The PSR-Transformer Nexus: A Deep Dive into Stock Time Series Forecasting

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F23%3A10256317" target="_blank" >RIV/61989100:27240/23:10256317 - isvavai.cz</a>

Výsledek na webu

<a href="https://thesai.org/Publications/ViewPaper?Volume=14&Issue=12&Code=IJACSA&SerialNo=92" target="_blank" >https://thesai.org/Publications/ViewPaper?Volume=14&Issue=12&Code=IJACSA&SerialNo=92</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.14569/IJACSA.2023.0141292" target="_blank" >10.14569/IJACSA.2023.0141292</a>

Jazyk výsledku

angličtina

Název v původním jazyce

The PSR-Transformer Nexus: A Deep Dive into Stock Time Series Forecasting

Popis výsledku v původním jazyce

Accurate stock market forecasting has remained an elusive endeavor due to the inherent complexity of financial systems dynamics. While deep neural networks have shown initial promise, robustness concerns around long-term dependencies persist. This research pioneers a synergistic fusion of nonlinear time series analysis and algorithmic advances in representation learning to enhance predictive modeling. Phase space reconstruction provides a principled way to reconstruct multidimensional phase spaces from single variable measurements, elucidating dynamical evolution. Transformer networks with self -attention have recently propelled state-of-the-art results in sequence modeling tasks. This paper introduces PSR-Transformer Networks specifically tailored for stock forecasting by feeding PSR interpreted constructs to transformer encoders. Extensive empirical evaluation on 20 years of historical equities data demonstrates significant accuracy improvements along with enhanced robustness against LSTM, CNNLSTM and Transformer models. The proposed interdisciplinary fusion establishes new performance benchmarks on modeling financial time series, validating synergies between domain -specific reconstruction and cutting -edge deep learning.

Název v anglickém jazyce

The PSR-Transformer Nexus: A Deep Dive into Stock Time Series Forecasting

Popis výsledku anglicky

Accurate stock market forecasting has remained an elusive endeavor due to the inherent complexity of financial systems dynamics. While deep neural networks have shown initial promise, robustness concerns around long-term dependencies persist. This research pioneers a synergistic fusion of nonlinear time series analysis and algorithmic advances in representation learning to enhance predictive modeling. Phase space reconstruction provides a principled way to reconstruct multidimensional phase spaces from single variable measurements, elucidating dynamical evolution. Transformer networks with self -attention have recently propelled state-of-the-art results in sequence modeling tasks. This paper introduces PSR-Transformer Networks specifically tailored for stock forecasting by feeding PSR interpreted constructs to transformer encoders. Extensive empirical evaluation on 20 years of historical equities data demonstrates significant accuracy improvements along with enhanced robustness against LSTM, CNNLSTM and Transformer models. The proposed interdisciplinary fusion establishes new performance benchmarks on modeling financial time series, validating synergies between domain -specific reconstruction and cutting -edge deep learning.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název periodika

International journal of advanced computer science and applications

ISSN

2158-107X

e-ISSN

2156-5570

Svazek periodika

14

Číslo periodika v rámci svazku

12

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

8

Strana od-do

917-924

Kód UT WoS článku

001244472600021

EID výsledku v databázi Scopus

—