 This paper presents a novel approach to predicting the capacitance of supercapacitor electrodes using machine learning techniques. The authors collected data from 147 publications and trained five different regression models to identify the most relevant factors affecting capacitance. They found that the specific surface area, presence of nitrogen doping, and potential window were the most significant descriptors for capacitance. This information can be used to estimate capacitance values for any given carbon-based electrode material, electrolyte, and testing method. This article was authored by Sakhit Mishra, Rajat Srivastava, Atta Muhammad, and others.