The Forecasts Performance of Gray Theory, BP Network, SVM for Stock Index

In order to evaluate the performance of several forecasts, the paper firstly uses three forecasting methods, namely grey model (GM (1,1)), BP neural networks and support vector machines (SVM), to forecast the Shanghai Industrial Index, the Shanghai Commercial Index, the Shanghai Real Estate Index, the Shanghai Public Utilities Index. Through evaluating the results of these forecasting methods, it is argued that, for forecasting concussing stock market, the forecast effects of BP network method is obviously better than the forecast effects of GM (1, 1) method and SVM method; GM (1, 1) method and SVM method are more suitable for forecasting stable stock market.