This paper investigates the performance of clamping force at the secondary pulley actuator of Electro-mechanical Dual Acting Pulley Continuously Variable Transmission (EMDAP CVT) using an identification technique for development of intelligent control. The implementation details are described and the experimental studies conducted in this research are analyzed. To investigate the dynamic response of the system, step input was applied to the EMDAP CVT and clamping forced was measured. The modeling of the system was developed using the Genetic Algorithm (GA). The validation and verification of the obtained model were evaluated using mean squared error (MSE) and correlation test. The performance of the nonlinear approach was compared and discussed based on MSE value. The predictive ability of the model was further observed with unseen data. The result shows that, Nonlinear ARX (NARX) model converges to an optimum solution faster with increasing of model order and the obtained dynamic model also described the system well.