The purpose of this paper is to study the effect of seasonal variations using artificial neural network (ANN) and support vector machine (SVM) prediction models. It is important to consider the seasonal effect because the predictors will be able to learn separately, different seasonal process. For example, in Malaysia, the Northeast season brings heavy rains, which eventually contributes to flood occurrences. The performances of predictor models are compared to other methods via the root mean square error (RMSE). The finding of results will help other researchers in climate prediction to consider the seasonal variations in their prediction models.