A novel method for predicting the rotor angle stability condition of a large power system immediately after a large disturbance is presented. The proposed two stage method involves a) estimation of the proximity of post-fault bus voltage trajectories after the disturbance to some pre-identified templates and b) prediction of the stability status using a classifier, which uses the proximity values calculated at different buses as inputs. The typical bus voltage variation patterns after a disturbance for both stable and unstable situations are identified from a database of simulations using the fuzzy c-means clustering algorithm. The same database is used to train the support vector machine classifier used in the second stage of the prediction process. Development of the transient stability prediction scheme and its performance were demonstrated using a case study carried out on the IEEE-39 bus system.