A machine learning based approach to trim-adjustment control of combustion instability using tunable Helmholtz resonator as control element is theoretically implemented. A model of a flame in a long duct with one end closed and other end open is considered. The linear system matrix of governing equations is formulated and solved to determine the stability of the system at a given operating condition. Genetic algorithm is used to find the optimal control value of Helmholtz resonator frequency. The genetic algorithm code starts out with a random set of values (individuals), which are evaluated using a fitness function. The imaginary part of the eigen frequency obtained from the system model is used as the fitness function. The best individuals are selected for breeding the next generation of individuals. This is iteratively done for a number of generations and the best value given by the code at the end of the run is taken as the optimal value. It is seen that the GA code is able to determine the optimal value of resonator frequency in each of the cases tested.