Cosmetic Product Selection Using Machine Learning
S Rubasri, S Hemavathi, K. Jayasakthi Velmurugan, A. Sangeerani Devi, K. Latha, N. Gopinath · 2022 International Conference on Communication, Computing and Internet of Things (IC3IoT) · 2022
Whenever a person wants to try a new cosmetic item, it's so difficult to choose. It's actually more than difficult. It's sometimes scary because new items that have never tried end up giving skin trouble. It is known that the information we need is on the back of each product, but it's really hard to interpret those ingredient lists unless you're a chemist. So instead of just being worried about the new choice, we decided to use Machine Learning technology to provide a solution for this problem. This paper suggests a simple cosmetic recommendation system. we extracted the effective cosmetic ingredients for each user attribute and developed a recommender system based on ingredients. We did a web scraping from sephora page, from where cosmetic ingredient information and chemicals used are extracted. Then NLP concepts are applied to the chemicals and a Document term matrix (DTM) is made. The matrix is filled with 1 or 0. If an ingredient is in a cosmetic, the value is 1. If not, it remains 0. All of the cosmetic items in our data will be vectorized into two-dimensional coordinates, and the distances between the points will indicate the similarities between the items. Finally, a plot is made. The plot is made as a scatter plot using plotly and add a hover tool to show that information.