Stock price fluctuation in stock markets is a very important issue in financial researches. However, the information in stock markets of China is too much to analysis. Fractal theory is an important modern branch of nonlinear science. Neural network has a strong nonlinear approximation ability and self-organizing, adaptive features. Based on fractal theory, the Shanghai integrated index are chosen and M F-DFA is used to study fractal property. Then use neural network to analysis and predict the new data sequence, to obtain satisfactory results.