Abstract: In order to realize the on-line rapid assessment and credibility evaluation of power system transient stability, a transient stability assessment method combining joint mutual information maximization（JMIM） and natural gradient boosting（NGBoost） is proposed. Based on JMIM, joint mutual information and"maximum of the minimum" principle are adopted to mine data correlation, so as to screen out the key characteristics of the power grid and avoid dimension explosion. To realize the transient stability assessment with high-confidence, a transient stability assessment model driven by NGBoost is constructed, which can predict parameters of the conditional probability distribution of the model in the form of a function to achieve probability prediction,thereby quantifying the credibility. Combined with the adaptive credibility threshold correction method, the time sequence assessment of system transient stability in disturbed states is realized. The case experiments are conducted on the data of New England 10-generator 39-bus system and a provincial power grid in China. Compared with other machine learning methods, the proposed method has better robustness under noise interference and can identify the unstable states more accurately.