An artificial neural network experiment on the prediction of the unemployment rate

Cosimo Magazzino, Marco Mele () and Mihai Mutascu ()
Additional contact information
Cosimo Magazzino: ROMA TRE - Università degli Studi Roma Tre = Roma Tre University, Azərbaycan Universiteti - Azerbaijan University [Baku]
Marco Mele: UNICUSANO - University Niccolò Cusano = Università Niccoló Cusano
Mihai Mutascu: LEO - Laboratoire d'Économie d'Orleans [2022-...] - UO - Université d'Orléans - UT - Université de Tours - UCA - Université Clermont Auvergne, Zeppelin University, UVT - Universitatea de Vest din Timișoara [România] = West University of Timișoara [Romania] = Université Ouest de Timișoara [Roumanie]

Post-Print from HAL

Abstract: This paper proposes an advanced Artificial Neural Networks (ANN) methodology with a Genetic test in order to estimate unemployment forecasting in 23 high-tech and most-developed countries over the period 1998–2016. The main findings reveal that the methodology adopted ensures an excellent accuracy of unemployment forecasting for the selected countries, allowing the analysis of the contributions of each input to unemployment estimation as well. A significant role is exerted by GDP, labor productivity, population growth, and Artificial Intelligence innovation, while inflation assumes only a secondary role. A minor contribution is also observed in Foreign Direct Investments and government size. Therefore, economic growth based on innovation in Artificial Intelligence with explicit effects on productivity, under adequate population growth, seems to drive the unemployment rate.

Date: 2025-05
References: Add references at CitEc
Citations:

Published in Journal of Policy Modeling, 2025, 47 (3), pp.471-491. ⟨10.1016/j.jpolmod.2024.10.004⟩

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

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:hal:journl:hal-05408938

DOI: 10.1016/j.jpolmod.2024.10.004

Access Statistics for this paper

More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().