The displacement of rock mass produced by blasting mining in open pit mines will affect the distribution of ore, resulting in ore dilution or loss. In order to accurately grasp the distribution of ore after blasting, the radial basis function neural network (RBFNN) is used to predict the displacement of rock after blasting. Because the displacement of rock after blasting is very scattered, it can not be specific to every part of blasting, so it can be transformed into the mass center of the section polygon for overall consideration. At the same time, in view of insufficient samples, GRA theory is introduced to determine the main factors affecting rock displacement after blasting, and GA algorithm is used to determine the radial basis expansion velocity of RBFNN, so as to establish GRA-BA-RBFNN rock displacement prediction model. Finally, the centroid displacement of blasting pile in Dexing Copper Mine of Jiangxi Province is predicted by using this model. Compared with the predicted results of RBFNN model without extracting the main factors and RBFNN model without BA algorithm optimization, it is found that the accuracy and stability of the model have been greatly improved. This study can provide some reference for the prediction of rock displacement in open-pit mine blasting.