In this paper, a sliding mode predictive control method is proposed for function improvement of affine discrete-time nonlinear systems using integral terminal sliding mode method (ITSMC). The proposed method is based on the integration of terminal integral sliding mode method and model predictive controller which leads to using the advantages of both methods. Indeed, in the proposed method, integral and terminal characteristics of terminal integral sliding mode method are used to design the sliding surface in order to reduce the error (in reaching phase) and to converge to the origin (in sliding phase). Moreover, the chattering phenomenon which usually exists in sliding mode based methods will be decreased using the model predictive controller. The proposed control method has the capability to eliminate the effect of external disturbances and uncertainties. In this paper, it is shown that the model predictive method decreases the chattering phenomenon more than using the saturation function in the control law of the sliding mode method. In addition, using numerical and functional examples, the performance of the proposed method in improving the quality of the system response in the presence of external disturbances and uncertainties is illustrated.