This study compares various imputation methods for daily rainfall data missing values in East Coast Peninsular Malaysia using data from 48 rainfall stations. Methods evaluated include mean substitution, nearest neighbor, random forest, non-linear iterative partial least squares (NIPALS), and Markov Chain Monte Carlo (MCMC), with performance assessed via multiple linear regression and statistical metrics like RMSE and MAE. The results indicate that the random forest combined with multiple linear regression is the most effective approach for addressing missing rainfall data in this region.