Abstract: Rainfall variability poses significant challenges to agricultural planning and water-resource management in the Naivasha region of Kenya. This study models and forecasts monthly rainfall using the Autoregressive Integrated Moving Average and Seasonal Autoregressive Integrated Moving Average approaches. Monthly data from 1990–2024 were analyzed, revealing strong seasonal patterns and high variability. Stationarity tests confirmed that the series was stationary in levels, while autocorrelation analysis indicated significant dependence at a 12-month lag. Model comparison showed that the SARIMA(1,0,0)(2,0,0)12 model outperformed ARIMA(1,0,0), with lower AIC and improved forecast accuracy. Forecasts suggest stable mean rainfall with increasing uncertainty over time.