Probabilistic neural network model based on wavelet and partical swarm optimization

Foreign exchange market is a complex market, with a high degree of volatility characteristics. Exchange rate formation mechanism and the factors affecting exchange rate volatility are also very complex, which is a nonlinear system. It is difficult to accurately forecast. Probabilistic neural network is applied to the frontiers of forecast, and aimed at the characteristics of probabilistic neural network to pretreat the exchange of data and forecast the tendency. And by changing the vector dimensionality experiment we obtain the best entry to embed dimensionality, tested and improved the precise prediction and valuable.