Aplication of artificial neural networks for forecasting in business economy

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27510%2F19%3A10243943" target="_blank" >RIV/61989100:27510/19:10243943 - isvavai.cz</a>

Výsledek na webu

<a href="https://imes.vse.cz/wp-content/uploads/2019/07/Conference_Proceedings_IMES_2019.pdf" target="_blank" >https://imes.vse.cz/wp-content/uploads/2019/07/Conference_Proceedings_IMES_2019.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18267/pr.2019.dvo.2316.0" target="_blank" >10.18267/pr.2019.dvo.2316.0</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Aplication of artificial neural networks for forecasting in business economy

Popis výsledku v původním jazyce

The forecasting method is now a whole lot. They are often based on the specific conditions of the given time series, and their methodology is mostly the result of research in scientific centres and universities. In recent years, Artificial Intelligence has been very much discussed (hereafter AI). Implementation of AI into enterprise decision-making brings a whole host of new opportunities and challenges. One of them is certainly the use of AI in forecasting. The paper after classic models present, the AI-based model, namely the neural networks model, introduce. Subsequently, the models are applied to 166 monthly data from year 2008 to 2018. After analysing the data, forecasting ex-post is performed and evaluated according to selected accuracy indicators. After evaluating accuracy, the most accurate model for the given enterprise variables is selected and ex-ante forecasting performed. Benefit of this paper can be seen in particular in the expansion of possible forecasting methods to ensure the most accurate results of business forecasts. The evaluation of the suitability of the models is ensured by the best values of the selected accuracy measures. The paper confirms the possibilities of using the neural network method for business time series as the best model with RMSE 0.3134768. In the practice of specific businesses, the contribution can help with the selection of suitable methods for forecasting. In future research, I can focus on other forecasting methods, such as the use of other AI tools, chaos theory, fuzzy logic, or genetic algorithms. At present, the practical use of neural networks in the corporate economy in the Czech Republic is still an outlying issue. Its wider use in practice requires exploration of the use of academic and other scientific institutions. The way in which scientific knowledge can be accessed through practice can be a wider use of this tool in practice.

Název v anglickém jazyce

Aplication of artificial neural networks for forecasting in business economy

Popis výsledku anglicky

The forecasting method is now a whole lot. They are often based on the specific conditions of the given time series, and their methodology is mostly the result of research in scientific centres and universities. In recent years, Artificial Intelligence has been very much discussed (hereafter AI). Implementation of AI into enterprise decision-making brings a whole host of new opportunities and challenges. One of them is certainly the use of AI in forecasting. The paper after classic models present, the AI-based model, namely the neural networks model, introduce. Subsequently, the models are applied to 166 monthly data from year 2008 to 2018. After analysing the data, forecasting ex-post is performed and evaluated according to selected accuracy indicators. After evaluating accuracy, the most accurate model for the given enterprise variables is selected and ex-ante forecasting performed. Benefit of this paper can be seen in particular in the expansion of possible forecasting methods to ensure the most accurate results of business forecasts. The evaluation of the suitability of the models is ensured by the best values of the selected accuracy measures. The paper confirms the possibilities of using the neural network method for business time series as the best model with RMSE 0.3134768. In the practice of specific businesses, the contribution can help with the selection of suitable methods for forecasting. In future research, I can focus on other forecasting methods, such as the use of other AI tools, chaos theory, fuzzy logic, or genetic algorithms. At present, the practical use of neural networks in the corporate economy in the Czech Republic is still an outlying issue. Its wider use in practice requires exploration of the use of academic and other scientific institutions. The way in which scientific knowledge can be accessed through practice can be a wider use of this tool in practice.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

50204 - Business and management

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

IMES 2019 : Innovation Management, Entrepreneurship and Sustainability : proceedings of the 7th international conference : May 30-31, 2019, Prague

ISBN

978-80-245-2316-3

ISSN

—

e-ISSN

—

Počet stran výsledku

10

Strana od-do

359-368

Název nakladatele

Vysoká škola ekonomická v Praze

Místo vydání

Praha

Místo konání akce

Praha

Datum konání akce

30. 5. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000518586600029