Machining Ti-6Al-4 V alloy poses significant challenges due to its unique properties, particularly under dry turning conditions where lubrication is absent. This study adopts a data-driven methodology to optimize the dry turning process, focusing on the critical balance between surface roughness (Ra) and material removal rate (MRR). A comprehensive experimental design evaluates the effects of cutting speed (Vc), feed rate (fz), and depth of cut (ap) on Ra and MRR. Machine learning (ML) models are developed to predict these outcomes, and multiobjective optimization (MOO) is carried out using the NSGA-II algorithm. The resulting Pareto-optimal solutions are ranked via the PROMETHEE II method, employing the GINI and ANGLE weight methods to select the optimal cutting parameters. The results indicate that a combination of Vc at 94.113 rpm, fz at 0.087 mm/min, and ap at 1.405 mm optimally balances surface quality and material removal efficiency. This methodology provides a robust framework for enhancing the machinability of Ti-6Al-4 V under dry conditions.