Research on stock price forecasting methods by support vector machines based on genetic algorithms

In this paper, an algorithm of support vector machines (SVMs) based on Genetic Algorithm (GA) is presented and used in stock price forecasting. The training of the standard support vector machine is a kind of linear constraint optimization problem, which can be solved by quadratic programming. After introducing a set of Lagrange multipliers the objective function of the constraint optimization problem is defined as the fitness function and genetic algorithm is used to minimize the fitness function. Finally, the algorithm is used to forecast stock price time series and experimental results show that the proposed approach achieves greater forecasting accuracy than standard support vector machine and BP neural network.