Systematic Literature Review: Predicted Color Output in UI/UX Design Using Machine Learning

An attractive user interface (UI) design is greatly influenced by the selection of appropriate colors, but the selection process tends to be subjective. To address this challenge, this study was conducted to identify commonly used machine learning techniques and evaluate their effectiveness in recommending colors based on RGB and HSL features. The method used was a Systematic Literature Review (SLR) of 39 articles published between 2020 and 2025. The study was conducted through three main stages, namely planning, implementation, and reporting. The review results show that approaches such as K-Means are widely used in the dominant color extraction stage, while classification algorithms such as Support Vector Machine (SVM), Artificial Neural Network (ANN), and Random Forest are applied for color prediction and recommendation. Random Forest is one of the models that shows superior performance, especially in terms of prediction stability and the ability to handle large numbers of variables. The model development process usually begins with color quantization, followed by data labeling and model training. Based on these findings, it can be concluded that Random Forest is a reliable model in color recommendation systems, especially when supported by good data preprocessing stages and proper parameter tuning.