Lithium-NMC batteries in electric vehicles exhibit complex degradation mechanisms, where capacity fade, internal re sistance growth, and discharge behavior evolve nonlinearly under varying operating conditions. Accurate remaining useful life prediction necessitates capturing these intricate interdependencies, which traditional models fail to gener alize effectively. This study develops a robust machine learning framework leveraging experimental cycling data under nominal and over-discharge conditions. Key param eters like voltage, discharge time, internal resistance, and state of health were chosen due to their direct correlation with electrochemical aging, resistive losses, and failure pro gression, ensuring high sensitivity to degradation dynam ics. Support Vector Regression and Bayesian-optimized Lasso Regression were employed to model these dependen cies, providing precise predictions of key battery health in dicators. A hybrid framework integrating these models for remaining useful life estimation achieved R 2, MAE, RMSE of 0.9998, 0.093 and 0.138 respectively, significantly out performing conventional approaches. Rigorous evaluation through K-fold cross-validation and subset stability analy sis ensured generalizability across diverse operating condi tions. Benchmark comparisons with state-of-the-art meth ods demonstrated superior predictive accuracy. By address ing critical limitations in traditional degradation modelling, this work provides a scalable, data-driven solution for real time battery health management, enhancing the reliability and sustainability of electric vehicle applications.