Isotope techniques are the most commonly used in cases where hydro-chemical analysis is insufficient to identify groundwater's origin and quality and reveal seawater intrusion into groundwater along coastlines. In this study, the potential of the Multilayer Perceptron (MLP), Radial Basis Neural Networks (RBNN), Generalized Regression Neural Networks (GRNN), Adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Machines (SVM), Gaussian Process Regression (GPR), Classification and Regression Tree (CART), and Multiple Linear Regression Analysis (MLR) were compared using known hydro-chemical properties of waters for estimating deuterium (δD) and oxygen-18 (δ18O) isotopes in groundwater of the Bafra plain, Northern Turkey. A total of 61 water samples collected from the plain were chemically analyzed. All data were divided into training (70%) and test (30%) sets. Cluster analysis was performed to reduce the number of input variables, and electrical conductivity (EC), chloride (Cl), magnesium (Mg) and, sulphate (SO4) were introduced into the models as input variables, after examining different combinations of these variables in the studied models. Three statistical indices were used to evaluate models' performances: determination coefficient (R2), root mean square error (RMSE) and mean absolute error (MAE). Moreover, a visualization technique (Taylor diagram) was used to assess the similarities between the measured and estimated δD and δ18O values. The comparison revealed that the performance accuracy of MLP was the best among the applied models in δD and δ18O estimations. Overall, the study suggests using data-driven methods, especially MLP, when lacking of appropriate laboratories for isotope analysis and facing with high cost.