In this study, a four-factor five-level Central Composite Design (CCD) was applied to develop mathematical model and optimize process parameters for malachite green dye (MG) removal from aqueous solutions using sepiolite. The individual, combined, and quadratic effects of four experimental factors (initial pH of solution, contact time, initial dye concentration, and sepiolite dosage) on dye adsorption were studied. Based on the analysis of variance (ANOVA) results, the order of factors from high to low contribution on removal efficiency was found as initial dye concentration, sepiolite dosage, initial dye concentration*initial dye concentration, sepiolite dosage*sepiolite dosage, and contact time with respect to sum of squares. Optimization results showed that the optimal settings for significant experimental factors were initial dye concentration= 77 mg l-1, sepiolite dosage= 26 g l-1, and contact time= 42 min. At this setting, predicted maximum removal efficiency was over 99%.