Prediction of rainfall in semi-arid regions is a vital role for proper planning of irrigation scheduling, crop water requirement, drought assessment, water resources development & management. The primary objectives of this study are: (i) to develop an appropriate model for monthly rainfall estimation in the Ajmer region of Rajasthan, and (ii) to conduct a comparative performance assessment of Random Forest (RF) and Support Vector Machine (SVM) models. Several combinations of input parameters were utilized based on the monthly rainfall data lagging technique for the development of models. The rainfall data set collected from the water resources department of Rajasthan covers the period from 1986 to 2016. In this study, random forest (RF) and support vector machine (SVM) models were applied to predict monthly rainfall. The results obtained by SVM and RF model were compared with observed rainfall and predicted model based on statistical indices such as Nash Sutcliffe Efficiency (NSE), Correlation Coefficient (CC), Root Mean Square Error (RMSE), and Normalized Root Mean Square Error (nRMSE), Mean absolute error (MAE), Willmott’s Index (WI) and Legates & McCabe’s Index (LMI). The results show that the performance of the RF model during testing phase (NSE = 0.544, CC = 0.770, WI = 0.795, LMI = 0.450, RMSE = 0.154 mm (normalized), & nRMSE = 1.121, MAE = 0.096) with 12 input variables is found to be superior in comparison to the SVM model in estimating monthly rainfall for proposed study area.