Consumers' fashion preferences are influenced by a range of variables including: demographics, location, personal preferences, social influences, age, gender, season, and culture. Additionally, recent study on fashion recommendation demonstrates that fashion preferences differ not only from one country to another but also from one city to another. Combining fashion preferences with the aforementioned variables related to clothing selections that may help researchers better understand customer preferences by transmitting the picture attributes. As a result, fashion designers and merchants benefit by studying client preferences and suggestions. Additionally, consumers' data gathered from clothing choices and product preference have become available on the Internet in the form of text, opinions, images and pictures. Both online and offline fashion retailers are using these platforms to reach billions of users who are active on the Internet. Therefore, e-commerce has become the predominant channel for shopping in the recent years.. With the development of e-commerce technology, A large number of consumers prefer to buy garments through e-commerce websites. But on the internet, where the large majority of choices have become overwhelming, it is necessary to filter, prioritize, and present pertinent information quickly according to every one's preferences. Recommendation systems (RSs) solve this problem through sifting a significant amount of dynamically created data to offer customers personalized content and suggestions. The suggestions relate to various decision-making processes, such as what items to buy, what music to listen to, or what online news to read. This paper examines the various traits and potentials of the prediction techniques used in Fashion Recommendation systems (FRs).