Prediction method based on PSO-ADGM-SVR combined model

The invention belongs to the technical field of data mining, and relates to a prediction method based on a PSO-ADGM-SVR combined model, and the method comprises the steps: collecting the nearest slope displacement data, and carrying out the preprocessing of the data; the preprocessed data are input into the optimized PSO-ADGM model, and a PSO-ADGM prediction result is obtained; the preprocessed data are input into the optimized PSO-SVR model, and a PSO-SVR prediction result is obtained; calculating a weight vector, and performing weighted combination on the PSO-ADGM prediction result and the PSO-SVR prediction result by using the weight vector to obtain slope displacement predicted by a combined model; the ADGM can explore the trend characteristics of the time series data, the SVR can reflect the randomness characteristics of the time series data, and the ADGM and the SVR have certain complementarity, so that the PSO-ADGM-SVR combined model is obtained by coupling the ADGM model and the SVR model, and the pre