In this study, wavelet transform (WT) and a relevance vector machine (RVM) are integrated to predict monthly runoff. First, the WT method is adopted to decompose the monthly runoff time series into subsequences of different scales, and the variation characteristics, especially the periodicity of the runoff, are analyzed. Then, the regression model of RVM is established in each subsequence. Finally, the prediction results of each subsequence are integrated to obtain the final predicted values of monthly runoff through wavelet inverse transform. The proposed model was tested using the historical data of Minjiang River; the results show that compared with the RVM model, the WT-RVM model has better precision and can be applied in the prediction of monthly runoff.