Title :
A model auto-selection financial data simulation software using neuron-adaptive feedforward neural networks
Author :
Xu, Shuxiang ; Zhang, Ming
Author_Institution :
Dept. of Comput. & Inf. Syst., Western Sydney Univ., Campbelltown, NSW, Australia
Abstract :
In this paper, a model auto-selection (MAS) neural network financial data simulation software, MASFinance, has been developed for use on UNIX. The core of the software is a neuron-adaptive feedforward neural network (NANN) and a learning algorithm that combines steepest descent rule with a pruning method, and the software serves as a tool for selecting a near optimal neural network simulation model for economic data. Our test outcomes show that, for a given set of real life financial data, MASFinance can automatically choose a near optimal simulation model (a NANN with a near optimal neuron activation function and near optimal numbers of hidden layers and units) and then simulates the data with a root-mean-squared error of less than 5%
Keywords :
feedforward neural nets; financial data processing; learning (artificial intelligence); simulation; MASFinance; feedforward neural network; financial data simulation software; learning algorithm; model auto-selection neural network; neuron activation function; pruning method; steepest descent rule; Artificial neural networks; Automatic testing; Computational modeling; Computer networks; Feedforward neural networks; Information systems; Neural networks; Neurons; Software algorithms; Software tools;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.830766
