreasing the amount of data that must be handled while precisely and fully characterising the original data collection. There are several methods for determining the k closest neighbours. The Euclidean distance, one of the most commonly used methods, is used to determine the distance between two points in a plane or three-dimensional space. The Pythagorean theory underpins the Euclidean distance. Finally, it makes suggestions based on the given input.
What we learned
As a result, new research into incorporating social media photos within fashion recommendation algorithms have exploded in popularity. We have developed a Recommendation system in which we suggest the consumer clothing based on their browsing.
What's next for Fashion Recommendation System
Future work for this project could be to apply on an online store database instead of the current clothing database to suggest clothes. A user could then directly buy the recommended clothes if he/she wants to. And it can even be extended as recommending fashion based on the occasion.
Log in or sign up for Devpost to join the conversation.