Abstract: This study presents a hybrid approach by associating the Genetic Algorithm (GA) and the Sequential Quadratic Programming (SQP) to improve the Stutzer Index optimization. The Stutzer Index is a well-recognized portfolio performance measure that provides unbiased estimates of risk-adjusted performance. However, the tasks in optimizing and determining a good starting point for the constrained optimization of Stutzer Index are challenging, especially with the additional constraint on the negative term θ. By integrating GA and SQP, this study anticipates the hybrid model to improve the efficiency and the performance of the optimization. The optimal indices obtained from both the SQP and the hybrid GA-SQP that used the initial guess recommended by Stutzer and the optimal index acquired via the hybrid GA-SQP with random starting point, for different period of data and number of assets respectively, are utilized for the comparative study. The results revealed that the hybrid model is superior in the Stutzer Index optimization, owing to the consistent capability of GA to locate the global optimum region and SQP to reach the optimal solution. The results also attested that the hybrid model enhanced the efficiency of the optimization as it does not required user-defined starting point and can sufficiently attained the optimal solution by utilizing a randomly generated starting point. In general, the hybrid model is competent in improving the efficiency and the performance of the Stutzer Index optimization, albeit the enhancement is not statistically significant in smaller number of observations.