According to the low speed of constringency and high complexity of training methods in SVM large scales training

quantum-behaved particle swarm algorithm (QPSO) is presented to solve the problem. Parameters selection is an important problem in the research area of support vector machines. Meanwhile

quantum-behaved particle swarm algorithm is used to choose the parameters of least square support vector machines

which can avoid the man-made blindness and enhance the efficiency and capability of forecasting. The experimental results indicate that this QPSO-SVM forecasting model can be trained quickly and good generalization

is easy to be realized

can save the calculating cost and improve the constringency speed.