The accelerated growth of the automobile industry intensifies sustainability issues, primarily because of its significant carbon emission and the resulting impacts on global environmental systems. These emissions are directly correlated with fuel usage, which is subsequently affected by the material weight utilized in automobile systems. This research utilized machine learning (ML) techniques to optimize the production parameters of natural fiber (NF)-reinforced materials for airplane body applications. A study was conducted using the Taguchi optimization approach to investigate the effect of different fiber lengths, concentrations of sodium hydroxide treatment, Nano SiO2 and hybrid fiber (bamboo fibers, and madar fibers (BMF)) on the performance of the material. In order to find the best combination of the factors that were considered for automobile structural applications with low fuel consumption (low carbon emissions) and high reliability, multi-objective optimization (MOO) methods like additive ratio assessment (ARAS) and genetic algorithms (GA) were utilized within the MATLAB programming environment. With R2 values above 80%, the regression analysis-derived models demonstrated good predictive accuracy. The optimization of ARAS for the developed composite by the GA identified the optimal process parameters for achieving lightweight materials suitable for automobile applications as 35% BMF, 10% Nano SiO2 at a fiber length of 24mm, and a 9 % concentration of sodium hydroxide, with ARAS reaching its maximum level of unity.