Dynamic compliance plays an important role in machining stability and accuracy. Dynamic compliance prediction can provide practical guidance for precision compensation and stability analysis of machine tool. It is well known that uncertainty will cause the lower accuracy and reliability. The traditional Markov chain prediction method cannot consider uncertainty problem. In this paper, a generalized Markov chain model is proposed to improve the accuracy and reliability of prediction. Dynamic compliance in machining process is predicted by the proposed model. The results show that the proposed prediction method has a good prediction performance.