Empirical validation of ELM trained neural networks for financial modelling

Allbwn ymchwil: Cyfraniad at gyfnodolynErthygladolygiad gan gymheiriaid

StandardStandard

Empirical validation of ELM trained neural networks for financial modelling. / Novykov, Volodymyr; Bilson, Christoper; Gepp, Adrian et al.
Yn: Neural Computing and Applications, Cyfrol 35, Rhif 2, 01.2023, t. 1581-1605.

Allbwn ymchwil: Cyfraniad at gyfnodolynErthygladolygiad gan gymheiriaid

HarvardHarvard

Novykov, V, Bilson, C, Gepp, A, Harris, G & Vanstone, B 2023, 'Empirical validation of ELM trained neural networks for financial modelling', Neural Computing and Applications, cyfrol. 35, rhif 2, tt. 1581-1605. https://doi.org/10.1007/s00521-022-07792-3

APA

Novykov, V., Bilson, C., Gepp, A., Harris, G., & Vanstone, B. (2023). Empirical validation of ELM trained neural networks for financial modelling. Neural Computing and Applications, 35(2), 1581-1605. https://doi.org/10.1007/s00521-022-07792-3

CBE

MLA

Novykov, Volodymyr et al. "Empirical validation of ELM trained neural networks for financial modelling". Neural Computing and Applications. 2023, 35(2). 1581-1605. https://doi.org/10.1007/s00521-022-07792-3

VancouverVancouver

Novykov V, Bilson C, Gepp A, Harris G, Vanstone B. Empirical validation of ELM trained neural networks for financial modelling. Neural Computing and Applications. 2023 Ion;35(2):1581-1605. Epub 2022 Hyd 1. doi: 10.1007/s00521-022-07792-3

Author

Novykov, Volodymyr ; Bilson, Christoper ; Gepp, Adrian et al. / Empirical validation of ELM trained neural networks for financial modelling. Yn: Neural Computing and Applications. 2023 ; Cyfrol 35, Rhif 2. tt. 1581-1605.

RIS

TY - JOUR

T1 - Empirical validation of ELM trained neural networks for financial modelling

AU - Novykov, Volodymyr

AU - Bilson, Christoper

AU - Gepp, Adrian

AU - Harris, Geoff

AU - Vanstone, Bruce

N1 - Open Access funding enabled and organized by CAUL and its Member Institutions.

PY - 2023/1

Y1 - 2023/1

N2 - The purpose of this work is to compare predictive performance of neural networks trained using the relatively novel technique of training single hidden layer feedforward neural networks (SFNN), called Extreme Learning Machine (ELM), with commonly used backpropagation-trained recurrent neural networks (RNN) as applied to the task of financial market prediction. Evaluated on a set of large capitalisation stocks on the Australian market, specifically the components of the ASX20, ELM-trained SFNNs showed superior performance over RNNs for individual stock price prediction. While this conclusion of efficacy holds generally, long short-term memory (LSTM) RNNs were found to outperform for a small subset of stocks. Subsequent analysis identified several areas of performance deviations which we highlight as potentially fruitful areas for further research and performance improvement.

AB - The purpose of this work is to compare predictive performance of neural networks trained using the relatively novel technique of training single hidden layer feedforward neural networks (SFNN), called Extreme Learning Machine (ELM), with commonly used backpropagation-trained recurrent neural networks (RNN) as applied to the task of financial market prediction. Evaluated on a set of large capitalisation stocks on the Australian market, specifically the components of the ASX20, ELM-trained SFNNs showed superior performance over RNNs for individual stock price prediction. While this conclusion of efficacy holds generally, long short-term memory (LSTM) RNNs were found to outperform for a small subset of stocks. Subsequent analysis identified several areas of performance deviations which we highlight as potentially fruitful areas for further research and performance improvement.

KW - Extreme Learning Machine

KW - Stock Price prediction

KW - Long short-term memory

KW - Recurrent Neural Network

U2 - 10.1007/s00521-022-07792-3

DO - 10.1007/s00521-022-07792-3

M3 - Article

VL - 35

SP - 1581

EP - 1605

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 1433-3058

IS - 2

ER -