This paper introduces an innovative, AI-driven methodology for predicting ship resistance using only three fundamental input parameters: Length Between Waterlines (LWL), Beam at Waterline (BWL), and Draft (T). Traditional resistance prediction techniques such as empirical methods, towing tank experiments, and computational fluid dynamics (CFD) simulations are highly accurate but involve significant time, cost, and complexity. Our approach leverages machine learning algorithms, including XGBoost, CatBoost, and Gradient Boosting, to derive a comprehensive suite of hydrodynamic characteristics from a robust dataset comprising 308 full-scale experiments across 22 different hull shapes. The methodology begins with meticulous data preprocessing and feature engineering, including normalization, outlier analysis, and correlation assessment, to ensure reliability and minimize error propagation. By transforming raw hydrodynamic data into dimensionless groups, our models effectively capture both linear and non-linear relationships among critical parameters such as displacement, wetted surface area, midship section area, waterplane area, and the longitudinal center of buoyancy (LCB). Simple linear regression techniques were successfully used to derive parameters with perfect correlations, while more complex non-linear interactions were accurately predicted using advanced ensemble methods. The integration of these AI models into a Django-based web application further enhances the utility of our approach, providing naval architects and marine engineers with a user-friendly, real-time tool for design optimization and performance evaluation. Comparative analysis indicates that our streamlined model delivers predictions of residual and frictional resistance with accuracy comparable to traditional methods, while offering significant improvements in computational efficiency and cost-effectiveness. Overall, this research bridges the gap between classical hydrodynamic theory and modern artificial intelligence techniques, offering a rapid, reliable, and scalable solution for ship resistance prediction that has the potential to significantly enhance early-stage design processes in naval architecture.