Stock is considered as one of the most important financial tools of the financial market. Whether the price of it could be predicted and how to predict it is always a controversial problem in the financial field. There are different kinds of models to predict stock price. But none of them can predict IPO stocks.Support Vector Machine uses the structural risk minimization principle. The risk is only influenced with the number of input samples, and is unrelated to the input dimension. Support Vector Machine avoids "dimension disaster" and overcomes some shortcomings, such as the slow convergence of traditional neural networks, local minimum value and so on. So Support Vector Machine has good generalization ability.We use this system to predict IPO stock price. We also discuss the different kernel functions and the different parameters to impact the results of forecasts. So this paper has important reference value in stock price predicting field. |