Predicting prices of the US and G7 stock indices in uncertain times: Evidence from the application of a hybrid neural network

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25410%2F25%3A39923421" target="_blank" >RIV/00216275:25410/25:39923421 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S2214804325000333" target="_blank" >https://www.sciencedirect.com/science/article/pii/S2214804325000333</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.socec.2025.102366" target="_blank" >10.1016/j.socec.2025.102366</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Predicting prices of the US and G7 stock indices in uncertain times: Evidence from the application of a hybrid neural network

Popis výsledku v původním jazyce

This study investigates the application of Artificial Neural Networks (ANNs) to forecast the one-day-ahead closing price of the US and G7 indices, and makes an extended analysis of three distinct periods, namely, the pre-2008 financial crisis (2003-2007), post-crisis recovery (2009-2016), and recent economic uncertainty (2017-2022). Unlike the traditional predictive approaches, our model distinguishes itself by utilizing a hybrid ANN-based architecture that integrates variable selection and forecasting stages. The proposed model consists of two main parts: selecting relevant input variables and developing a forecasting model. In the first part, an ANNbased variable selection model is utilized to identify significant input variables based on historical market conditions that reflect economic and psychological influences over the study period. These inputs are then refined by eliminating variables with low contributions, resulting in improved model performance. In the second part, we evaluate the impact of different training algorithms, hidden layer sizes, and training data distributions on the ANN&apos;s forecasting accuracy. The findings demonstrate that ANNs can effectively forecast the S&amp;P 500 index&apos;s and G7 indices&apos; prices with high accuracy, particularly when employing the Levenberg-Marquardt algorithm with a simplified model architecture. Moreover, the expanded dataset covering three distinct periods has enabled us to test the model&apos;s stability and generalization across diverse market volatility and structural conditions. The study highlights the critical role of data volume in enhancing the model&apos;s performance, confirming that extensive training data is essential for capturing the complex dynamics of market behavior.

Název v anglickém jazyce

Predicting prices of the US and G7 stock indices in uncertain times: Evidence from the application of a hybrid neural network

Popis výsledku anglicky

This study investigates the application of Artificial Neural Networks (ANNs) to forecast the one-day-ahead closing price of the US and G7 indices, and makes an extended analysis of three distinct periods, namely, the pre-2008 financial crisis (2003-2007), post-crisis recovery (2009-2016), and recent economic uncertainty (2017-2022). Unlike the traditional predictive approaches, our model distinguishes itself by utilizing a hybrid ANN-based architecture that integrates variable selection and forecasting stages. The proposed model consists of two main parts: selecting relevant input variables and developing a forecasting model. In the first part, an ANNbased variable selection model is utilized to identify significant input variables based on historical market conditions that reflect economic and psychological influences over the study period. These inputs are then refined by eliminating variables with low contributions, resulting in improved model performance. In the second part, we evaluate the impact of different training algorithms, hidden layer sizes, and training data distributions on the ANN&apos;s forecasting accuracy. The findings demonstrate that ANNs can effectively forecast the S&amp;P 500 index&apos;s and G7 indices&apos; prices with high accuracy, particularly when employing the Levenberg-Marquardt algorithm with a simplified model architecture. Moreover, the expanded dataset covering three distinct periods has enabled us to test the model&apos;s stability and generalization across diverse market volatility and structural conditions. The study highlights the critical role of data volume in enhancing the model&apos;s performance, confirming that extensive training data is essential for capturing the complex dynamics of market behavior.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

50206 - Finance

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Journal of behavioral and experimental economics

ISSN

2214-8043

e-ISSN

2214-8051

Svazek periodika

116

Číslo periodika v rámci svazku

June

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

14

Strana od-do

102366

Kód UT WoS článku

001461561000001

EID výsledku v databázi Scopus

2-s2.0-105001272811