Abstract
This study aims to predict the volatility of stocks on the first day of Initial Public Offering (IPO) listing using machine learning methods, specifically the Random Forest algorithm. The data utilized is sourced from a IPO dataset obtained from Kaggle, including various variables such as final price, daily returns for the first seven days, industry sector, and warrant ratio. Random Forest was chosen due to its ability to handle complex variables and provide accurate predictions. The results indicate that the Random Forest model can predict IPO stock volatility with satisfactory accuracy, offering valuable insights for investors and market analysts to anticipate volatility risks on the first trading day. The study also highlights the importance of features such as closing price, daily returns, and warrant ratio in influencing volatility prediction. Therefore, this model can serve as an effective tool for investment decision-making in the Indonesian capital market.