Introduces an ensemble-averaging model based on a GRNN (generalized regression neural network) for financial forecasting. The model trains all input individually using GRNNs and uses a simple ensemble-averaging committee machine to improve the accuracy performance. In a financial problem, there are many different factors that can effect the asset price movement at different times. An experiment is implemented in two different data sets, S&P 500 index and currency exchange rate. The predictive abilities of the model are evaluated on the basis of root mean squared error, standard deviation and percent direction correctness. The study shows a promising result of the model in both data sets.

Meeting Name

Adaptive Systems for Signal Processing, Communications, and Control Symposium 2000. AS-SPCC. The IEEE 2000


Engineering Management and Systems Engineering

Keywords and Phrases

500 Index; S&P; Accuracy; Asset Price Movement; Currency Exchange Rate; Financial Forecasting Problems; Forecasting Theory; Generalized Regression Neural Network; Neural Nets; Percent Direction Correctness; Predictive Abilities; Root Mean Squared Error; Simple Ensemble-Averaging Model; Standard Deviation; Stock Markets

Document Type

Article - Conference proceedings

Document Version

Final Version

File Type





© 2000 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.