Association Between Online Texts and Stock Prices

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62156489%3A43110%2F17%3A43911768" target="_blank" >RIV/62156489:43110/17:43911768 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/26867184:_____/17:N0000010

Výsledek na webu

<a href="http://mvso.cz/wp-content/uploads/2017/06/IDS_2017_Conference_Proceedings.pdf" target="_blank" >http://mvso.cz/wp-content/uploads/2017/06/IDS_2017_Conference_Proceedings.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Association Between Online Texts and Stock Prices

Popis výsledku v původním jazyce

The paper is focused on quantifying the strength of association between stock price movements and content of texts of corresponding companies. As the principal tool, machine learning based classification was used. Four different variable parameters of data preparation were used and six classifiers were applied to the data. It has been found that a classifier type and a smoothing method applied to stock price data were the most important factors. After the mentioned parameters were considered and investigated texts related to periods with significant stock price movements were separated with accuracy ranging from about 60 to 74% which demonstrates a nonrandom association between these two time series.

Název v anglickém jazyce

Association Between Online Texts and Stock Prices

Popis výsledku anglicky

The paper is focused on quantifying the strength of association between stock price movements and content of texts of corresponding companies. As the principal tool, machine learning based classification was used. Four different variable parameters of data preparation were used and six classifiers were applied to the data. It has been found that a classifier type and a smoothing method applied to stock price data were the most important factors. After the mentioned parameters were considered and investigated texts related to periods with significant stock price movements were separated with accuracy ranging from about 60 to 74% which demonstrates a nonrandom association between these two time series.

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/GA16-26353S" target="_blank" >GA16-26353S: Sentiment a jeho vliv na akciové trhy</a><br>

Návaznosti

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

Rok uplatnění

2017

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the International Scientific Conference: International Day of Science 2017. Economics, Management, Innovation

ISBN

978-80-7455-060-7

ISSN

—

e-ISSN

neuvedeno

Počet stran výsledku

7

Strana od-do

23-29

Název nakladatele

Univerzita Palackého v Olomouci

Místo vydání

Olomouc

Místo konání akce

Olomouc

Datum konání akce

25. 4. 2017

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—