<p>Water deficiency is a growing threat in most parts of the world, so storage of the surface runoff water by constructing dams across the rivers is an efficient solution for this problem. Consequently, dam site suitability (DSS) studies have become essential for water resource management. This DSS study evaluates eight key factors such as Geology, Drainage Density, Rainfall, Soil, Lineament density, Slope, Distance from Roads and LULC (Land Use &amp; Land Cover) for Palar basin, located in southern part of India. Decision making techniques like AHP (Analytical Hierarchal Process), Fuzzy membership with overlay and Machine learning (ML) models were employed in this study. The weights of the factors influencing Dam Site Suitability (DSS) were determined using Saaty relative scaling as part of the Analytic Hierarchy Process (AHP), with Geology receiving the highest weightage due to its significant influence on the structural integrity and long-term stability of dam foundations. Groundwater Potential served as the dependent variable, while the eight thematic layers were used as predictors. Several algorithms such as Support Vector Machine (SVM), Boosted trees, Bagged trees, K-Nearest Neighbours (KNN) and Neural Network were applied to train and test the models using the eight thematic factors as independent variables with Groundwater Potential (GWP) as dependent variable. Among them, Bagged trees (BT) achieved the highest accuracy of 83.1%. Dam site suitability maps were generated using all three methods, with Machine Learning model demonstrating superior predictive capability, especially along the main course of the river.</p>