<p>Accurately and reliably predicting the stability of high-risk or potentially unstable slopes during sudden rainfall events is crucial for ensuring safe and efficient operations. Accordingly, three novel combined prediction models for rainfall-induced slope instability are proposed, which are developed by integrating a regression model and a stacking model using multiple fusion strategies. First, a sensitivity analysis was conducted to identify the key factors influencing slope stability under rainfall conditions. An extensive database was constructed using extended Latin hypercube sampling in combination with numerical simulations performed in Geo-Studio. Based on this database, machine learning methods are employed to capture the nonlinear relationships between slope stability and key factors such as geometry, strength parameters, and rainfall conditions, thereby enabling intelligent prediction of rainfall-induced slope instability. Subsequently, the prediction results of various machine learning methods are compared with the calculated values to assess the prediction performance of each model. The results show that the three combined models exhibit good fitting performance, with RMSE values of 0.14, 0.11, and 0.12, respectively, which are significantly lower than those of the other models. Finally, an intelligent slope stability prediction system was developed by integrating the combined models in MATLAB and applying it to the S106 road slope in Bijie City, Guizhou Province, China. The results demonstrate that the combined models are reliable and effective, providing a reliable tool for the practical prediction of rainfall-induced slope instability.</p>