Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Neural network models for conditional distribution under bayesian analysis.

Tatiana Miazhynskaia1, Sylvia Frühwirth-Schnatter, Georg Dorffner

  • 1Institute of Management Science, Vienna University of Technology, Vienna, Austria. tmiazhyn@pop.tuwien.ac.at

Neural Computation
|November 30, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Two years of COVID-19: persistently reduced well-being and increases in global psychopathology during the pandemic in a representative Austrian population-sample within the COH-FIT study.

Frontiers in psychiatry·2026
Same author

Negative symptoms in schizophrenia: Methodological challenges and emerging solutions for outcome measurement.

Neuroscience applied·2026
Same author

Expert Opinions on Postoperative Complications in Breast Cancer Surgery After Neoadjuvant Chemotherapy: A Descriptive Study Through Structured Interviews With Surgeons in Austria.

The breast journal·2026
Same author

Validation of a Machine Learning-Derived Algorithm for the Measurement of Facial First Impressions.

Aesthetic plastic surgery·2026
Same author

Machine learning-based tool to assess risk of hemodynamically significant PDA in extremely premature infants.

Pediatric research·2025
Same author

Methodological challenges in outcomes research for early-trials for implementation of new therapies in neuropediatric rare diseases.

Orphanet journal of rare diseases·2025
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

Neural networks effectively predict financial return series volatility, outperforming traditional GARCH models. A Bayesian approach with model evidence was key to selecting an optimal neural network for market data analysis.

Area of Science:

  • Quantitative Finance
  • Machine Learning
  • Econometrics

Background:

  • Accurate prediction of financial return series volatility is crucial for risk management.
  • Traditional models like GARCH(1,1) have limitations in capturing complex nonlinear dynamics.
  • Neural networks offer a flexible alternative for modeling nonlinear autoregressive processes.

Purpose of the Study:

  • To compare the predictive performance of neural network (NN) models against the GARCH(1,1) model for the second moment of conditional density in return series.
  • To develop and apply a Bayesian methodology for estimating NN models, incorporating model evidence for complexity and hidden unit identification.
  • To empirically validate the proposed strategy using real market data.

Main Methods:

  • Nonlinear autoregression using neural networks.

Related Experiment Videos

  • Bayesian estimation framework employing Markov chain Monte Carlo (MCMC) simulations.
  • Model evidence-based selection for NN architecture (hidden units and complexity).
  • Comparison with the Generalized Autoregressive Conditional Heteroskedasticity (GARCH(1,1)) model.

    • Main Results:

    • Neural network models demonstrated strong performance in predicting the second moment of conditional density.
    • The proposed Bayesian methodology successfully identified optimal NN configurations.
    • Empirical application to market data showed significant support for a nonlinear multilayer perceptron model with two hidden units.
    • The NN approach outperformed the GARCH(1,1) model in this context.

    Conclusions:

    • Neural networks, particularly nonlinear multilayer perceptrons, provide a powerful tool for modeling and predicting financial return series volatility.
    • The integrated Bayesian framework offers a robust method for estimating and selecting complex NN models.
    • The findings suggest that advanced machine learning techniques can enhance traditional econometric approaches in financial forecasting.