This paper deals with identification and predictive control of a nonlinear chaotic discrete plant. The main difficulties for identification and control of this plant arise from the strongly nonlinear center and its chaotic behavior. First, an internal feedback is applied to suppress the chaotic behavior. Then, a neural network based predictive controller using Multi Layer Perceptron (MLP) is designed to govern the dynamics of this plant. The effectiveness of the purposed methodology is shown through simulation results.