In this study, combined Discrete Wavelet Transform-Fuzzy (DWT-Fuzzy) and combined Continuous Wavelet Transform-Fuzzy (CWT-Fuzzy) models are developed for predicting the daily water levels at northern and southern boundary of Bosphorus Strait. The observed daily water level data is decomposed into spectral bands (sub-series) by using wavelet transformation as a pre-processing tool in order to achieve more accurate daily water level predictions with extended lead-times up to 7 days. The time series of daily water level data is decomposed into spectral bands, which are used as inputs into the Fuzzy model and the daily water levels are predicted from the sum of the predicted components (spectral bands). A predictive model is developed using combined DWT-Fuzzy and combined CWT-Fuzzy models to predict water level fluctuations. It is found that CWT-Fuzzy model performed better than DWT-Fuzzy and stand-alone Fuzzy models for prediction lead-times up to 7 days at northern and southern boundary of Bosphorus based on RMSE and CE evaluation criteria. It is concluded that CWT is a better pre-processing technique as it yields more accurate daily water level predictions with improved prediction lead-times than DWT.