In this paper, the authors present a life prediction method based on Least Squares Support Vector Machine (LSSVM) for small data samples from Weibull distributions. This method can directly predict lifetime by building a least squares support vector regression model. Monte Carlo simulations demonstrated the effectiveness of LSSVM approach in prediction of Weibull data sets. Error Back Propagation (BP) neural network was also compared with it. The simulation results show that LSSVM method has better generalization and higher accuracy of life prediction than BP neural network when dealing with small data samples from Weibull distribution.