Analysis of slope stability based on BP neural network, the analytical model of slope stability is built. Aiming at the defects that BP neural network is likely to fall into local optimum in the progress of parameter optimization; DE is associated to put forward the DE-BP neural network prediction model that is coded by real numbers. The results show that this model has a high precision for the analysis of slope stability. It is feasible and efficient to analyze slope stability based on BP neural network.