M1 money is the most liquid form of money supply because all its components (currency and giral) can be directly used for daily transactions and reflect the dynamics of public consumption. M1 money forecasting is necessary to anticipate its fluctuations that can affect price stability and inflation. This study aims to compare the results of M1 money forecasting with the Seasonal Autoregressive Integrated Moving Average (SARIMA) and Support Vector Regression (SVR) methods. The M1 Money data is divided into two, 80% training data from January 2010 to February 2021 and 20% testing data from March 2021 to December 2023. SARIMA and SVR modeling were carried out separately and then the best model was selected based on the smallest Mean Absolute Percentage Error (MAPE). The results of the study found that the best SARIMA model is SARIMA (1,1,0)(1,1,0)₁₂ with a MAPE of 2,250%, while the best SVR model uses a linear kernel with optimal hyperparameters C=100; ε=0,001; and γ=0,001 resulting in a MAPE of 2,254%. Thus, the SARIMA model has a better level of accuracy in predicting M1 money in Indonesia. The application of this model in predicting is expected to help related parties in evaluating the direction of monetary policy and understanding economic conditions.