Effective degradation indicator and robust prediction model are very important for residual life prediction. Thus a new residual life prediction based on Markov indicator and support vector is proposed. Since the Markov model is good at dealing with stochastic characteristics in time domain, Markov model is joined with multiple fault features for the construction of an effective degradation indicator of rolling element bearings. The support vector regression is used to construct an adaptive prediction model composed of two prediction models that are, respectively, based on historical data and online data. Thus the ultimate prediction result is obtained by taking a weighted average of the two prediction results captured by the two prediction models, and the weights are adjusted by the LMS to enhance the prediction accuracy. The experimental results show that the Markov indicator is more sensitive than the common features, and the proposed prediction method is more effective in comparison to other methods.