Personality Based Lipstick Color Recommender System using K-Nearest Neighbors Algorithm
Lipstick is a lip color which available in many colors. A research said instant valuation of woman personality can be figured by their lipstick color choice. Therefore there is a necessity to use the right lipstick color to obtain a harmony between personality and appearance. This experiment was conducted to give lipstick color recommendation by using K-Nearest Neighbors algorithm, and Myers-Briggs Type Indicator (MBTI) personality test instrument. The system was built on Android application. Euclidean distance value is affected by 5 factors which are age, introvert, sensing, thinking, and judging. Lipstick color recommendation is obtained by fetching 7 training data with nearest Euclidean distance when compared to personality test result. The colors used in this experiment are nude, pink, red, orange, and purple. After evaluation, it is obtained the application’s accuracy of 87.38% which considered as good classification, both precision and recall with 75.68% which considered as fair classification. The score for software quality is 79.13% which considered as good quality.
Keywords—K-Nearest Neighbors, Data Mining, Myers-Briggs Type Indicator,Recommender System, Lipstick.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
1. Accepted paper’s author should read and approve the content of Copyright Transfer Form and send it back via editorial email address.
2. Copyright Transfer Form must be signed by the first author of the paper.