Accurate user churn prediction ability facilitates improving user retention rate, increasing user count and increasing profitability. Most of the existing user churn prediction models are single model or simple integration of multiple models, and the advantages of multi-model integration are not fully utilized.This paper draws on the idea of Bootstrap Sampling in random forests, proposes an improved Stacking ensemble method, and applies the method to the real data set to predict the user churn. Through the experimental comparison on the validation set, the proposed method is better than the classical Stacking ensemble method with the same structure in the terms of the F1-score, recall rate and prediction accuracy of user churn. When the appropriate structure is adopted, the performance can surpass the optimal performance on the base classifier.