Taking the non-equilibrium distribution characteristics of the coal mine water burst sample set into account, this study presents a coal mine water inrush prediction model based on the integrated learning classification. It focuses on the construction method of base classifier, the performance index and the weight analysis of base classifier, and the integrated learning algorithm based on improved Boosting. The experimental results show that although the algorithm does not achieve the minimum error rate of non-waterlogging samples, a 100% discrimination rate for water burst samples is realized, and the calculation load is small and it is easy to realize.