Financial Data Simulation using PL-HONN Model

M. Zhang (USA)

Keywords

Multi-Polynomial, Logarithm, Higher Order NeuralNetwork, Simulator, Simulation.

Abstract

A new model, called Multi-Polynomial with Logarithm function Higher Order Neural Network (PL-HONN), has been developed. Using Sun workstation, C++, and Motif, a PL-HONN Simulator has been built as well. Real world data always can not be simply simulated very well by single polynomial function. So the ordinary higher order neural networks could be failed to simulate such complicated real world data. But PL-HONN model can simulate multi-polynomial functions which include logarithm functions, , it makes PL-HONN model can achieve more accuracy for real world data simulation. The comparison experiments between PL-HONN and ordinary higher order neural network also shows that PL-HONN always can have 2.02-52% more accuracy than ordinary higher order neural networks.

Important Links:



Go Back