This study explores the separation and optimization of molybdenum (Mo) from mixed mineral acids derived from semiconductor industry waste streams with tributyl phosphate (TBP) by implementing machine learning (ML) models. Considerable experimental tests were performed to evaluate the impact of various operational variables on the effectiveness of Mo extraction and stripping. The support vector regression (SVR) paired with harmony search algorithm (HSA), genetic algorithm (GA), and shuffled frog leaping algorithm (SFLA) were employed for enhancement in the separation process and structural optimization. The SVR-SFLA model yielded the most meticulous predictions, identifying optimal extraction conditions with a TBP concentration, mixing time, temperature, and O/A ratio of 50%, 30 min, 25 °C, and 1, respectively, achieving 77.8% efficiency. The derived results from the SVR-SFLA model, in tandem with the McCabe-Theil diagram, indicated a four-stage counter-current extraction process required to achieve a yield exceeding 99%. For the stripping process, the hybrid model indicated optimal conditions with 3 M NH4OH and an A/O ratio of 0.5 at 50 °C for 20 min, requiring two counter-current stages for nearly complete stripping. Feature importance analysis using a random forest algorithm (RFA) highlighted the NH4OH concentration and phase ratio as the most significant factors, contributing 40.3% and 29.1%, respectively, to the stripping from the loaded TBP phase. The final product, obtained after crystallization and thermal decomposition of the strip solutions, was characterized by X-ray diffraction (XRD), thermogravimetric analysis (TGA), scanning electron microscopy (SEM), and energy-dispersive X-ray spectroscopy (EDS), revealing 99.74% purity for molybdenum trioxide.