MACRO-MANAGEMENT INDICES MODELED WITH ARTIFICIAL NEURAL NETWORK. INFLUENCES ON PURCHASING POWER PARITIES

Constantin Ilie and Margareta Ilie

Proceedings of the INTERNATIONAL MANAGEMENT CONFERENCE, 2021, vol. 15, issue 1, 554-563

Abstract: The present paper shows research results regarding Artificial Neural Network simulation on macroeconomics indices and their influences over purchasing power parities. The objective was the successful build, train, and testing of different types of Artificial Neural Network to determine the best structure for applications. In modeling and simulation, authors used, not only the classical indices but also, the new ones such as online companies and houses with internet connections. The method used Artificial Neural Networks in the form of feedforward and different functions and algorithms for simulating the influence between several indices over the purchasing power parities. The results showed that’s the best Artificial Neural Network hidden neurons function is tanh and the best solver four weights optimization was Adam algorithm. Applying them, the research results in absolute error smaller than 0.002 and a mean squared error smaller than 2*10-6. These results proved that the chosen Artificial Neural Networks can be applied to the problem modeled and can be used further for a greater amount of data. The small error demonstrates the efficiency of training and the possibility of using the proposed type and features of an Artificial Neural Network.

Keywords: Artificial Neural Network; decision making; macro management; simulation; purchasing power parities. (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
https://conferinta.management.ase.ro/archives/2021 ... 0IMC%202021/3_10.pdf

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:rom:mancon:v:15:y:2021:i:1:p:554-563

DOI: 10.24818/IMC/2021/03.10

Access Statistics for this article

Proceedings of the INTERNATIONAL MANAGEMENT CONFERENCE is currently edited by Ciocoiu Nadia Carmen

More articles in Proceedings of the INTERNATIONAL MANAGEMENT CONFERENCE from Faculty of Management, Academy of Economic Studies, Bucharest, Romania Contact information at EDIRC.
Bibliographic data for series maintained by Ciocoiu Nadia Carmen ().