Forecasting of the Stock Price Using Recurrent Neural Network - Long Short-term Memory

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F21%3A50018194" target="_blank" >RIV/62690094:18450/21:50018194 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.36689/uhk/hed/2021-01-014" target="_blank" >http://dx.doi.org/10.36689/uhk/hed/2021-01-014</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.36689/uhk/hed/2021-01-014" target="_blank" >10.36689/uhk/hed/2021-01-014</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Forecasting of the Stock Price Using Recurrent Neural Network - Long Short-term Memory

Popis výsledku v původním jazyce

We employ a recurrent neural network with Long short-term memory for the task of stock price forecasting. We chose three stocks from the same sub-industry: Visa, Mastercard, and PayPal. This paper aims to test the LSTM network&apos;s prediction on stock prices and propose the best settings for selected stock price forecasting. The secondary goal is to assess how the settings differed in the case of two highly correlated stocks (Visa-Mastercard year correlation coefficient average: 0.97) and the case of only weak correlated stock (Visa-PayPal correlation coefficient average: 0.39). We tested 117 different settings of LSTM neural networks. The settings differed by the number of epochs/splits (from ten to fifty-eight by the step of four) and the range (minute, hour, and day). Our dataset was the stock price from 1.6.2020 to 15.1.2021. The best performing network has been trained on a 10-day period for Visa and 10-minute for Mastercard and PYPL. However, the differences were negligible, so we did not find the number of epochs as a key setting, unlike in the case of FOREX.

Název v anglickém jazyce

Forecasting of the Stock Price Using Recurrent Neural Network - Long Short-term Memory

Popis výsledku anglicky

We employ a recurrent neural network with Long short-term memory for the task of stock price forecasting. We chose three stocks from the same sub-industry: Visa, Mastercard, and PayPal. This paper aims to test the LSTM network&apos;s prediction on stock prices and propose the best settings for selected stock price forecasting. The secondary goal is to assess how the settings differed in the case of two highly correlated stocks (Visa-Mastercard year correlation coefficient average: 0.97) and the case of only weak correlated stock (Visa-PayPal correlation coefficient average: 0.39). We tested 117 different settings of LSTM neural networks. The settings differed by the number of epochs/splits (from ten to fifty-eight by the step of four) and the range (minute, hour, and day). Our dataset was the stock price from 1.6.2020 to 15.1.2021. The best performing network has been trained on a 10-day period for Visa and 10-minute for Mastercard and PYPL. However, the differences were negligible, so we did not find the number of epochs as a key setting, unlike in the case of FOREX.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

50201 - Economic Theory

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

HRADEC ECONOMIC DAYS, VOL 11(1)

ISBN

978-80-7435-822-7

ISSN

2464-6059

e-ISSN

2464-6067

Počet stran výsledku

10

Strana od-do

145-154

Název nakladatele

UNIV HRADEC KRALOVE

Místo vydání

HRADEC KRALOVE 3

Místo konání akce

Hradec Kralove

Datum konání akce

25. 3. 2021

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

000670596900014