Abstract: Based on the displacement sequence of slope, the stability of slope could be judged effectively by forecasting the displacement of slope in the future. After analyzing the advantages and disadvantages of grey forecasting methods and projection pursuit regression (PPR) method respectively; a new nonlinear forecasting model of grey projection pursuit regression (GPPR) is proposed. The new model not only developing the advantages of accumulation generation of the grey forecasting method, weakening the effect of stochastic-disturbing factors in original sequence and strengthening the regularity of data, but also using the quickly solving speed and the excellent characteristics of projection pursuit regression method for nonlinear relationship and avoiding the theoretical defects existing in the grey forecasting model. At the same time, the model is verified. At last, two engineering examples are given to testify the effectiveness of the grey projection pursuit regression forecasting method to predict displacements of two slopes. The results show that the new model has higher calculation precision, so as to provide a new way to predict displacements of slopes

Key words: slope displacement, grey theory, projection pursuit regression, time sequence, nonlinearity