The main objective of this study is to analyze how input parameters such as cutting speed ( Vc), depth of cut ( ap), feed per revolution ( f), and tool nose radius ( r) influence the performance of dry turning AISI 304 stainless steel. Performance evaluation includes cutting force components ( Fx, Fy, and Fz), surface roughness (SR), material removal rate (MRR), cutting power ( Cp), and cutting temperature ( T). Experiments are planned using the Taguchi L18 experimental design, and a coated carbide tool (GC 2025) is employed. ANOVA revealed that the most influential factors on SR are f and r, contributing 52.40% and 26.54%, respectively. Axial and tangential cutting force components are influenced by ap and f, with contributions of 72.99% and 5.93% for Fx and 81.57% and 13.38% for Fz, respectively. The radial component is influenced by ap (85.74%). Vc, f, and ap all contribute to cutting power, with contributions of 55.13%, 24.35%, and 10.74%, respectively. Finally, ap and the interaction f*ap contribute 45.18% and 8.81%, respectively, to the temperature in the cutting zone. This article introduces a novel multi-objective optimization method based on weighted principal component analysis. This method distinguishes itself by its ability to address challenges related to data matrix normalization, the ambiguity of eigenvector signs, and the issue of negative signs in Taguchi’s philosophy. The results of the new method, the desirability function, and the classical WPCA method are compared. The results show that the new method suggests a compromise solution that is similar to the desirability function and better than the classical WPCA’s suggestion.