Financial simulation system using a higher order trigonometric polynomial neural network group model

A trigonometric polynomial high order neural network financial simulation (THONN) system is presented. The system was written in C, incorporates a user-friendly graphical user interface (GUI), and runs under X-Windows on a Sun workstation. The experimental results show that the THONN group model is able to handle higher frequency, higher order non-linear and discontinuous data. Using the THONN model, the accuracy is about 5%-10% better than conventional trigonometric polynomial neural network models.