Beyond Sentiment in Stock Price Prediction: Integrating News Sentiment and Investor Attention with Temporal Fusion Transformer

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25410%2F24%3A39922253" target="_blank" >RIV/00216275:25410/24:39922253 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-031-63219-8_3" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-63219-8_3</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-63219-8_3" target="_blank" >10.1007/978-3-031-63219-8_3</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Beyond Sentiment in Stock Price Prediction: Integrating News Sentiment and Investor Attention with Temporal Fusion Transformer

Popis výsledku v původním jazyce

News sentiment is attracting considerable interest in stock market prediction, given its crucial role in shaping stock prices. Previous research has mainly focused on improving prediction accuracy by exploiting news sentiment, without adequately considering the different levels of attention that individual news articles receive. Furthermore, despite the advanced predictive capabilities of deep learning models, there has been a lack of focus on the interpretability of these models, leading to predictions that are not transparent. This study presents an innovative prediction model that integrates a FinBERT-based analysis of news sentiment and investor attention metrics with an attention-based Temporal Fusion Transformer framework. This approach not only enables highly effective forecasting, but also provides insights into the temporal dynamics that influence the stockmarket. The effectiveness of the model is demonstrated by analyzing stock price data for 41 of the largest market capitalization companies over the period 2010 to 2021. The results confirm the superiority of the proposed model over existing deep learning approaches, and the attention analysis underscores the critical role of synthesizing news sentiment and attention metrics in predicting stock prices.

Název v anglickém jazyce

Beyond Sentiment in Stock Price Prediction: Integrating News Sentiment and Investor Attention with Temporal Fusion Transformer

Popis výsledku anglicky

News sentiment is attracting considerable interest in stock market prediction, given its crucial role in shaping stock prices. Previous research has mainly focused on improving prediction accuracy by exploiting news sentiment, without adequately considering the different levels of attention that individual news articles receive. Furthermore, despite the advanced predictive capabilities of deep learning models, there has been a lack of focus on the interpretability of these models, leading to predictions that are not transparent. This study presents an innovative prediction model that integrates a FinBERT-based analysis of news sentiment and investor attention metrics with an attention-based Temporal Fusion Transformer framework. This approach not only enables highly effective forecasting, but also provides insights into the temporal dynamics that influence the stockmarket. The effectiveness of the model is demonstrated by analyzing stock price data for 41 of the largest market capitalization companies over the period 2010 to 2021. The results confirm the superiority of the proposed model over existing deep learning approaches, and the attention analysis underscores the critical role of synthesizing news sentiment and attention metrics in predicting stock prices.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

<a href="/cs/project/GA22-22586S" target="_blank" >GA22-22586S: Aspektově orientovaná analýza sentimentu finančních textů pro predikci finanční výkonnosti podniku</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

ARTIFICIAL INTELLIGENCE APPLICATIONS AND INNOVATIONS, PT III, AIAI 2024

ISBN

978-3-031-63218-1

ISSN

1868-4238

e-ISSN

1868-422X

Počet stran výsledku

14

Strana od-do

30-43

Název nakladatele

SPRINGER INTERNATIONAL PUBLISHING AG

Místo vydání

CHAM

Místo konání akce

Corfu

Datum konání akce

27. 6. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001283392400003