In this study, a multiple response optimization model based on response surface methodology was developed to determine the best rotor speed and yarn twist level for optimum rotor yarn strength and unevenness, and minimum yarn hairiness and imperfections. Cotton yarn of 30 tex, was produced on rotor spinning machine with different twist levels (i.e. 500, 550, 600 and 700 tpm) at different rotor speeds (i.e. 70000, 80000, 90000 and 100000 rpm). Yarn quality characteristics were determined for all the experiments. Based on the results, multiple response optimization model was developed using response surface regression on $MINITAB^{(R)}$ 16 statistical tool. Optimization results indicate that with the quality of raw material selected for this study, top 50 % quality level, according to $USTER^{(R)}$ yarn quality benchmarks, can be achieved with 100 % desirability satisfaction for all the selected yarn quality parameters at rotor speed of 77,800 rpm and yarn twist of 700 twists per meter.