A novel Hybrid RBF Neural Networks model as a forecaster

Oguz Akbilgic, Hamparsum Bozdogan, M. Erdal Balaban

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

We introduce a novel predictive statistical modeling technique called Hybrid Radial Basis Function Neural Networks (HRBF-NN) as a forecaster. HRBF-NN is a flexible forecasting technique that integrates regression trees, ridge regression, with radial basis function (RBF) neural networks (NN). We develop a new computational procedure using model selection based on information-theoretic principles as the fitness function using the genetic algorithm (GA) to carry out subset selection of best predictors. Due to the dynamic and chaotic nature of the underlying stock market process, as is well known, the task of generating economically useful stock market forecasts is difficult, if not impossible. HRBF-NN is well suited for modeling complex non-linear relationships and dependencies between the stock indices. We propose HRBF-NN as our forecaster and a predictive modeling tool to study the daily movements of stock indices. We show numerical examples to determine a predictive relationship between the Istanbul Stock Exchange National 100 Index (ISE100) and seven other international stock market indices. We select the best subset of predictors by minimizing the information complexity (ICOMP) criterion as the fitness function within the GA. Using the best subset of variables we construct out-of-sample forecasts for the ISE100 index to determine the daily directional movements. Our results obtained demonstrate the utility and the flexibility of HRBF-NN as a clever predictive modeling tool for highly dependent and nonlinear data.

Original languageEnglish (US)
Pages (from-to)365-375
Number of pages11
JournalStatistics and Computing
Volume24
Issue number3
DOIs
StatePublished - Jan 1 2014
Externally publishedYes

Fingerprint

Radial Basis Function Neural Network
Neural Network Model
Neural networks
Predictive Modeling
Stock Market
Stock Index
Fitness Function
Forecast
Predictors
Set theory
Genetic Algorithm
Regression Tree
Subset Selection
Ridge Regression
Subset
Genetic algorithms
Statistical Modeling
Model Selection
Network model
Radial basis function

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Statistics and Probability
  • Statistics, Probability and Uncertainty
  • Computational Theory and Mathematics

Cite this

A novel Hybrid RBF Neural Networks model as a forecaster. / Akbilgic, Oguz; Bozdogan, Hamparsum; Balaban, M. Erdal.

In: Statistics and Computing, Vol. 24, No. 3, 01.01.2014, p. 365-375.

Research output: Contribution to journalArticle

Akbilgic, Oguz ; Bozdogan, Hamparsum ; Balaban, M. Erdal. / A novel Hybrid RBF Neural Networks model as a forecaster. In: Statistics and Computing. 2014 ; Vol. 24, No. 3. pp. 365-375.
@article{44b2c6eb7e0d40b994675853800975c3,
title = "A novel Hybrid RBF Neural Networks model as a forecaster",
abstract = "We introduce a novel predictive statistical modeling technique called Hybrid Radial Basis Function Neural Networks (HRBF-NN) as a forecaster. HRBF-NN is a flexible forecasting technique that integrates regression trees, ridge regression, with radial basis function (RBF) neural networks (NN). We develop a new computational procedure using model selection based on information-theoretic principles as the fitness function using the genetic algorithm (GA) to carry out subset selection of best predictors. Due to the dynamic and chaotic nature of the underlying stock market process, as is well known, the task of generating economically useful stock market forecasts is difficult, if not impossible. HRBF-NN is well suited for modeling complex non-linear relationships and dependencies between the stock indices. We propose HRBF-NN as our forecaster and a predictive modeling tool to study the daily movements of stock indices. We show numerical examples to determine a predictive relationship between the Istanbul Stock Exchange National 100 Index (ISE100) and seven other international stock market indices. We select the best subset of predictors by minimizing the information complexity (ICOMP) criterion as the fitness function within the GA. Using the best subset of variables we construct out-of-sample forecasts for the ISE100 index to determine the daily directional movements. Our results obtained demonstrate the utility and the flexibility of HRBF-NN as a clever predictive modeling tool for highly dependent and nonlinear data.",
author = "Oguz Akbilgic and Hamparsum Bozdogan and Balaban, {M. Erdal}",
year = "2014",
month = "1",
day = "1",
doi = "10.1007/s11222-013-9375-7",
language = "English (US)",
volume = "24",
pages = "365--375",
journal = "Statistics and Computing",
issn = "0960-3174",
publisher = "Springer Netherlands",
number = "3",

}

TY - JOUR

T1 - A novel Hybrid RBF Neural Networks model as a forecaster

AU - Akbilgic, Oguz

AU - Bozdogan, Hamparsum

AU - Balaban, M. Erdal

PY - 2014/1/1

Y1 - 2014/1/1

N2 - We introduce a novel predictive statistical modeling technique called Hybrid Radial Basis Function Neural Networks (HRBF-NN) as a forecaster. HRBF-NN is a flexible forecasting technique that integrates regression trees, ridge regression, with radial basis function (RBF) neural networks (NN). We develop a new computational procedure using model selection based on information-theoretic principles as the fitness function using the genetic algorithm (GA) to carry out subset selection of best predictors. Due to the dynamic and chaotic nature of the underlying stock market process, as is well known, the task of generating economically useful stock market forecasts is difficult, if not impossible. HRBF-NN is well suited for modeling complex non-linear relationships and dependencies between the stock indices. We propose HRBF-NN as our forecaster and a predictive modeling tool to study the daily movements of stock indices. We show numerical examples to determine a predictive relationship between the Istanbul Stock Exchange National 100 Index (ISE100) and seven other international stock market indices. We select the best subset of predictors by minimizing the information complexity (ICOMP) criterion as the fitness function within the GA. Using the best subset of variables we construct out-of-sample forecasts for the ISE100 index to determine the daily directional movements. Our results obtained demonstrate the utility and the flexibility of HRBF-NN as a clever predictive modeling tool for highly dependent and nonlinear data.

AB - We introduce a novel predictive statistical modeling technique called Hybrid Radial Basis Function Neural Networks (HRBF-NN) as a forecaster. HRBF-NN is a flexible forecasting technique that integrates regression trees, ridge regression, with radial basis function (RBF) neural networks (NN). We develop a new computational procedure using model selection based on information-theoretic principles as the fitness function using the genetic algorithm (GA) to carry out subset selection of best predictors. Due to the dynamic and chaotic nature of the underlying stock market process, as is well known, the task of generating economically useful stock market forecasts is difficult, if not impossible. HRBF-NN is well suited for modeling complex non-linear relationships and dependencies between the stock indices. We propose HRBF-NN as our forecaster and a predictive modeling tool to study the daily movements of stock indices. We show numerical examples to determine a predictive relationship between the Istanbul Stock Exchange National 100 Index (ISE100) and seven other international stock market indices. We select the best subset of predictors by minimizing the information complexity (ICOMP) criterion as the fitness function within the GA. Using the best subset of variables we construct out-of-sample forecasts for the ISE100 index to determine the daily directional movements. Our results obtained demonstrate the utility and the flexibility of HRBF-NN as a clever predictive modeling tool for highly dependent and nonlinear data.

UR - http://www.scopus.com/inward/record.url?scp=84898549669&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898549669&partnerID=8YFLogxK

U2 - 10.1007/s11222-013-9375-7

DO - 10.1007/s11222-013-9375-7

M3 - Article

VL - 24

SP - 365

EP - 375

JO - Statistics and Computing

JF - Statistics and Computing

SN - 0960-3174

IS - 3

ER -