Stock Index Modeling Using Hierarchical Radial Basis Function Networks

Abstract

Abstract. Forecasting exchange rates is an important financial problem that is receiving increasing attention especially because of its difficulty and practical applications. This paper proposes a Hierarchical Radial Basis Function Network (HiRBF) model for forecasting three major international currency exchange rates. Based on the pre-defined instruction sets, HRBF model can be created and evolved. The HRBF structure is developed using the Extended Compact Genetic Programming (ECGP) and the free parameters embedded in the tree are optimized by the Degraded Ceiling Algorithm (DCA). Empirical results indicate that the proposed method is better than the conventional neural network and RBF networks forecasting models.

Estimating time series future optima using a steepest descent methodology as a backtracker

“…Grosan and Abraham, [1], and Chen et al, [19], incorporated results from genetic algorithms and neural network applications together, in a single multiobjective algorithm to conclude that the obtained results appear more accurate than the single use of one technique.…”

Stock Index Prediction Based on Multi-Level Transfer Function Quantum Neural Tree

“…According to the characteristics of complex system, Flexible Neural Tree (FNT) [4][5][6][7][8] is presented by Chen, as a general sense of Neural network system, USES the Tree structure and a collection of a set of operators. The Flexible Neural Tree has been applied to function approximation, time-series prediction, nonlinear system identification problems, cancel detection, i.e., successfully.…”

Stock Index Modeling Using the System of Differential Equations

“…The local linear wavelet neural network (LLWNN) technique was used to represent the behavior of stock index, and the LLWNN was optimized by using estimation of distribution algorithm (EDA) [1]. The hierarchical radial basis function network (HiRBF) model was proposed for forecasting three international currency exchange rates, which structure and parameters were optimized by genetic programming and degraded ceiling algorithm [2]. Chen [3] investigated how the seemingly chaotic behavior of stock markets could be well represented using Flexible Neural Tree (FNT) ensemble technique.…”